Wrangle 2016: (Lightning Talk) FizzBuzz in TensorFlowWrangleConf
Ā
By Joel Grus, AI2
FizzBuzz is a ubiquitous, nearly trivial problem used to weed out developer job applicants. Recently, Joel wrote a joking-not-joking blog post about a fictional interviewee who solves it using neural networks. After the blog post went viral, he spent a lot of time thinking about FizzBuzz as a machine-learning problem. It turns out, it's surprisingly interesting and subtle! Here, Joel talks about how and why.
Wrangling data the tidy way with the tidyverseCasper Crause
Ā
Have you checked out the new tidyr version 1.0.0?
I experimented with the pivot_long and pivot_wide functions and I love the new functionality!
I cleaned a weather data-set that was poorly constructed but thanks to the tidyverse it was a breeze!
Presentation delivered on 21-Feb-2019 about SIMD (vectorial) operations in java, using as an example a CNN (Convolutional Neural Network) and the requirement in Deep Learning to process massive arrays and matrices. We provide some insight and some solutions of how to perform that in Java using DeepLearning4J, after investigating CERN's Colt Java Library.
Wrangle 2016: (Lightning Talk) FizzBuzz in TensorFlowWrangleConf
Ā
By Joel Grus, AI2
FizzBuzz is a ubiquitous, nearly trivial problem used to weed out developer job applicants. Recently, Joel wrote a joking-not-joking blog post about a fictional interviewee who solves it using neural networks. After the blog post went viral, he spent a lot of time thinking about FizzBuzz as a machine-learning problem. It turns out, it's surprisingly interesting and subtle! Here, Joel talks about how and why.
Wrangling data the tidy way with the tidyverseCasper Crause
Ā
Have you checked out the new tidyr version 1.0.0?
I experimented with the pivot_long and pivot_wide functions and I love the new functionality!
I cleaned a weather data-set that was poorly constructed but thanks to the tidyverse it was a breeze!
Presentation delivered on 21-Feb-2019 about SIMD (vectorial) operations in java, using as an example a CNN (Convolutional Neural Network) and the requirement in Deep Learning to process massive arrays and matrices. We provide some insight and some solutions of how to perform that in Java using DeepLearning4J, after investigating CERN's Colt Java Library.
Mastering the game of Go with deep neural networks and tree search (article o...Ilya Kuzovkin
Ā
"This is the first time that a computer program has defeated a human professional player in the full-sized game of Go, a feat previously thought to be at least a decade away." In this presentation I go through the pipeline following the steps the algorithm does to understand the process.
Machine Learning for Understanding and Managing Ecosystemsdiannepatricia
Ā
Thomas Dietterich, Distinguished Professor (Emeritus) and Director of Intelligent Systems Research in the School of Electrical Engineering and Computer Science at Oregon State University, made this presentation as part of the Cognitive Systems Institute Speaker Series on August 4, 2106.
Demystifying Machine Learning - How to give your business superpowers.10x Nation
Ā
A "no math" introduction to machine learning concepts. Touches on various ML architectures, including neural networks and deep learning. Includes tons of resource links.
Machine Learning and Data Mining: 03 Data RepresentationPier Luca Lanzi
Ā
Course "Machine Learning and Data Mining" for the degree of Computer Engineering at the Politecnico di Milano. This lecture overviews the data representation issues in Data Mining.
A Beginner's Guide to Machine Learning with Scikit-LearnSarah Guido
Ā
Given at the PyData NYC 2013 conference (http://vimeo.com/79517341), and will be given at PyTennessee 2014.
Scikit-learn is one of the most well-known machine learning Python modules in existence. But how does it work, and what, for that matter, is machine learning? For those with programming experience but who are new to machine learning, this talk gives a beginner-level overview of how machine learning can be useful, important machine learning concepts, and how to implement them with scikit-learn. Weāll use real world data to look at supervised and unsupervised machine learning algorithms and why scikit-learn is useful for performing these tasks.
Machine learning the next revolution or just another hypeJorge Ferrer
Ā
These are the slides of my session and ModConf / Liferay DevCon 2016.
It attempts to make it easy for any developer to get started with Machine Learning. It presents three exercises which I'm giving as homework (yup, homework, you missed it, right? ;) to the audience.
The video for this session is now available at https://www.facebook.com/liferay/videos/vl.383534535315216/10154154247423108/?type=1 (starts at min 34)
A Nontechnical Introduction to Machine LearningSam Elshamy
Ā
This presentation describes what machine learning is, in simple words and examples. No PhD required to understand it.
Feel free to use any material from this deck. Proper acknowledgement is appreciated.
Slide presentasi ini dibawakan oleh Imron Zuhri dalam acara Seminar & Workshop Pengenalan & Potensi Big Data & Machine Learning yang diselenggarakan oleh KUDO pada tanggal 14 Mei 2016.
