Dr. Achim Rettinger from Karlsruhe Institute of Technology presented this today as part of the Cognitive Systems Institute Speaker Series on October 13, 2016
[David a. coley]_an_introduction_to_genetic_algori(book_fi.org)swapnatoya
This document provides an introduction to genetic algorithms. It begins with a brief overview of genetic algorithms and some of their applications, such as image processing, protein structure prediction, chip layout design, and analysis of time series data. The rest of the document covers the typical components of a genetic algorithm, including an initial population of solutions, a fitness function, operators to combine solutions and introduce mutations, and iteration of these steps over generations. Code implementations and further resources are also discussed.
The document discusses genetic algorithms, which are inspired by biological evolution. It explains that genetic algorithms use populations of candidate solutions that undergo processes of selection, crossover and mutation to evolve toward better solutions. It provides examples of representing solutions as binary strings and calculating their fitness to problems. The basic genetic algorithm is outlined as generating random populations, evaluating fitness, selecting parents for recombination, applying crossover and mutation, and iterating toward improving solutions over generations.
(1) The document describes the Service Design Thinking program at the Karlsruhe Service Research Institute.
(2) The program brings together international students and industry partners to develop innovative solutions to business problems using design thinking methodology over 9 months.
(3) Students work in small teams, guided by teaching staff, to fully understand users' needs and prototype potential solutions, presenting their work at various stages for feedback.
1. There is growing data available but lack of research on data-driven business models. Most companies plan to invest in advanced analytics.
2. The document analyzes how companies can infuse data and analytics into their business models, affecting value proposition, creation, and capturing.
3. Five patterns of data-infused business models are identified: optimized internal operations, personalized customer understanding, new value propositions, changing how value is captured, and completely new data-driven business models.
Joining Industry and Students for Cognitive Solutions at Karlsruhe Services R...diannepatricia
Gerhard Satzger, Director of the Karlsruhe Service Research Institute and two former students and IBMers, Sebastian Hirschl and Kathrin Fitzer, presention"Joining Industry and Students for Cognitive Solutions at Karlsruhe Services Research Center" as part of the Cognitive Systems Institute Speaker Series.
The Karlsruhe Service Research Institute (KSRI) is a public-private partnership located at the Karlsruhe Institute of Technology (KIT) that focuses on interdisciplinary and application-oriented research related to IT-based services and digital transformation. KSRI works with industry partners like IBM and Bosch to jointly conduct research, educate students, and innovate in areas like service systems, design, analytics and more. The partnership provides opportunities for all parties but also faces challenges in bridging academic and industry needs.
[David a. coley]_an_introduction_to_genetic_algori(book_fi.org)swapnatoya
This document provides an introduction to genetic algorithms. It begins with a brief overview of genetic algorithms and some of their applications, such as image processing, protein structure prediction, chip layout design, and analysis of time series data. The rest of the document covers the typical components of a genetic algorithm, including an initial population of solutions, a fitness function, operators to combine solutions and introduce mutations, and iteration of these steps over generations. Code implementations and further resources are also discussed.
The document discusses genetic algorithms, which are inspired by biological evolution. It explains that genetic algorithms use populations of candidate solutions that undergo processes of selection, crossover and mutation to evolve toward better solutions. It provides examples of representing solutions as binary strings and calculating their fitness to problems. The basic genetic algorithm is outlined as generating random populations, evaluating fitness, selecting parents for recombination, applying crossover and mutation, and iterating toward improving solutions over generations.
(1) The document describes the Service Design Thinking program at the Karlsruhe Service Research Institute.
(2) The program brings together international students and industry partners to develop innovative solutions to business problems using design thinking methodology over 9 months.
(3) Students work in small teams, guided by teaching staff, to fully understand users' needs and prototype potential solutions, presenting their work at various stages for feedback.
1. There is growing data available but lack of research on data-driven business models. Most companies plan to invest in advanced analytics.
2. The document analyzes how companies can infuse data and analytics into their business models, affecting value proposition, creation, and capturing.
3. Five patterns of data-infused business models are identified: optimized internal operations, personalized customer understanding, new value propositions, changing how value is captured, and completely new data-driven business models.
Joining Industry and Students for Cognitive Solutions at Karlsruhe Services R...diannepatricia
Gerhard Satzger, Director of the Karlsruhe Service Research Institute and two former students and IBMers, Sebastian Hirschl and Kathrin Fitzer, presention"Joining Industry and Students for Cognitive Solutions at Karlsruhe Services Research Center" as part of the Cognitive Systems Institute Speaker Series.
The Karlsruhe Service Research Institute (KSRI) is a public-private partnership located at the Karlsruhe Institute of Technology (KIT) that focuses on interdisciplinary and application-oriented research related to IT-based services and digital transformation. KSRI works with industry partners like IBM and Bosch to jointly conduct research, educate students, and innovate in areas like service systems, design, analytics and more. The partnership provides opportunities for all parties but also faces challenges in bridging academic and industry needs.
The document discusses two NSF-funded research projects on intelligence and security informatics:
1. A project to filter and monitor message streams to detect "new events" and changes in topics or activity levels. It describes the technical challenges and components of automatic message processing.
2. A project called HITIQA to develop high-quality interactive question answering. It describes the team members and key research issues like question semantics, human-computer dialogue, and information quality metrics.
- Systems biology uses computational approaches to produce quantitative, predictive models of biological processes by integrating math, biology, and high-throughput data.
- Eclipse technology can help by providing an extensible and customizable user interface for biologists to access modeling tools and IDEs for computational modelers, with reusable components.
- The SBSI software provides clients, a dispatcher, numerics algorithms, and a repository for systems biology modeling and optimization, with plugins for tasks like pathway editing, simulation, and data visualization.
COMPASS is a new framework that trains a latent space of diverse reinforcement learning policies to solve combinatorial optimization problems. It has two phases: (1) training phase samples the latent space and trains policies, and (2) inference phase searches the latent space within a budget to find high-performing policies. COMPASS achieves state-of-the-art results on 29 tasks, generalizes better than baselines on out-of-distribution instances, and its search strategy effectively reaches high-performance regions of the latent space.
The document summarizes the experience of a biologist in adopting an e-science approach to their work. It describes how before e-science, the biologist took an uncoordinated "spaghetti" approach using various tools without a unified strategy. The biologist then explains how adopting e-science principles like collaboration, reusable workflows, and web services helped enhance their work by allowing experts from different domains to combine their expertise. The biologist also reflects on outreach efforts to promote e-science to other researchers.
The document provides an overview of data science, artificial intelligence, and machine learning. It discusses the differences between AI and machine learning, as well as what constitutes data science. Examples are given of applying data science in healthcare to study the impact of remote patient monitoring devices and identify high-risk patients. State-of-the-art machine learning techniques like neural networks, deep learning, and deep reinforcement learning are also overviewed. Finally, the document discusses how companies are using data science and AI and provides next steps for learning and applying these fields.
In this talk I'll discuss work in biomedical image and volume segmentation and classification, as well as outcome prediction modeling from insurance claims data that I've pursued at LifeOmic here in the Triangle. In the former case datasets include radiological image volumes, retinal fundus images, and cell images created with fluorescent microscopy. The latter includes MIMIC-III data represented as FHIR objects. I'll discuss the relative challenges and advantages of doing ML locally vs. on a cloud-based platform.