Machine Learning in Pathology Diagnostics with Simagis Livekhvatkov
Ā
Simagis Live Digital Pathology platform employs latest generation of visual recognition technology with Deep Learning bring game changing application to pathology cancer diagnostics
Seminar overview of the third article produced by Google DeepMind. This one again contains conceptual novelties: adding external memory to machine learning pipeline (using an Artificial Neural Network as a Controller, which decides how to use this memory). System is differentiable, meaning that you can give it inputs, show the outputs it should produce, define an error-function (cross-entropy in this case) and then train the whole thing using gradient descent. The amazing outcome is that the system learns not the statistical relations between the input and the output as your usual ML, but attempts to learn an algorithm, which allows it to generalize well and perform correctly on problem instances which are bigger or different from what is has been trained on.
Machine Learning and Search -State of Search 2016 Eric Enge
Ā
Machine learning is the next great computer revolution, one that is already here. We donāt have to wait for the future; Google has been using machine learning to solve many complex search-related problems for years, and the applications keep growing, including last yearās announcement of the addition of RankBrain to the search algorithm, the impact of machine learning on search. Google's #RankBrain algorithm caused major confusion in the digital marketing community. This presentation will show you what RankBrain really is about, what else Google is likely to do with machine learning, and how it impacts your SEO strategy.Ā
This presentation is shown by Eric Enge at State of Search Conference in November 2016
All major cloud service providers now have some ML offering. The startup costs are low-to-no. They provide seamless leverage of cloud resources for scale-ups = $ās.
Open source ML options are now common making the creation of very large models now possible. Open data sets are proliferating.
Presented at CF Machine Learning
Natural Language Processing (NLP) is often taught at the academic level from the perspective of computational linguists. However, as data scientists, we have a richer view of the world of natural language - unstructured data that by its very nature has important latent information for humans. NLP practitioners have benefitted from machine learning techniques to unlock meaning from large corpora, and in this class weāll explore how to do that particularly with Python, the Natural Language Toolkit (NLTK), and to a lesser extent, the Gensim Library.
NLTK is an excellent library for machine learning-based NLP, written in Python by experts from both academia and industry. Python allows you to create rich data applications rapidly, iterating on hypotheses. Gensim provides vector-based topic modeling, which is currently absent in both NLTK and Scikit-Learn. The combination of Python + NLTK means that you can easily add language-aware data products to your larger analytical workflows and applications.
Introduction to Machine Learning for newcomers. It will show you some basic concepts like what is supervised learning, unsupervised learning, classification, regression, under/overfitting, clustering, anomaly detection, and how to have some measures. It will illustrates examples through scikit-learn and tensorflow code
Mastering the game of Go with deep neural networks and tree search (article o...Ilya Kuzovkin
Ā
"This is the first time that a computer program has defeated a human professional player in the full-sized game of Go, a feat previously thought to be at least a decade away." In this presentation I go through the pipeline following the steps the algorithm does to understand the process.
Machine Learning for Understanding and Managing Ecosystemsdiannepatricia
Ā
Thomas Dietterich, Distinguished Professor (Emeritus) and Director of Intelligent Systems Research in the School of Electrical Engineering and Computer Science at Oregon State University, made this presentation as part of the Cognitive Systems Institute Speaker Series on August 4, 2106.
Demystifying Machine Learning - How to give your business superpowers.10x Nation
Ā
A "no math" introduction to machine learning concepts. Touches on various ML architectures, including neural networks and deep learning. Includes tons of resource links.
Machine Learning and Data Mining: 03 Data RepresentationPier Luca Lanzi
Ā
Course "Machine Learning and Data Mining" for the degree of Computer Engineering at the Politecnico di Milano. This lecture overviews the data representation issues in Data Mining.
A Beginner's Guide to Machine Learning with Scikit-LearnSarah Guido
Ā
Given at the PyData NYC 2013 conference (http://vimeo.com/79517341), and will be given at PyTennessee 2014.
Scikit-learn is one of the most well-known machine learning Python modules in existence. But how does it work, and what, for that matter, is machine learning? For those with programming experience but who are new to machine learning, this talk gives a beginner-level overview of how machine learning can be useful, important machine learning concepts, and how to implement them with scikit-learn. Weāll use real world data to look at supervised and unsupervised machine learning algorithms and why scikit-learn is useful for performing these tasks.
Machine learning the next revolution or just another hypeJorge Ferrer
Ā
These are the slides of my session and ModConf / Liferay DevCon 2016.
It attempts to make it easy for any developer to get started with Machine Learning. It presents three exercises which I'm giving as homework (yup, homework, you missed it, right? ;) to the audience.
The video for this session is now available at https://www.facebook.com/liferay/videos/vl.383534535315216/10154154247423108/?type=1 (starts at min 34)
A Nontechnical Introduction to Machine LearningSam Elshamy
Ā
This presentation describes what machine learning is, in simple words and examples. No PhD required to understand it.
Feel free to use any material from this deck. Proper acknowledgement is appreciated.
Slide presentasi ini dibawakan oleh Imron Zuhri dalam acara Seminar & Workshop Pengenalan & Potensi Big Data & Machine Learning yang diselenggarakan oleh KUDO pada tanggal 14 Mei 2016.
Machine Learning in Pathology Diagnostics with Simagis Livekhvatkov
Ā
Simagis Live Digital Pathology platform employs latest generation of visual recognition technology with Deep Learning bring game changing application to pathology cancer diagnostics
Seminar overview of the third article produced by Google DeepMind. This one again contains conceptual novelties: adding external memory to machine learning pipeline (using an Artificial Neural Network as a Controller, which decides how to use this memory). System is differentiable, meaning that you can give it inputs, show the outputs it should produce, define an error-function (cross-entropy in this case) and then train the whole thing using gradient descent. The amazing outcome is that the system learns not the statistical relations between the input and the output as your usual ML, but attempts to learn an algorithm, which allows it to generalize well and perform correctly on problem instances which are bigger or different from what is has been trained on.
Machine Learning and Search -State of Search 2016 Eric Enge
Ā
Machine learning is the next great computer revolution, one that is already here. We donāt have to wait for the future; Google has been using machine learning to solve many complex search-related problems for years, and the applications keep growing, including last yearās announcement of the addition of RankBrain to the search algorithm, the impact of machine learning on search. Google's #RankBrain algorithm caused major confusion in the digital marketing community. This presentation will show you what RankBrain really is about, what else Google is likely to do with machine learning, and how it impacts your SEO strategy.Ā
This presentation is shown by Eric Enge at State of Search Conference in November 2016
All major cloud service providers now have some ML offering. The startup costs are low-to-no. They provide seamless leverage of cloud resources for scale-ups = $ās.
Open source ML options are now common making the creation of very large models now possible. Open data sets are proliferating.
Presented at CF Machine Learning
Natural Language Processing (NLP) is often taught at the academic level from the perspective of computational linguists. However, as data scientists, we have a richer view of the world of natural language - unstructured data that by its very nature has important latent information for humans. NLP practitioners have benefitted from machine learning techniques to unlock meaning from large corpora, and in this class weāll explore how to do that particularly with Python, the Natural Language Toolkit (NLTK), and to a lesser extent, the Gensim Library.
NLTK is an excellent library for machine learning-based NLP, written in Python by experts from both academia and industry. Python allows you to create rich data applications rapidly, iterating on hypotheses. Gensim provides vector-based topic modeling, which is currently absent in both NLTK and Scikit-Learn. The combination of Python + NLTK means that you can easily add language-aware data products to your larger analytical workflows and applications.
Introduction to Machine Learning for newcomers. It will show you some basic concepts like what is supervised learning, unsupervised learning, classification, regression, under/overfitting, clustering, anomaly detection, and how to have some measures. It will illustrates examples through scikit-learn and tensorflow code
Machine Learning : why we should know and how it worksKevin Lee
Ā
The most popular buzz word nowadays in the technology world is āMachine Learning (ML).ā Most economists and business experts foresee Machine Learning changing every aspect of our lives in the next 10 years through automating and optimizing processes such as: self-driving vehicles; online recommendation on Netflix and Amazon; fraud detection in banks; image and video recognition; natural language processing; question answering machines (e.g., IBM Watson); and many more. This is leading many organizations to seek experts who can implement Machine Learning into their businesses.
Statistical programmers and statisticians in the pharmaceutical industry are in very interesting positions. We have very similar backgrounds as Machine Learning experts, such as programming, statistics, and data expertise, thus embodying the essential technical skill sets needed. This similarity leads many individuals to ask us about Machine Learning. If you are the leaders of biometric groups, you get asked more often.
The paper is intended for statistical programmers and statisticians who are interested in learning and applying Machine Learning to lead innovation in the pharmaceutical industry. The paper will start with the introduction of basic concepts of Machine Learning - hypothesis and cost function and gradient descent. Then, paper will introduce Supervised ML (e.g., Support Vector Machine, Decision Trees, Logistic Regression), Unsupervised ML (e.g., clustering) and the most powerful ML algorithm, Artificial Neural Network (ANN). The paper will also introduce some of popular SAS Ā® ML procedures and SAS Visual Data Mining and Machine Learning. Finally, the paper will discuss the current ML implementation, its future implementation and how programmers and statisticians could lead this exciting and disruptive technology in pharmaceutical industry.
Detecting Misleading Headlines in Online News: Hands-on Experiences on Attent...Kunwoo Park
Ā
This slide is used for the tutorial in Deep Learning Summer School, held in IBS, Daejeon. Based on the recent effort on detecting misleading headlines through deep neural networks (Yoon et al., AAAI 2019), it explains how RNN and Attention mechanism works for text. Moreover, implementations based on TensorFlow 1.x are introduced.
Presented at Data Day Texas 2020 and attempts to show the tradeoffs between bigger data, better math, and better data. Uses Fashion MNIST as the use case, and a progression of better math from Random Forest to Gradient Boosted Trees to Feedforward Neural Nets to Convolutional Neural Nets.
Oh, and Cthulhu
These are the slides from workshop: Introduction to Machine Learning with R which I gave at the University of Heidelberg, Germany on June 28th 2018.