The Software Sustainability Institute (SSI) provides services to help research groups sustain their software over the long term. It collaborates with groups in various fields to improve key software through advice, training, and partnerships. Case studies describe projects in fields like fusion energy, climate modeling, geospatial data, and computational chemistry. The SSI aims to promote best practices and change perceptions so software is recognized as a valuable long-term asset, not just for initial research. Sustaining software requires support for both technical aspects and community engagement over decades.
AI-SDV 2022: Accommodating the Deep Learning Revolution by a Development Proc...Dr. Haxel Consult
Word embeddings, deep learning, transformer models and other pre-trained neural language models (sometimes recently referred to as "foundational models") have fundamentally changed the way state-of-the-art systems for natural language processing and information access are built today. The "Data-to-Value" process methodology (Leidner 2013; Leidner 2022a,b) has been devised to embody best practices for the construction of natural language engineering solutions; it can assist practitioners and has also been used to transfer industrial insights into the university classroom. This talk recaps how the methodology supports engineers in building systems more consistently and then outlines the changes in the methodology to adapt it to the deep learning age. The cost and energy implications will also be discussed.
Curation-Friendly Tools for the Scientific Researcherbwestra
Presentation for Online Northwest Conference, in Corvallis Oregon, February 10, 2012.
Highlights electronic lab notebooks (ELN) and OMERO (Open Microscopy Environment) as two tools that enable researchers to better manage their research data.
Keynote on software sustainability given at the 2nd Annual Netherlands eScience Symposium, November 2014.
Based on the article
Carole Goble ,
Better Software, Better Research
Issue No.05 - Sept.-Oct. (2014 vol.18)
pp: 4-8
IEEE Computer Society
http://www.computer.org/csdl/mags/ic/2014/05/mic2014050004.pdf
http://doi.ieeecomputersociety.org/10.1109/MIC.2014.88
http://www.software.ac.uk/resources/publications/better-software-better-research
Data Science and AI in Biomedicine: The World has ChangedPhilip Bourne
This document discusses the changing landscape of data science and AI in biomedicine. Some key points:
- We are at a tipping point where data science is becoming a driver of biomedical research rather than just a tool. Biomedical researchers need to become data scientists.
- Data science is interdisciplinary and touches every field due to the rise of digital data. It requires openness, translation of findings, and consideration of responsibilities like algorithmic bias.
- Advances like AlphaFold2 show the power of large collaborative efforts combining data, computing resources, engineering, and domain expertise. This points to the need for public-private partnerships and new models of open data sharing.
- The definition of
A summary of my personal expertise and knowledge completed by a description of some of the most relevant research and developments engagements carried out so far via specific examples
Striving to Demystify Bayesian Computational ModellingMarco Wirthlin
Abstract
Bayesian approaches to computational modelling have experienced a slow, but steady gain in recognition and
usage in academia and industry alike, accompanying the growing availability of evermore powerful computing
platforms at shrinking costs. Why would one use such techniques? How are those models conceived and
implemented? Which is the recommended workflow? Why make life hard when there are P-values?
In his talk, Marco Wirthlin will first attempt an introduction to statistical notions supporting Bayesian computation and
explain the difference to the Frequentist framework. In the second half, an example of a recommended workflow is
outlined on a simple toy model, with simulated data. Live coding will be used as much as possible to illustrate
concepts on an implementational level in the R language. Ample literature and media references for self-learning
will be provided during the talk.
Context and Licence
This talk was performed in the context of the “R Lunch” on the 29 of October 2019 at the University of Geneva and
was organized by Elise Tancoigne (@tancoigne) & Xavier Adam (@xvrdm). Many thanks for inviting me! :D
Code (if any) is licenced under the BSD (3 clause), while the text licence is CC BY-NC 4.0. Any derived work has
been cited. Please contact me if you see non-attributed work (marco.wirthlin@gmail.com).
Presenter: Dr. Xin Wang, NII
Paper: https://arxiv.org/abs/2111.07725
Self-supervised speech model is a rapid progressing research topic, and many pre-trained models have been released and used in various down stream tasks. For speech anti-spoofing, most countermeasures (CMs) use signal processing algorithms to extract acoustic features for classification. In this study, we use pre-trained self-supervised speech models as the front end of spoofing CMs. We investigated different back end architectures to be combined with the self-supervised front end, the effectiveness of fine-tuning the front end, and the performance of using different pre-trained self-supervised models. Our findings showed that, when a good pre-trained front end was fine-tuned with either a shallow or a deep neural network-based back end on the ASVspoof 2019 logical access (LA) training set, the resulting CM not only achieved a low EER score on the 2019 LA test set but also significantly outperformed the baseline on the ASVspoof 2015, 2021 LA, and 2021 deepfake test sets. A sub-band analysis further demonstrated that the CM mainly used the information in a specific frequency band to discriminate the bona fide and spoofed trials across the test sets.
Industry-Academia Communication In Empirical Software EngineeringPer Runeson
This document discusses industry-academia communication in empirical software engineering. It provides context on a conference in 1968 that aimed to improve communication between industry and academia. It notes key differences in time horizons and languages between the two. Industry focuses on short-term market changes and profits, while academia focuses on long-term learning and publications. The document advocates for both sides to learn each other's languages and cultures to improve collaboration and help tear down walls between the two. It provides examples of successful collaboration projects over time that have helped improve practice.
IRJET - Automatic Lip Reading: Classification of Words and Phrases using Conv...IRJET Journal
This document presents research on developing an automatic lip reading system using convolutional neural networks. The system takes in video frames of a speaker's face without audio and classifies the words or phrases being spoken. The researchers preprocessed the data by detecting faces in video frames and cropping them. They then trained a CNN model on concatenated frames. Their model achieved 80.44% accuracy on the test set in classifying 10 words and 10 phrases from 17 speakers. The researchers concluded the model could be improved by addressing overfitting to unseen speakers with a larger dataset and regularization techniques.
This document discusses best practices for organizing computational biology projects. It recommends creating a directory structure with folders for source code, data, documentation, results and binaries/executables. Data folders should include README files explaining where the data came from. Version control is important to track changes over time. Comments and documentation will help others understand the project and allow researchers to revisit past work without reconstructing their experiments from scratch. Organizing and documenting projects thoroughly makes computational experiments more reproducible, understandable and useful to both the original researchers and others in the future.
1. The document discusses how a biologist, Marco Roos, became interested in e-science through his work in molecular and cellular biology, bioinformatics, and data integration projects.
2. Roos describes how e-science allows for collaboration between different experts and disciplines through technologies like workflows, semantic web, and virtual laboratories.
3. Roos emphasizes that e-science should empower scientists by making tools and resources easy to use, share, and build upon so that scientists can focus on scientific problems rather than technical challenges.
Investigating Crowdsourcing as an Evaluation Method for (TEL) Recommender Sy...Christoph Rensing
The document investigates using crowdsourcing as an evaluation method for recommender systems that recommend learning resources. Researchers generated recommendations from two algorithms (AScore and FolkRank) for climate change resources and evaluated them using a crowdsourced questionnaire. The results supported that AScore provided more relevant and novel resources than the baseline FolkRank algorithm, but not more diverse resources. The researchers conclude that crowdsourcing can evaluate recommender systems and plan to further analyze the collected data and improve the crowdsourcing evaluation concept.