The accompanying code to generate all plots in these slides (plus additional code) can be found on my blog: https://shirinsplayground.netlify.com/2018/06/intro_to_ml_workshop_heidelberg/
The workshop covered the basics of machine learning. With an example dataset I went through a standard machine learning workflow in R with the packages caret and h2o:
- reading in data
- exploratory data analysis
- missingness
- feature engineering
- training and test split
- model training with Random Forests, Gradient Boosting, Neural Nets, etc.
- hyperparameter tuning
Machine Learning in a Flash (Extended Edition 2): An Introduction to Neural N...Kory Becker
Ā
Learn the basics behind machine learning, neural networks, natural language processing, and clustering. In this presentation weāll go over a handful of really quick machine learning algorithms. Weāll cover the difference between unsupervised and supervised learning in artificial intelligence, classification, clustering, and natural language processing to classify sentences as being about āeatingā. We'll also see how to automatically categorize data under specific groups, using unsupervised learning, and apply topic detection to a finance data-set.
Comparing Machine Learning Algorithms in Text MiningAndrea Gigli
Ā
In this project I compare different Machine Learning Algorithm on different Text Mining Tasks.
ML algorithms: Naive Bayes, Support Vector Machine, Decision Trees, Random Forest, Ordinal Regression as ML task
Tasks considered: Classifying Positive and Negative Reviews, Predicting Review Stars, Quantifying Sentiment Over Time, Detecting Fake Reviews
During the 24th Dutch Testing Day organized by TU Delft, Software Engineering Professor Arie van Deursen gave this talk about The European STAMP project on testing and Continuous Integration.
Similar to Introduction to Machine Learning @ Mooncascade ML Camp (20)
Understanding Information Processing in Human Brain by Interpreting Machine L...Ilya Kuzovkin
Ā
The thesis explores the role machine learning methods play in creating intuitive computational models of neural processing. Combined with interpretability techniques, machine learning could replace human modeler and shift the focus of human effort to extracting the knowledge from the ready-made models and articulating that knowledge into intuitive descriptions of reality. This perspective makes the case in favor of the larger role that exploratory and data-driven approach to computational neuroscience could play while coexisting alongside the traditional hypothesis-driven approach.
We exemplify the proposed approach in the context of the knowledge representation taxonomy with three research projects that employ interpretability techniques on top of machine learning methods at three different levels of neural organization. The first study (Chapter 3) explores feature importance analysis of a random forest decoder trained on intracerebral recordings from 100 human subjects to identify spectrotemporal signatures that characterize local neural activity during the task of visual categorization. The second study (Chapter 4) employs representation similarity analysis to compare the neural responses of the areas along the ventral stream with the activations of the layers of a deep convolutional neural network. The third study (Chapter 5) proposes a method that allows test subjects to visually explore the state representation of their neural signal in real time. This is achieved by using a topology-preserving dimensionality reduction technique that allows to transform the neural data from the multidimensional representation used by the computer into a two-dimensional representation a human can grasp.
The approach, the taxonomy, and the examples, present a strong case for the applicability of machine learning methods to automatic knowledge discovery in neuroscience.
The Brain and the Modern AI: Drastic Differences and Curious SimilaritiesIlya Kuzovkin
Ā
In this presentation we user Marr's three levels of analysis to approach the question of how similar or different are the brain and the machines. By approaching this discussion in a more structured manner we find that the answer is different depending on the level of abstraction we are operating at.
Introductory talk about how to think about various deep learning architectures and their suitability to different types of data. Presented at Data Science Meetup @ University of Tartu
Intuitive Intro to Gƶdel's Incompleteness TheoremIlya Kuzovkin
Ā
Intuitive introduction into meaning of Gƶdel's incompleteness theorem. Slides are prepared for "Philosophy of Artificial Intelligence" class at University of Tartu
Paper overview: "Deep Residual Learning for Image Recognition"Ilya Kuzovkin
Ā
A talk given at Computational Neuroscience Seminar @ University of Tartu. We discuss the idea behind deep neural network that has won ILSVRC (ImageNet) 2015 and COCO 2015 Image competitions.
Article overview: Unsupervised Learning of Visual Structure Using Predictive ...Ilya Kuzovkin
Ā
This set of slides goes over the recent article that tries to tie together the idea of predictive coding and deep learning. The main point of the article is that a generative system trained on sequential data to predict the future samples learns more "useful" representation than the usual autoencoder. The result resonates with the fact that our brain is probably using predictive mechanisms.
Article overview: Deep Neural Networks Reveal a Gradient in the Complexity of...Ilya Kuzovkin
Ā
The article presents the comparison of the complexity of the representation of visual features in the deep convolutional neural network and in our brain. DNN activity layer-by-layer is used to predict voxel activations and it is shown that lower layers of DNN are better at predicting V1,V2 and that higher layers of DNN are better in predicting activity in LO and higher areas of ventral stream. The result effectively demonstrates that layer-by-layer complexity of visual features we see in DNN is also present in the visual cortex.
NIPS2014 Article Overview: Do Deep Nets Really Need to be Deep?Ilya Kuzovkin
Ā
Year 2014 passed under the huge Deep Learning sign. At the last seminar of computational neuroscience I've presented a very recent article, which looks into the question of whether deepness in a requirements for approximating a function, or, under the right condition, shallow nets are capable of performing equally well?
Introductory lecture on neuroimaging techniques: intracortical, fMRI, EEG. Tends to explain the ideas of the technologies on a good level of intuition. Presented at AACIMP'14 (http://summerschool.ssa.org.ua/program/42-program/ns-2014/442-machine-learning-on-neuroimaging-data)
Article Overview "Reach and grasp by people with tetraplegia using a neurally...Ilya Kuzovkin
Ā
This presentation is article overview given at the Computational Neuroscience seminar in the University of Tartu. In my opinion at the moment this is the most prominent BCI system out there.
The presentation is given during the Computer Graphics seminar at the University of Tartu. It is an introductory overview of the GPGPU idea in general and gives "hello world" examples using old-school shader computing, OpenCL and CUDA. The code is available in my <a>Github repository</a>.
Ilya Kuzovkin - Adaptive Interactive Learning for Brain-Computer InterfacesIlya Kuzovkin
Ā
This is a brief description of the approach and algorithm I proposed in my master's thesis. The core algorithm keeps track of both user's and computer's progress and gives them valuable feedback.
UiPath Test Automation using UiPath Test Suite series, part 4DianaGray10
Ā
Welcome to UiPath Test Automation using UiPath Test Suite series part 4. In this session, we will cover Test Manager overview along with SAP heatmap.
The UiPath Test Manager overview with SAP heatmap webinar offers a concise yet comprehensive exploration of the role of a Test Manager within SAP environments, coupled with the utilization of heatmaps for effective testing strategies.
Participants will gain insights into the responsibilities, challenges, and best practices associated with test management in SAP projects. Additionally, the webinar delves into the significance of heatmaps as a visual aid for identifying testing priorities, areas of risk, and resource allocation within SAP landscapes. Through this session, attendees can expect to enhance their understanding of test management principles while learning practical approaches to optimize testing processes in SAP environments using heatmap visualization techniques
What will you get from this session?
1. Insights into SAP testing best practices
2. Heatmap utilization for testing
3. Optimization of testing processes
4. Demo
Topics covered:
Execution from the test manager
Orchestrator execution result
Defect reporting
SAP heatmap example with demo
Speaker:
Deepak Rai, Automation Practice Lead, Boundaryless Group and UiPath MVP
Neuro-symbolic is not enough, we need neuro-*semantic*Frank van Harmelen
Ā
Neuro-symbolic (NeSy) AI is on the rise. However, simply machine learning on just any symbolic structure is not sufficient to really harvest the gains of NeSy. These will only be gained when the symbolic structures have an actual semantics. I give an operational definition of semantics as āpredictable inferenceā.
All of this illustrated with link prediction over knowledge graphs, but the argument is general.
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...James Anderson
Ā
Effective Application Security in Software Delivery lifecycle using Deployment Firewall and DBOM
The modern software delivery process (or the CI/CD process) includes many tools, distributed teams, open-source code, and cloud platforms. Constant focus on speed to release software to market, along with the traditional slow and manual security checks has caused gaps in continuous security as an important piece in the software supply chain. Today organizations feel more susceptible to external and internal cyber threats due to the vast attack surface in their applications supply chain and the lack of end-to-end governance and risk management.
The software team must secure its software delivery process to avoid vulnerability and security breaches. This needs to be achieved with existing tool chains and without extensive rework of the delivery processes. This talk will present strategies and techniques for providing visibility into the true risk of the existing vulnerabilities, preventing the introduction of security issues in the software, resolving vulnerabilities in production environments quickly, and capturing the deployment bill of materials (DBOM).
Speakers:
Bob Boule
Robert Boule is a technology enthusiast with PASSION for technology and making things work along with a knack for helping others understand how things work. He comes with around 20 years of solution engineering experience in application security, software continuous delivery, and SaaS platforms. He is known for his dynamic presentations in CI/CD and application security integrated in software delivery lifecycle.
Gopinath Rebala
Gopinath Rebala is the CTO of OpsMx, where he has overall responsibility for the machine learning and data processing architectures for Secure Software Delivery. Gopi also has a strong connection with our customers, leading design and architecture for strategic implementations. Gopi is a frequent speaker and well-known leader in continuous delivery and integrating security into software delivery.
DevOps and Testing slides at DASA ConnectKari Kakkonen
Ā
My and Rik Marselis slides at 30.5.2024 DASA Connect conference. We discuss about what is testing, then what is agile testing and finally what is Testing in DevOps. Finally we had lovely workshop with the participants trying to find out different ways to think about quality and testing in different parts of the DevOps infinity loop.
Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024Tobias Schneck
Ā
As AI technology is pushing into IT I was wondering myself, as an āinfrastructure container kubernetes guyā, how get this fancy AI technology get managed from an infrastructure operational view? Is it possible to apply our lovely cloud native principals as well? What benefitās both technologies could bring to each other?