Teaching cognitive computing with ibm watsondiannepatricia
Ralph Badinelli, Lenz Chair in the Department of Business Information Technology, Pamplin College of Business of Virginia Tech. presented "Teaching Cognitive Computing with IBM Watson" as part of the Cognitive Systems Institute Speaker Series.
Cognitive systems institute talk 8 june 2017 - v.1.0diannepatricia
José Hernández-Orallo, Full Professor, Department of Information Systems and Computation at the Universitat Politecnica de València, presentation “Evaluating Cognitive Systems: Task-oriented or Ability-oriented?” as part of the Cognitive Systems Institute Speaker Series.
More Related Content
Similar to “Towards Multi-Step Expert Advice for Cognitive Computing” - Dr. Achim Rettinger, Karlsruhe Institute of Technology
The document discusses two NSF-funded research projects on intelligence and security informatics:
1. A project to filter and monitor message streams to detect "new events" and changes in topics or activity levels. It describes the technical challenges and components of automatic message processing.
2. A project called HITIQA to develop high-quality interactive question answering. It describes the team members and key research issues like question semantics, human-computer dialogue, and information quality metrics.
- Systems biology uses computational approaches to produce quantitative, predictive models of biological processes by integrating math, biology, and high-throughput data.
- Eclipse technology can help by providing an extensible and customizable user interface for biologists to access modeling tools and IDEs for computational modelers, with reusable components.
- The SBSI software provides clients, a dispatcher, numerics algorithms, and a repository for systems biology modeling and optimization, with plugins for tasks like pathway editing, simulation, and data visualization.
COMPASS is a new framework that trains a latent space of diverse reinforcement learning policies to solve combinatorial optimization problems. It has two phases: (1) training phase samples the latent space and trains policies, and (2) inference phase searches the latent space within a budget to find high-performing policies. COMPASS achieves state-of-the-art results on 29 tasks, generalizes better than baselines on out-of-distribution instances, and its search strategy effectively reaches high-performance regions of the latent space.
The document summarizes the experience of a biologist in adopting an e-science approach to their work. It describes how before e-science, the biologist took an uncoordinated "spaghetti" approach using various tools without a unified strategy. The biologist then explains how adopting e-science principles like collaboration, reusable workflows, and web services helped enhance their work by allowing experts from different domains to combine their expertise. The biologist also reflects on outreach efforts to promote e-science to other researchers.
The document provides an overview of data science, artificial intelligence, and machine learning. It discusses the differences between AI and machine learning, as well as what constitutes data science. Examples are given of applying data science in healthcare to study the impact of remote patient monitoring devices and identify high-risk patients. State-of-the-art machine learning techniques like neural networks, deep learning, and deep reinforcement learning are also overviewed. Finally, the document discusses how companies are using data science and AI and provides next steps for learning and applying these fields.
In this talk I'll discuss work in biomedical image and volume segmentation and classification, as well as outcome prediction modeling from insurance claims data that I've pursued at LifeOmic here in the Triangle. In the former case datasets include radiological image volumes, retinal fundus images, and cell images created with fluorescent microscopy. The latter includes MIMIC-III data represented as FHIR objects. I'll discuss the relative challenges and advantages of doing ML locally vs. on a cloud-based platform.
The Software Sustainability Institute (SSI) provides services to help research groups sustain their software over the long term. It collaborates with groups in various fields to improve key software through advice, training, and partnerships. Case studies describe projects in fields like fusion energy, climate modeling, geospatial data, and computational chemistry. The SSI aims to promote best practices and change perceptions so software is recognized as a valuable long-term asset, not just for initial research. Sustaining software requires support for both technical aspects and community engagement over decades.
AI-SDV 2022: Accommodating the Deep Learning Revolution by a Development Proc...Dr. Haxel Consult
Word embeddings, deep learning, transformer models and other pre-trained neural language models (sometimes recently referred to as "foundational models") have fundamentally changed the way state-of-the-art systems for natural language processing and information access are built today. The "Data-to-Value" process methodology (Leidner 2013; Leidner 2022a,b) has been devised to embody best practices for the construction of natural language engineering solutions; it can assist practitioners and has also been used to transfer industrial insights into the university classroom. This talk recaps how the methodology supports engineers in building systems more consistently and then outlines the changes in the methodology to adapt it to the deep learning age. The cost and energy implications will also be discussed.
Curation-Friendly Tools for the Scientific Researcherbwestra
Presentation for Online Northwest Conference, in Corvallis Oregon, February 10, 2012.
Highlights electronic lab notebooks (ELN) and OMERO (Open Microscopy Environment) as two tools that enable researchers to better manage their research data.
Keynote on software sustainability given at the 2nd Annual Netherlands eScience Symposium, November 2014.
Based on the article
Carole Goble ,
Better Software, Better Research
Issue No.05 - Sept.-Oct. (2014 vol.18)
pp: 4-8
IEEE Computer Society
http://www.computer.org/csdl/mags/ic/2014/05/mic2014050004.pdf
http://doi.ieeecomputersociety.org/10.1109/MIC.2014.88
http://www.software.ac.uk/resources/publications/better-software-better-research
Data Science and AI in Biomedicine: The World has ChangedPhilip Bourne
This document discusses the changing landscape of data science and AI in biomedicine. Some key points:
- We are at a tipping point where data science is becoming a driver of biomedical research rather than just a tool. Biomedical researchers need to become data scientists.
- Data science is interdisciplinary and touches every field due to the rise of digital data. It requires openness, translation of findings, and consideration of responsibilities like algorithmic bias.
- Advances like AlphaFold2 show the power of large collaborative efforts combining data, computing resources, engineering, and domain expertise. This points to the need for public-private partnerships and new models of open data sharing.
- The definition of
A summary of my personal expertise and knowledge completed by a description of some of the most relevant research and developments engagements carried out so far via specific examples
Striving to Demystify Bayesian Computational ModellingMarco Wirthlin
Abstract
Bayesian approaches to computational modelling have experienced a slow, but steady gain in recognition and
usage in academia and industry alike, accompanying the growing availability of evermore powerful computing
platforms at shrinking costs. Why would one use such techniques? How are those models conceived and
implemented? Which is the recommended workflow? Why make life hard when there are P-values?
In his talk, Marco Wirthlin will first attempt an introduction to statistical notions supporting Bayesian computation and
explain the difference to the Frequentist framework. In the second half, an example of a recommended workflow is
outlined on a simple toy model, with simulated data. Live coding will be used as much as possible to illustrate
concepts on an implementational level in the R language. Ample literature and media references for self-learning
will be provided during the talk.
Context and Licence
This talk was performed in the context of the “R Lunch” on the 29 of October 2019 at the University of Geneva and
was organized by Elise Tancoigne (@tancoigne) & Xavier Adam (@xvrdm). Many thanks for inviting me! :D
Code (if any) is licenced under the BSD (3 clause), while the text licence is CC BY-NC 4.0. Any derived work has
been cited. Please contact me if you see non-attributed work (marco.wirthlin@gmail.com).
Presenter: Dr. Xin Wang, NII
Paper: https://arxiv.org/abs/2111.07725
Self-supervised speech model is a rapid progressing research topic, and many pre-trained models have been released and used in various down stream tasks. For speech anti-spoofing, most countermeasures (CMs) use signal processing algorithms to extract acoustic features for classification. In this study, we use pre-trained self-supervised speech models as the front end of spoofing CMs. We investigated different back end architectures to be combined with the self-supervised front end, the effectiveness of fine-tuning the front end, and the performance of using different pre-trained self-supervised models. Our findings showed that, when a good pre-trained front end was fine-tuned with either a shallow or a deep neural network-based back end on the ASVspoof 2019 logical access (LA) training set, the resulting CM not only achieved a low EER score on the 2019 LA test set but also significantly outperformed the baseline on the ASVspoof 2015, 2021 LA, and 2021 deepfake test sets. A sub-band analysis further demonstrated that the CM mainly used the information in a specific frequency band to discriminate the bona fide and spoofed trials across the test sets.