Let me take this questions and provide you a short journey through existing deployment models and use cases for AI software. On practical examples, we discuss what cloud/on-premise strategy we may need for applying it to our own infrastructure to get it to work from an enterprise perspective. I want to give an overview about infrastructure requirements and technologies, what could be beneficial or limiting your AI use cases in an enterprise environment. An interactive Demo will give you some insides, what approaches I got already working for real.
Transcript: Selling digital books in 2024: Insights from industry leaders - T...BookNet Canada
Ā
The publishing industry has been selling digital audiobooks and ebooks for over a decade and has found its groove. Whatās changed? What has stayed the same? Where do we go from here? Join a group of leading sales peers from across the industry for a conversation about the lessons learned since the popularization of digital books, best practices, digital book supply chain management, and more.
Link to video recording: https://bnctechforum.ca/sessions/selling-digital-books-in-2024-insights-from-industry-leaders/
Presented by BookNet Canada on May 28, 2024, with support from the Department of Canadian Heritage.
Epistemic Interaction - tuning interfaces to provide information for AI supportAlan Dix
Ā
Paper presented at SYNERGY workshop at AVI 2024, Genoa, Italy. 3rd June 2024
https://alandix.com/academic/papers/synergy2024-epistemic/
As machine learning integrates deeper into human-computer interactions, the concept of epistemic interaction emerges, aiming to refine these interactions to enhance system adaptability. This approach encourages minor, intentional adjustments in user behaviour to enrich the data available for system learning. This paper introduces epistemic interaction within the context of human-system communication, illustrating how deliberate interaction design can improve system understanding and adaptation. Through concrete examples, we demonstrate the potential of epistemic interaction to significantly advance human-computer interaction by leveraging intuitive human communication strategies to inform system design and functionality, offering a novel pathway for enriching user-system engagements.
Connector Corner: Automate dynamic content and events by pushing a buttonDianaGray10
Ā
Here is something new! In our next Connector Corner webinar, we will demonstrate how you can use a single workflow to:
Create a campaign using Mailchimp with merge tags/fields
Send an interactive Slack channel message (using buttons)
Have the message received by managers and peers along with a test email for review
But thereās more:
In a second workflow supporting the same use case, youāll see:
Your campaign sent to target colleagues for approval
If the āApproveā button is clicked, a Jira/Zendesk ticket is created for the marketing design team
Butāif the āRejectā button is pushed, colleagues will be alerted via Slack message
Join us to learn more about this new, human-in-the-loop capability, brought to you by Integration Service connectors.
And...
Speakers:
Akshay Agnihotri, Product Manager
Charlie Greenberg, Host
17. Instance
Raw data
Class (label)
A data sample:
ā7ā
How to represent it in a machine-readable form?
Feature extraction
28px
28 px
18. Instance
Raw data
Class (label)
A data sample:
ā7ā
28px
28 px
784 pixels in total
Feature vector
(0, 0, 0, ā¦, 28, 65, 128, 255, 101, 38,ā¦ 0, 0, 0)
How to represent it in a machine-readable form?
Feature extraction
19. Instance
Raw data
Class (label)
A data sample:
ā7ā
28px
28 px
784 pixels in total
Feature vector
(0, 0, 0, ā¦, 28, 65, 128, 255, 101, 38,ā¦ 0, 0, 0)
How to represent it in a machine-readable form?
Feature extraction
(0, 0, 0, ā¦, 28, 65, 128, 255, 101, 38,ā¦ 0, 0, 0)
(0, 0, 0, ā¦, 13, 48, 102, 0, 46, 255,ā¦ 0, 0, 0)
(0, 0, 0, ā¦, 17, 34, 12, 43, 122, 70,ā¦ 0, 7, 0)
(0, 0, 0, ā¦, 98, 21, 255, 255, 231, 140,ā¦ 0, 0, 0)
ā7ā
ā2ā
ā8ā
ā2ā
20. Instance
Raw data
Class (label)
A data sample:
ā7ā
28px
28 px
784 pixels in total
Feature vector
(0, 0, 0, ā¦, 28, 65, 128, 255, 101, 38,ā¦ 0, 0, 0)
How to represent it in a machine-readable form?
Feature extraction
(0, 0, 0, ā¦, 28, 65, 128, 255, 101, 38,ā¦ 0, 0, 0)
(0, 0, 0, ā¦, 13, 48, 102, 0, 46, 255,ā¦ 0, 0, 0)
(0, 0, 0, ā¦, 17, 34, 12, 43, 122, 70,ā¦ 0, 7, 0)
Dataset
(0, 0, 0, ā¦, 98, 21, 255, 255, 231, 140,ā¦ 0, 0, 0)