Industry-Academia Communication In Empirical Software EngineeringPer Runeson
This document discusses industry-academia communication in empirical software engineering. It provides context on a conference in 1968 that aimed to improve communication between industry and academia. It notes key differences in time horizons and languages between the two. Industry focuses on short-term market changes and profits, while academia focuses on long-term learning and publications. The document advocates for both sides to learn each other's languages and cultures to improve collaboration and help tear down walls between the two. It provides examples of successful collaboration projects over time that have helped improve practice.
IRJET - Automatic Lip Reading: Classification of Words and Phrases using Conv...IRJET Journal
This document presents research on developing an automatic lip reading system using convolutional neural networks. The system takes in video frames of a speaker's face without audio and classifies the words or phrases being spoken. The researchers preprocessed the data by detecting faces in video frames and cropping them. They then trained a CNN model on concatenated frames. Their model achieved 80.44% accuracy on the test set in classifying 10 words and 10 phrases from 17 speakers. The researchers concluded the model could be improved by addressing overfitting to unseen speakers with a larger dataset and regularization techniques.
This document discusses best practices for organizing computational biology projects. It recommends creating a directory structure with folders for source code, data, documentation, results and binaries/executables. Data folders should include README files explaining where the data came from. Version control is important to track changes over time. Comments and documentation will help others understand the project and allow researchers to revisit past work without reconstructing their experiments from scratch. Organizing and documenting projects thoroughly makes computational experiments more reproducible, understandable and useful to both the original researchers and others in the future.
1. The document discusses how a biologist, Marco Roos, became interested in e-science through his work in molecular and cellular biology, bioinformatics, and data integration projects.
2. Roos describes how e-science allows for collaboration between different experts and disciplines through technologies like workflows, semantic web, and virtual laboratories.
3. Roos emphasizes that e-science should empower scientists by making tools and resources easy to use, share, and build upon so that scientists can focus on scientific problems rather than technical challenges.
Investigating Crowdsourcing as an Evaluation Method for (TEL) Recommender Sy...Christoph Rensing
The document investigates using crowdsourcing as an evaluation method for recommender systems that recommend learning resources. Researchers generated recommendations from two algorithms (AScore and FolkRank) for climate change resources and evaluated them using a crowdsourced questionnaire. The results supported that AScore provided more relevant and novel resources than the baseline FolkRank algorithm, but not more diverse resources. The researchers conclude that crowdsourcing can evaluate recommender systems and plan to further analyze the collected data and improve the crowdsourcing evaluation concept.
Similar to “Towards Multi-Step Expert Advice for Cognitive Computing” - Dr. Achim Rettinger, Karlsruhe Institute of Technology (20)
Teaching cognitive computing with ibm watsondiannepatricia
Ralph Badinelli, Lenz Chair in the Department of Business Information Technology, Pamplin College of Business of Virginia Tech. presented "Teaching Cognitive Computing with IBM Watson" as part of the Cognitive Systems Institute Speaker Series.
Cognitive systems institute talk 8 june 2017 - v.1.0diannepatricia
José Hernández-Orallo, Full Professor, Department of Information Systems and Computation at the Universitat Politecnica de València, presentation “Evaluating Cognitive Systems: Task-oriented or Ability-oriented?” as part of the Cognitive Systems Institute Speaker Series.
Building Compassionate Conversational Systemsdiannepatricia
Rama Akkiraju, Distinguished Engineer and Master Inventor at IBM, presention "Building Compassionate Conversational Systems" as part of the Cognitive Systems Institute Speaker Series.
“Artificial Intelligence, Cognitive Computing and Innovating in Practice”diannepatricia
Cristina Mele, Full Professor of Management at the University of Napoli “Federico II”, presentation as part of Cognitive Systems Institute Speaker Series
Eric Manser and Will Scott from IBM Research, presentation on "Cognitive Insights Drive Self-driving Accessibility" as part of the Cognitive Systems Institute Speaker Series
Roberto Sicconi and Malgorzata (Maggie) Stys, founders of TeleLingo, presented "AI in the Car" as part of the Cognitive Systems Institute Speaker Series.
“Semantic PDF Processing & Document Representation”diannepatricia
Sridhar Iyengar, IBM Distinguished Engineer at the IBM T. J. Watson Research Center, presention “Semantic PDF Processing & Document Representation” as part of the Cognitive Systems Institute Group Speaker Series.
170330 cognitive systems institute speaker series mark sherman - watson pr...diannepatricia
Dr. Mark Sherman, Director of the Cyber Security Foundations group at CERT within CMU’s Software Engineering Institute. , presention “Experiences Developing an IBM Watson Cognitive Processing Application to Support Q&A of Application Security Diagnostics” as part of the Cognitive Systems Institute Speaker Series.
“Fairness Cases as an Accelerant and Enabler for Cognitive Assistance Adoption”diannepatricia
Chuck Howell, Chief Engineer for Intelligence Programs and Integration at the MITRE Corporation, presentation “Fairness Cases as an Accelerant and Enabler for Cognitive Assistance Adoption” as part of the Cognitive Systems Institute Speaker Series.
From complex Systems to Networks: Discovering and Modeling the Correct Network"diannepatricia
This document discusses representing complex systems as higher-order networks (HON) to more accurately model dependencies. Conventionally, networks represent single entities at nodes, but HON breaks nodes into higher-order components carrying different relationship types. This captures dependencies beyond first order in a scalable way. The document presents applications of HON, including more accurately clustering global shipping patterns and ranking web pages based on clickstreams. HON provides a general framework for network analysis tasks like ranking, clustering and link prediction across domains involving complex trajectories, information flow, and disease spread.
Developing Cognitive Systems to Support Team Cognitiondiannepatricia
Steve Fiore from the University of Central Florida presented “Developing Cognitive Systems to Support Team Cognition” as part of the Cognitive Systems Institute Speaker Series
Kevin Sullivan from the University of Virginia presented: "Cyber-Social Learning Systems: Take-Aways from First Community Computing Consortium Workshop on Cyber-Social Learning Systems" as part of the Cognitive Systems Institute Speaker Series.
“IT Technology Trends in 2017… and Beyond”diannepatricia
William Chamberlin, IBM Distinguished Market Intelligence Professional, presented “IT Technology Trends in 2017… and Beyond” as part of the Cognitive Systems Institute Speaker Series on January 26, 2017.
Grady Booch proposes embodied cognition as placing Watson's cognitive capabilities into physical robots, avatars, spaces and objects. This would allow Watson to perceive the world through senses like vision and touch, and interact with it through movement and manipulation. The goal is to augment human abilities by giving Watson capabilities like seeing a patient's full medical condition or feeling the flow of a supply chain. Booch later outlines an "Self" architecture intended to power embodied cognitive systems with capabilities like learning, reasoning about others, and both involuntary and voluntary behaviors.