ā7ā
ā2ā
ā8ā
ā2ā
21. The data is in the right format ā whatās next?
22. The data is in the right format ā whatās next?
ā¢ C4.5
ā¢ Random forests
ā¢ Bayesian networks
ā¢ Hidden Markov models
ā¢ Artificial neural network
ā¢ Data clustering
ā¢ Expectation-maximization
algorithm
ā¢ Self-organizing map
ā¢ Radial basis function network
ā¢ Vector Quantization
ā¢ Generative topographic map
ā¢ Information bottleneck method
ā¢ IBSEAD
ā¢ Apriori algorithm
ā¢ Eclat algorithm
ā¢ FP-growth algorithm
ā¢ Single-linkage clustering
ā¢ Conceptual clustering
ā¢ K-means algorithm
ā¢ Fuzzy clustering
ā¢ Temporal difference learning
ā¢ Q-learning
ā¢ Learning Automata
ā¢ AODE
ā¢ Artificial neural network
ā¢ Backpropagation
ā¢ Naive Bayes classifier
ā¢ Bayesian network
ā¢ Bayesian knowledge base
ā¢ Case-based reasoning
ā¢ Decision trees
ā¢ Inductive logic
programming
ā¢ Gaussian process regression
ā¢ Gene expression
programming
ā¢ Group method of data
handling (GMDH)
ā¢ Learning Automata
ā¢ Learning Vector
Quantization
ā¢ Logistic Model Tree
ā¢ Decision tree
ā¢ Decision graphs
ā¢ Lazy learning
ā¢ Monte Carlo Method
ā¢ SARSA
ā¢ Instance-based learning
ā¢ Nearest Neighbor Algorithm
ā¢ Analogical modeling
ā¢ Probably approximately correct learning
(PACL)
ā¢ Symbolic machine learning algorithms
ā¢ Subsymbolic machine learning algorithms
ā¢ Support vector machines
ā¢ Random Forest
ā¢ Ensembles of classifiers
ā¢ Bootstrap aggregating (bagging)
ā¢ Boosting (meta-algorithm)
ā¢ Ordinal classification
ā¢ Regression analysis
ā¢ Information fuzzy networks (IFN)
ā¢ Linear classifiers
ā¢ Fisher's linear discriminant
ā¢ Logistic regression
ā¢ Naive Bayes classifier
ā¢ Perceptron
ā¢ Support vector machines
ā¢ Quadratic classifiers
ā¢ k-nearest neighbor
ā¢ Boosting
Pick an algorithm
23. The data is in the right format ā whatās next?
ā¢ C4.5
ā¢ Random forests
ā¢ Bayesian networks
ā¢ Hidden Markov models
ā¢ Artificial neural network
ā¢ Data clustering
ā¢ Expectation-maximization
algorithm
ā¢ Self-organizing map
ā¢ Radial basis function network
ā¢ Vector Quantization
ā¢ Generative topographic map
ā¢ Information bottleneck method
ā¢ IBSEAD
ā¢ Apriori algorithm
ā¢ Eclat algorithm
ā¢ FP-growth algorithm
ā¢ Single-linkage clustering
ā¢ Conceptual clustering
ā¢ K-means algorithm
ā¢ Fuzzy clustering
ā¢ Temporal difference learning
ā¢ Q-learning
ā¢ Learning Automata
ā¢ AODE
ā¢ Artificial neural network
ā¢ Backpropagation
ā¢ Naive Bayes classifier
ā¢ Bayesian network
ā¢ Bayesian knowledge base
ā¢ Case-based reasoning
ā¢ Decision trees
ā¢ Inductive logic
programming
ā¢ Gaussian process regression
ā¢ Gene expression
programming
ā¢ Group method of data
handling (GMDH)
ā¢ Learning Automata
ā¢ Learning Vector
Quantization
ā¢ Logistic Model Tree
ā¢ Decision tree
ā¢ Decision graphs
ā¢ Lazy learning
ā¢ Monte Carlo Method
ā¢ SARSA
ā¢ Instance-based learning
ā¢ Nearest Neighbor Algorithm
ā¢ Analogical modeling
ā¢ Probably approximately correct learning
(PACL)
ā¢ Symbolic machine learning algorithms
ā¢ Subsymbolic machine learning algorithms
ā¢ Support vector machines
ā¢ Random Forest
ā¢ Ensembles of classifiers
ā¢ Bootstrap aggregating (bagging)
ā¢ Boosting (meta-algorithm)
ā¢ Ordinal classification
ā¢ Regression analysis
ā¢ Information fuzzy networks (IFN)
ā¢ Linear classifiers
ā¢ Fisher's linear discriminant
ā¢ Logistic regression
ā¢ Naive Bayes classifier
ā¢ Perceptron
ā¢ Support vector machines
ā¢ Quadratic classifiers
ā¢ k-nearest neighbor
ā¢ Boosting
Pick an algorithm
39. ACCURACY
Confusion matrix
acc =
correctly classiļ¬ed
total number of samples
Beware of an
imbalanced dataset!
Consider the following model:
āAlways predict 2ā
Trueclass
Predicted class
40. ACCURACY
Confusion matrix
acc =
correctly classiļ¬ed
total number of samples
Beware of an
imbalanced dataset!
Consider the following model:
āAlways predict 2ā
Accuracy 0.9
Trueclass
Predicted class
42. DECISION TREE
āYou said 100%
accurate?! Every 10th
digit your system
detects is wrong!ā
Angry client
43. DECISION TREE
āYou said 100%
accurate?! Every 10th
digit your system
detects is wrong!ā
Angry client
Weāve trained our system on the data the client gave us. But our
system has never seen the new data the client applied it to.