Kate is a machine intelligence platform that uses context aware learning to enable robots to walk farther in an unsupervised manner. Kate uses a biological architecture with a central pattern generator to coordinate actuation and contextual control to predict patterns and provide mitigation. In initial simulations, Kate was able to walk 8 times farther using context aware learning compared to without. Kate detects anomalies in its walking patterns and is able to mitigate issues to continue walking. This approach shows potential for using unsupervised learning from large correlated robot datasets to improve mobility.
1) Cognitive computing technologies can help address aging-related issues as over 65 populations increase in countries like Japan.
2) IBM Research has conducted extensive eldercare research including elderly vision simulation, accessibility studies, and conversation-based sensing to monitor health and provide family updates.
3) Future focus areas include using social, sensing and brain data with AI assistants to help the elderly live independently for longer through intelligent assistance, accessibility improvements, and early detection of cognitive decline.
The document discusses the development of cognitive assistants to help visually impaired people access real-world information and navigate the world. It describes technologies like localization, object recognition, mapping, and voice interaction that cognitive assistants can leverage. The goal is for assistants to augment human abilities by recognizing environments, objects, and providing contextual information. The document outlines a research project to develop such a cognitive navigation assistant and argues that accessibility needs have historically spurred innovations that become widely useful.
Monitoring and Managing Anomaly Detection on OpenShift.pdfTosin Akinosho
Monitoring and Managing Anomaly Detection on OpenShift
Overview
Dive into the world of anomaly detection on edge devices with our comprehensive hands-on tutorial. This SlideShare presentation will guide you through the entire process, from data collection and model training to edge deployment and real-time monitoring. Perfect for those looking to implement robust anomaly detection systems on resource-constrained IoT/edge devices.
Key Topics Covered
1. Introduction to Anomaly Detection
- Understand the fundamentals of anomaly detection and its importance in identifying unusual behavior or failures in systems.
2. Understanding Edge (IoT)
- Learn about edge computing and IoT, and how they enable real-time data processing and decision-making at the source.
3. What is ArgoCD?
- Discover ArgoCD, a declarative, GitOps continuous delivery tool for Kubernetes, and its role in deploying applications on edge devices.
4. Deployment Using ArgoCD for Edge Devices
- Step-by-step guide on deploying anomaly detection models on edge devices using ArgoCD.
5. Introduction to Apache Kafka and S3
- Explore Apache Kafka for real-time data streaming and Amazon S3 for scalable storage solutions.
6. Viewing Kafka Messages in the Data Lake
- Learn how to view and analyze Kafka messages stored in a data lake for better insights.
7. What is Prometheus?
- Get to know Prometheus, an open-source monitoring and alerting toolkit, and its application in monitoring edge devices.
8. Monitoring Application Metrics with Prometheus
- Detailed instructions on setting up Prometheus to monitor the performance and health of your anomaly detection system.
9. What is Camel K?
- Introduction to Camel K, a lightweight integration framework built on Apache Camel, designed for Kubernetes.
10. Configuring Camel K Integrations for Data Pipelines
- Learn how to configure Camel K for seamless data pipeline integrations in your anomaly detection workflow.
11. What is a Jupyter Notebook?
- Overview of Jupyter Notebooks, an open-source web application for creating and sharing documents with live code, equations, visualizations, and narrative text.
12. Jupyter Notebooks with Code Examples
- Hands-on examples and code snippets in Jupyter Notebooks to help you implement and test anomaly detection models.
HCL Notes and Domino License Cost Reduction in the World of DLAUpanagenda
Webinar Recording: https://www.panagenda.com/webinars/hcl-notes-and-domino-license-cost-reduction-in-the-world-of-dlau/
The introduction of DLAU and the CCB & CCX licensing model caused quite a stir in the HCL community. As a Notes and Domino customer, you may have faced challenges with unexpected user counts and license costs. You probably have questions on how this new licensing approach works and how to benefit from it. Most importantly, you likely have budget constraints and want to save money where possible. Don’t worry, we can help with all of this!
We’ll show you how to fix common misconfigurations that cause higher-than-expected user counts, and how to identify accounts which you can deactivate to save money. There are also frequent patterns that can cause unnecessary cost, like using a person document instead of a mail-in for shared mailboxes. We’ll provide examples and solutions for those as well. And naturally we’ll explain the new licensing model.
Join HCL Ambassador Marc Thomas in this webinar with a special guest appearance from Franz Walder. It will give you the tools and know-how to stay on top of what is going on with Domino licensing. You will be able lower your cost through an optimized configuration and keep it low going forward.
These topics will be covered
- Reducing license cost by finding and fixing misconfigurations and superfluous accounts
- How do CCB and CCX licenses really work?
- Understanding the DLAU tool and how to best utilize it
- Tips for common problem areas, like team mailboxes, functional/test users, etc
- Practical examples and best practices to implement right away
In the realm of cybersecurity, offensive security practices act as a critical shield. By simulating real-world attacks in a controlled environment, these techniques expose vulnerabilities before malicious actors can exploit them. This proactive approach allows manufacturers to identify and fix weaknesses, significantly enhancing system security.
This presentation delves into the development of a system designed to mimic Galileo's Open Service signal using software-defined radio (SDR) technology. We'll begin with a foundational overview of both Global Navigation Satellite Systems (GNSS) and the intricacies of digital signal processing.
The presentation culminates in a live demonstration. We'll showcase the manipulation of Galileo's Open Service pilot signal, simulating an attack on various software and hardware systems. This practical demonstration serves to highlight the potential consequences of unaddressed vulnerabilities, emphasizing the importance of offensive security practices in safeguarding critical infrastructure.
Taking AI to the Next Level in Manufacturing.pdfssuserfac0301
Read Taking AI to the Next Level in Manufacturing to gain insights on AI adoption in the manufacturing industry, such as:
1. How quickly AI is being implemented in manufacturing.
2. Which barriers stand in the way of AI adoption.
3. How data quality and governance form the backbone of AI.
4. Organizational processes and structures that may inhibit effective AI adoption.
6. Ideas and approaches to help build your organization's AI strategy.
Introduction of Cybersecurity with OSS at Code Europe 2024Hiroshi SHIBATA
I develop the Ruby programming language, RubyGems, and Bundler, which are package managers for Ruby. Today, I will introduce how to enhance the security of your application using open-source software (OSS) examples from Ruby and RubyGems.
The first topic is CVE (Common Vulnerabilities and Exposures). I have published CVEs many times. But what exactly is a CVE? I'll provide a basic understanding of CVEs and explain how to detect and handle vulnerabilities in OSS.
Next, let's discuss package managers. Package managers play a critical role in the OSS ecosystem. I'll explain how to manage library dependencies in your application.
I'll share insights into how the Ruby and RubyGems core team works to keep our ecosystem safe. By the end of this talk, you'll have a better understanding of how to safeguard your code.
5th LF Energy Power Grid Model Meet-up SlidesDanBrown980551
5th Power Grid Model Meet-up
It is with great pleasure that we extend to you an invitation to the 5th Power Grid Model Meet-up, scheduled for 6th June 2024. This event will adopt a hybrid format, allowing participants to join us either through an online Mircosoft Teams session or in person at TU/e located at Den Dolech 2, Eindhoven, Netherlands. The meet-up will be hosted by Eindhoven University of Technology (TU/e), a research university specializing in engineering science & technology.
Power Grid Model
The global energy transition is placing new and unprecedented demands on Distribution System Operators (DSOs). Alongside upgrades to grid capacity, processes such as digitization, capacity optimization, and congestion management are becoming vital for delivering reliable services.
Power Grid Model is an open source project from Linux Foundation Energy and provides a calculation engine that is increasingly essential for DSOs. It offers a standards-based foundation enabling real-time power systems analysis, simulations of electrical power grids, and sophisticated what-if analysis. In addition, it enables in-depth studies and analysis of the electrical power grid’s behavior and performance. This comprehensive model incorporates essential factors such as power generation capacity, electrical losses, voltage levels, power flows, and system stability.
Power Grid Model is currently being applied in a wide variety of use cases, including grid planning, expansion, reliability, and congestion studies. It can also help in analyzing the impact of renewable energy integration, assessing the effects of disturbances or faults, and developing strategies for grid control and optimization.
What to expect
For the upcoming meetup we are organizing, we have an exciting lineup of activities planned:
-Insightful presentations covering two practical applications of the Power Grid Model.
-An update on the latest advancements in Power Grid -Model technology during the first and second quarters of 2024.
-An interactive brainstorming session to discuss and propose new feature requests.
-An opportunity to connect with fellow Power Grid Model enthusiasts and users.
Have you ever been confused by the myriad of choices offered by AWS for hosting a website or an API?
Lambda, Elastic Beanstalk, Lightsail, Amplify, S3 (and more!) can each host websites + APIs. But which one should we choose?
Which one is cheapest? Which one is fastest? Which one will scale to meet our needs?
Join me in this session as we dive into each AWS hosting service to determine which one is best for your scenario and explain why!
Ivanti’s Patch Tuesday breakdown goes beyond patching your applications and brings you the intelligence and guidance needed to prioritize where to focus your attention first. Catch early analysis on our Ivanti blog, then join industry expert Chris Goettl for the Patch Tuesday Webinar Event. There we’ll do a deep dive into each of the bulletins and give guidance on the risks associated with the newly-identified vulnerabilities.
For the full video of this presentation, please visit: https://www.edge-ai-vision.com/2024/06/temporal-event-neural-networks-a-more-efficient-alternative-to-the-transformer-a-presentation-from-brainchip/
Chris Jones, Director of Product Management at BrainChip , presents the “Temporal Event Neural Networks: A More Efficient Alternative to the Transformer” tutorial at the May 2024 Embedded Vision Summit.
The expansion of AI services necessitates enhanced computational capabilities on edge devices. Temporal Event Neural Networks (TENNs), developed by BrainChip, represent a novel and highly efficient state-space network. TENNs demonstrate exceptional proficiency in handling multi-dimensional streaming data, facilitating advancements in object detection, action recognition, speech enhancement and language model/sequence generation. Through the utilization of polynomial-based continuous convolutions, TENNs streamline models, expedite training processes and significantly diminish memory requirements, achieving notable reductions of up to 50x in parameters and 5,000x in energy consumption compared to prevailing methodologies like transformers.
Integration with BrainChip’s Akida neuromorphic hardware IP further enhances TENNs’ capabilities, enabling the realization of highly capable, portable and passively cooled edge devices. This presentation delves into the technical innovations underlying TENNs, presents real-world benchmarks, and elucidates how this cutting-edge approach is positioned to revolutionize edge AI across diverse applications.
HCL Notes und Domino Lizenzkostenreduzierung in der Welt von DLAUpanagenda
Webinar Recording: https://www.panagenda.com/webinars/hcl-notes-und-domino-lizenzkostenreduzierung-in-der-welt-von-dlau/
DLAU und die Lizenzen nach dem CCB- und CCX-Modell sind für viele in der HCL-Community seit letztem Jahr ein heißes Thema. Als Notes- oder Domino-Kunde haben Sie vielleicht mit unerwartet hohen Benutzerzahlen und Lizenzgebühren zu kämpfen. Sie fragen sich vielleicht, wie diese neue Art der Lizenzierung funktioniert und welchen Nutzen sie Ihnen bringt. Vor allem wollen Sie sicherlich Ihr Budget einhalten und Kosten sparen, wo immer möglich. Das verstehen wir und wir möchten Ihnen dabei helfen!
Wir erklären Ihnen, wie Sie häufige Konfigurationsprobleme lösen können, die dazu führen können, dass mehr Benutzer gezählt werden als nötig, und wie Sie überflüssige oder ungenutzte Konten identifizieren und entfernen können, um Geld zu sparen. Es gibt auch einige Ansätze, die zu unnötigen Ausgaben führen können, z. B. wenn ein Personendokument anstelle eines Mail-Ins für geteilte Mailboxen verwendet wird. Wir zeigen Ihnen solche Fälle und deren Lösungen. Und natürlich erklären wir Ihnen das neue Lizenzmodell.
Nehmen Sie an diesem Webinar teil, bei dem HCL-Ambassador Marc Thomas und Gastredner Franz Walder Ihnen diese neue Welt näherbringen. Es vermittelt Ihnen die Tools und das Know-how, um den Überblick zu bewahren. Sie werden in der Lage sein, Ihre Kosten durch eine optimierte Domino-Konfiguration zu reduzieren und auch in Zukunft gering zu halten.
Diese Themen werden behandelt
- Reduzierung der Lizenzkosten durch Auffinden und Beheben von Fehlkonfigurationen und überflüssigen Konten
- Wie funktionieren CCB- und CCX-Lizenzen wirklich?
- Verstehen des DLAU-Tools und wie man es am besten nutzt
- Tipps für häufige Problembereiche, wie z. B. Team-Postfächer, Funktions-/Testbenutzer usw.
- Praxisbeispiele und Best Practices zum sofortigen Umsetzen
How to Interpret Trends in the Kalyan Rajdhani Mix Chart.pdfChart Kalyan
A Mix Chart displays historical data of numbers in a graphical or tabular form. The Kalyan Rajdhani Mix Chart specifically shows the results of a sequence of numbers over different periods.
Generating privacy-protected synthetic data using Secludy and MilvusZilliz
During this demo, the founders of Secludy will demonstrate how their system utilizes Milvus to store and manipulate embeddings for generating privacy-protected synthetic data. Their approach not only maintains the confidentiality of the original data but also enhances the utility and scalability of LLMs under privacy constraints. Attendees, including machine learning engineers, data scientists, and data managers, will witness first-hand how Secludy's integration with Milvus empowers organizations to harness the power of LLMs securely and efficiently.
Programming Foundation Models with DSPy - Meetup SlidesZilliz
Prompting language models is hard, while programming language models is easy. In this talk, I will discuss the state-of-the-art framework DSPy for programming foundation models with its powerful optimizers and runtime constraint system.
SAP S/4 HANA sourcing and procurement to Public cloud
“Towards Multi-Step Expert Advice for Cognitive Computing” - Dr. Achim Rettinger, Karlsruhe Institute of Technology
1. KIT – Karlsruhe Institute of Technology
INSTITUTE OF APPLIED INFORMATICS ANDFORMAL DESCRIPTION METHODS (AIFB)
www.kit.edu
Towards Multi-Step Expert Advice for Cognitive Computing
Achim Rettinger (rettinger@kit.edu)
Cognitive Systems Institute Speaker Series, October/13/2016
2. Institute of Applied Informatics and
Formal Description Methods
2
My Research Group
Media Channel
Analytics
Healthcare
Analytics
KIT
• Former University
of Karlsruhe,
Germany
• 24.800 students
• 9.500 employees
AIFB
• Research Group
Web Science and
Knowledge
Managment
• Prof. Studer and
Prof. Sure-Vetter
KSRI
• Industry-on-
campus model
• Prof. Satzger
3. Institute of Applied Informatics and
Formal Description Methods
3
Our Research
Cross-Lingual
Technologies
Cross-Modal
Technologies
Language A Language B
DiCaprio
appeare
d in
Titanic
DiCaprio
spielt in
Titanic
(Mogadala et al. 2015)
instances of modalities present in the documents. To reduce the c
we assume a multi-modal document Di = (T ext, Media) to contai
media item either an image, video or audio embedded with a text desc
collection Cj = {D1, D2...Di...Dn} of these documents in different lang
{LC1 , LC2 ...LCj ...LCm } are spread across web. Formally, our research
to find a cross-modal semantically similar document across language
LCo using unsupervised similarity measures on low-dimension correla
representation. Figure 2 shows broad visualization of the approach.
Fig. 2. Correlated Space Retrieval
(Zhang et al. 2014)
4. Institute of Applied Informatics and
Formal Description Methods
4
Our Research
Semantic Search Entity Summarization
Fig. 1. Automatically annotated excerpt of a Wikipedia article9
and the summaClient
knowledge panel with a summary by LinkSUM.
that can be enabled at the top of each page. Other proprietary solutions include
the Bing Knowledge Widget6
and Ontotext’s Now7
. Most of the proprietary
solutions are highly customized and the annotation and knowledge panel parts
are often strongly connected.
4 Summary
With ELES, we propose loose coupling between automatic entity linking and en-
tity summarization systems via ITS 2.0. We exemplify the lightweight integration
approach with the applications DBpedia Spotlight and the qSUM method of the
SUMMA entity summarization interface.
Filter for
Multiple
Entities
Constan
t Stream
(Zhang et at. 2016) (Thalhammer et al. 2016)
5. Institute of Applied Informatics and
Formal Description Methods
5
Our Innovation Projects
LiMexLiMe – crossLingual crossMedia knowledge extraction
http://xlime.eu
Augment with
related content
from news and
social media
Semantic
Search across
content in
channels
Supported by
6. Institute of Applied Informatics and
Formal Description Methods
6
“Watson Seminar” supported by IBM Academic Initiative
Our Teaching
▪ Create a system that identifies
the relationship between two
randomly given characters
Expectations to final solution
7. Institute of Applied Informatics and
Formal Description Methods
7
TOWARDS
MULTI-STEP EXPERT ADVICE
FOR COGNITIVE COMPUTING
Joint work with Patrick Philipp
8. Institute of Applied Informatics and
Formal Description Methods
8
Many tasks comprise multiple steps …
Step 1 Step 2 Step n…
9. Institute of Applied Informatics and
Formal Description Methods
9
Medical Assistance
Brain
Stripping
Brain
Registration
Robust
Brain
Normalization
Normal
Brain
Normalization
Tumor
Segmentation
Map
Generation
Tumor
Prediction
Tumor Progression Mapping
(Philipp et al. 2015)
10. Institute of Applied Informatics and
Formal Description Methods
10
Natural Language Processing
Named Entity
Recognition
Named Entity
Linking
Entity Disambiguation
WebofDocuments
WebofThings
11. Institute of Applied Informatics and
Formal Description Methods
11
Multiple “experts“ might be available …
Step 1 Step 2 Step n…
Expert 1
Expert 2
Expert
m
Expert 1
Expert 2
Expert
m
Expert 1
Expert 2
Expert
m
…
…
…
12. Institute of Applied Informatics and
Formal Description Methods
12
Natural Language Processing
Named Entity
Recognition
Named Entity
Linking
Entity Disambiguation - Example
FOX
Stanford
Tagger
X-LISA
POS Rules
…
AGDISTIS
AIDA
X-LISA
Disambiguator
…
13. Institute of Applied Informatics and
Formal Description Methods
13
Develop robust approaches given various data distributions
NLP: News articles, social media, blogs, …
Medical Assistance: Patients of different departments, scans taken with different
machines by different people
à Many Machine Learning techniques oversimplify as they assume data
to be independent and identically distributed (i.i.d.)
Multiple interpretation steps render brute force approaches
impractical
Number of possible alternatives grow fast over multiple steps
Potential (continuous-) parameters have to be set
Different kinds of additional constraints might be set
Execution / query budgets: Not all experts can be asked
Time budgets: A solution has to be found in a predefined time frame
à Learn behavior of experts with as few training samples as possible
and transfer knowledge among different training datasets
Various Challenges
14. Institute of Applied Informatics and
Formal Description Methods
14
Natural Language Processing
Can be applied to natural language processing tasks
E.g. named entity recognition and –disambiguation pipeline
Hypothesis generation and evaluation
Score outputs of experts
Adapt weight over time
Dynamic learning
Learn weights for each expert given a specific context
Adapt expert choices given a specific context
Incrementally improves with experience
Connection to
IBM Watson‘s Cognitive Computing Capabilities
15. Institute of Applied Informatics and
Formal Description Methods
15
(Budgeted-) Decision Making with Expert Advice (Cesa-Bianchi et al.
1997, Amin et al. 2015)
Adversarial (non i.i.d.) setting with potential budgets
Best expert / subset of experts need to be found
(Contextual-) Bandits (e.g. Auer et al. 2002)
Approaches for adversarial and i.i.d. settings available
Only one action can be played, no feedback for the rest
A high-dimensional context might be given to generalize
(Contextual-) Markov Decision Processes (Puterman 1996,
Krishnamurthy et al. 2016 ) for Reinforcement Learning
Multi-stage contextual bandit with different context spaces
Only intractable solutions with good theoretical performance guarantees exist
Connection to Decision Making Theory
16. Institute of Applied Informatics and
Formal Description Methods
16
Problem Formalization –
Entity Disambiguation Example
!
"!
!
Michael
Jordan
basket
ball
$!
!
$%
!
!
"!
!
$!
%
$%
%
!
"!
! !
"!
!!
"!
!Michael
Jordan
à
NE
basketball
à
NE
Michael
Jordan
à
NE
basket
ball
à
NIL
!
"!
!Michael
Jordan
à
dbpedia:
Michael_J
ordan
basket
ball
à
NIL
+1
Michael
Jordan
à
NE
basket
ball
à
NIL
basket
ball
à
NIL
Michael
Jordan
à
dbpedia:
Michael_J
ordan
17. Institute of Applied Informatics and
Formal Description Methods
17
Probabilistic Soft Logic (PSL)
PSL (Kimmig et al. 2012) is a template language to instantiate a Hinge
Loss Markov Random Field (HL-MRF) (Bach et al. 2012)
0.3: *+,$-. /, 1 ∧ 345$"64+ 1, 7 ≫ 345$"64+(/, 7),
0.8: "<4="$ /, 1 ∧ 345$"64+ 1, 7 ≫ 345$"64+(/, 7)
Given such PSL rules and observations (data), we can infer the unknown
truth values (atoms)
Our Idea: Certain sequences of experts perform better on certain
decision candidates
Introduce a set of PSL rules that describes the dependencies between
experts and decision candidates in a specific state
Collect observations of executions of the pipeline
Probabilistic inference will give you the weights telling you how to
execute experts in each state
18. Institute of Applied Informatics and
Formal Description Methods
18
PSL Rules for Multi-Step Learning
>!
?@!
>%
?@!
>!
?
>%
?
>A
?
!
B!
?@!
%
B!
?@!
!
B!
?
19. Institute of Applied Informatics and
Formal Description Methods
19
PSL Rules for Multi-Step Learning
>!
?@!
>%
?@!
>!
?
>%
?
>A
?
!
B!
?@!
%
B!
?@!
!
B!
?
Hypothesis / Locality / Weight / Value
20. Institute of Applied Informatics and
Formal Description Methods
20
PSL Rules for Multi-Step Learning
>!
?@!
>%
?@!
>!
?
>%
?
>A
?
!
B!
?@!
%
B!
?@!
%
B!
?
Hypothesis / Locality / Weight / Value
C!.!: D4EFG,5H >, B => K$,Lℎ5(>, B)
C1.2: K$,Lℎ5(>, B!) ∧ PH<45ℎ$"," >, B!, B% => QFG=$(B%)
21. Institute of Applied Informatics and
Formal Description Methods
21
PSL Rules for Multi-Step Learning
>!
?@!
>%
?@!
>!
?
>%
?
>A
?
!
B!
?@!
%
B!
?@!
!
B!
?
Independence
22. Institute of Applied Informatics and
Formal Description Methods
22
PSL Rules for Multi-Step Learning
>!
?@!
>%
?@!
>!
?
>%
?
>A
?
!
B!
?@!
%
B!
?@!
!
B!
?
Independence / Combination
C2: R-.$<$-.$-5 >!, >%, B => K$,Lℎ5(>!, B)
23. Institute of Applied Informatics and
Formal Description Methods
23
PSL Rules for Multi-Step Learning
>!
?@!
>%
?@!
>!
?
>%
?
>A
?
!
B!
?@!
%
B!
?@!
!
B!
?
Robustness / Future Reward
24. Institute of Applied Informatics and
Formal Description Methods
24
PSL Rules for Multi-Step Learning
>!
?@!
>%
?@!
>!
?
>%
?
>A
?
!
B!
?@!
%
B!
?@!
!
B!
?
Robustness / Future Reward
C3: S4T="5 >!, >%, B => K$,Lℎ5(>!, B)
25. Institute of Applied Informatics and
Formal Description Methods
25
Task: Named Entity Recognition + Named Entity Disambiguation
(Entity Linking) for tweets and news articles
Scenario 1 (individual steps): Predict the performance on NER and
NED of experts for
Tweets, left out from training set
Articles, trained on tweets only
Scenario 2 (full pipeline): Given a process for collecting samples (e,s)
(i.e. expert performance on tweet or article), select best outcomes to
improve overall performance
Empirical Evaluation
26. Institute of Applied Informatics and
Formal Description Methods
26
1. NER
1. NED
2.
Preliminary Results
27. Institute of Applied Informatics and
Formal Description Methods
27
Heuristic similarity measures such as text length or number of extra
characters yield good results
The relational learning approach (PSL) seems to allow for knowledge
transfer but further evaluations are needed
PSL scales well for thousands of tweets and articles if meta-
dependencies are precomputed
Lessons learnt
28. Institute of Applied Informatics and
Formal Description Methods
28
PSL approach beats State-of-the-Art for heterogeneous textual data
Our approach needs to be embedded into contextual bandit /
reinforcement learning techniques. No exploration / exploitation
strategy implemented so far.
Conclusion & Future Work
29. Institute of Applied Informatics and
Formal Description Methods
29
(Amin et at. 2015)
(Auer et al. 2002)
(Krishnamurthy et al.
2016)
(Puterman 1994)
(Bach et al. 2012)
(Kimmig et al. 2012)
Amin, K., Kale, S., Tesauro, G., and Turaga, D. S. (2015).
Budgeted prediction with expert advice. In AAAI, pages
2490–2496.
Auer, P., Cesa-Bianchi, N., Freund, Y., and Schapire, R. E.
(2002). The nonstochastic multiarmed bandit problem.
SIAM J. Comput., 32(1):48–77.
Krishnamurthy, A., Agarwal, A., and Langford, J. (2016).
Contextual-mdps for pac-reinforcement learning with rich
observations. CoRR, abs/1602.02722.
Puterman, M.L. (1994). Markov Decision Processes: Discrete
Stochastic Dynamic Programming. WileyInterscience, New York.
Bach, S. H., Broecheler, M., Getoor, L., and O’Leary, D. P.
(2012). Scaling MPE inference for constrained continuous
markov random fields with consensus optimization. In
NIPS, pages 2663–2671.
Kimmig, A., Bach, S., Broecheler, M., Huang, B., and
Getoor, L. (2012). A short introduction to probabilistic soft
logic. In NIPS Workshop on Probabilistic Programming:
Foundations and Applications, pages 1–4.
References
30. Institute of Applied Informatics and
Formal Description Methods
30
(Zhang et al. 2016)
(Thalhammer et al. 2016)
(Philipp et al. 2015)
(Mogadala et al. 2015)
(Zhang et al. 2014)
Lei Zhang, Michael Färber, Achim Rettinger; XKnowSearch! Exploiting Knowledge Bases for
Entity-based Cross-lingual Information Retrieval; The 25th ACM International on Conference
on Information and Knowledge Management (CIKM), ACM, Oktober, 2016
Andreas Thalhammer, Nelia Lasierra, Achim Rettinger; LinkSUM: Using Link Analysis to
Summarize Entity Data; In Bozzon, Alessandro and Cudré-Mauroux, Philippe and Pautasso,
Cesare, Web Engineering, 16th International Conference, ICWE 2016, Lugano, Switzerland,
June 6-9, 2016. Proceedings, Seiten: 244-261, Springer International Publishing, Lecture
Notes in Computer Science, 9671, Cham, Juni, 2016
Patrick Philipp, Maria Maleshkova, Darko Katic, Christian Weber, Michael Goetz, Achim
Rettinger, Stefanie Speidel, Benedikt Kämpgen, Marco Nolden, Anna-Laura Wekerle,
Rüdiger Dillmann, Hannes Kenngott, Beat Müller, Rudi Studer; Toward Cognitive Pipelines of
Medical Assistance Algorithms; International Journal of Computer Assisted Radiology and
Surgery, November, 2015
Aditya Mogadala, Achim Rettinger; Multi-Modal Correlated Centroid Space for Multi-Lingual
Cross-Modal Retrieval; In Hanbury, Allan and Kazai, Gabriella and Rauber, Andreas and Fuhr,
Norbert, Advances in Information Retrieval: 37th European Conference on IR Research
(ECIR), Vienna, Austria., Seiten: http://people.aifb.kit.edu/amo/ecir2015/, Springer
International Publishing, Cham, Germany, April, 2015
Lei Zhang, Achim Rettinger; X-LiSA: Cross-lingual Semantic Annotation; Proceedings of the
VLDB Endowment (PVLDB), the 40th International Conference on Very Large Data Bases
(VLDB), 7, (13), Seiten 1693-1696, September, 2014
Own Publications
31. Institute of Applied Informatics and
Formal Description Methods
31
rettinger@kit.edu
http://www.aifb.kit.edu/web/Achim_Rettinger/en
concerning
Research Discussions
Innovation Ideas
about
Expert Processes
Cross-Lingual Technologies
Cross-Modal Technologies
Semantic Search
Entity Summarization
Thank you & feel free to contact me