And in the real life ā it never willā¦
56. TEST SET
20%
TRAINING SET
60%
THE WHOLE DATASET
VALIDATION SET
20%
Fit various models
and parameter
combinations on this
subset
ā¢ Evaluate the
models created
with different
parameters
57. TEST SET
20%
TRAINING SET
60%
THE WHOLE DATASET
VALIDATION SET
20%
Fit various models
and parameter
combinations on this
subset
ā¢ Evaluate the
models created
with different
parameters
!
ā¢ Estimate overļ¬tting
TRA
VALI
58. TEST SET
20%
TRAINING SET
60%
THE WHOLE DATASET
VALIDATION SET
20%
Fit various models
and parameter
combinations on this
subset
ā¢ Evaluate the
models created
with different
parameters
!
ā¢ Estimate overļ¬tting
TRA
VALI
TRA
VALI
59. TEST SET
20%
TRAINING SET
60%
THE WHOLE DATASET
VALIDATION SET
20%
Fit various models
and parameter
combinations on this
subset
ā¢ Evaluate the
models created
with different
parameters
!
ā¢ Estimate overļ¬tting
TRA
VALI
TRA
VALI
TRA
VALI
60. TEST SET
20%
TRAINING SET
60%
THE WHOLE DATASET
VALIDATION SET
20%
Fit various models
and parameter
combinations on this
subset
ā¢ Evaluate the
models created
with different
parameters
!
ā¢ Estimate overļ¬tting
TRA
VALI
TRA
VALI
TRA
VALI
TRA
VALI
61. TEST SET
20%
TRAINING SET
60%
THE WHOLE DATASET
VALIDATION SET
20%
Fit various models
and parameter
combinations on this
subset
ā¢ Evaluate the
models created
with different
parameters
!
ā¢ Estimate overļ¬tting
TRA
VALI
TRA
VALI
TRA
VALI
TRA
VALI
TRA
VALI
62. TEST SET
20%
TRAINING SET
60%
THE WHOLE DATASET
VALIDATION SET
20%
Fit various models
and parameter
combinations on this
subset
ā¢ Evaluate the
models created
with different
parameters
!
ā¢ Estimate overļ¬tting
Use only once to get
the ļ¬nal performance
estimate
TRA
VALI
TRA
VALI
TRA
VALI
TRA
VALI
TRA
VALI
68. CROSS-VALIDATION
TRAINING SET 60%
THE WHOLE DATASET
VALIDATION SET 20%
What if we got too
optimistic validation set?
TRAINING SET 80%
Fix the parameter value you ned to evaluate, say msl=15
69. CROSS-VALIDATION
TRAINING SET 60%
THE WHOLE DATASET
VALIDATION SET 20%
What if we got too
optimistic validation set?
TRAINING SET 80%
Fix the parameter value you ned to evaluate, say msl=15
TRAINING VAL
TRAINING VAL
TRAININGVAL
Repeat 10 times
70. CROSS-VALIDATION
TRAINING SET 60%
THE WHOLE DATASET
VALIDATION SET 20%
What if we got too
optimistic validation set?
TRAINING SET 80%
Fix the parameter value you ned to evaluate, say msl=15
TRAINING VAL
TRAINING VAL
TRAININGVAL
Repeat 10 times
}
Take average
validation score
over 10 runs ā
it is a more
stable estimate.
71.
72.
73.
74. MACHINE LEARNING PIPELINE
Take raw data Extract features
Split into TRAINING
and TEST
Pick an algorithm
and parameters
Train on the
TRAINING data
Evaluate on the
TRAINING data
with CV
Train on the
whole TRAINING
Fix the best
parameters
Evaluate on TEST
Report ļ¬nal
performance to
the client
Try our different algorithms
and parameters
75. MACHINE LEARNING PIPELINE
Take raw data Extract features
Split into TRAINING
and TEST
Pick an algorithm
and parameters
Train on the
TRAINING data
Evaluate on the
TRAINING data
with CV
Train on the
whole TRAINING
Fix the best
parameters
Evaluate on TEST
Report ļ¬nal
performance to
the client
Try our different algorithms
and parameters
āSo it is ~87%ā¦ermā¦
Could you do better?ā
76. MACHINE LEARNING PIPELINE
Take raw data Extract features
Split into TRAINING
and TEST
Pick an algorithm
and parameters
Train on the
TRAINING data
Evaluate on the
TRAINING data
with CV
Train on the
whole TRAINING
Fix the best
parameters
Evaluate on TEST
Report ļ¬nal
performance to
the client
Try our different algorithms
and parameters
āSo it is ~87%ā¦ermā¦
Could you do better?ā
Yes
77. ā¢ C4.5
ā¢ Random forests
ā¢ Bayesian networks
ā¢ Hidden Markov models
ā¢ Artificial neural network
ā¢ Data clustering
ā¢ Expectation-maximization
algorithm
ā¢ Self-organizing map
ā¢ Radial basis function network
ā¢ Vector Quantization
ā¢ Generative topographic map
ā¢ Information bottleneck method
ā¢ IBSEAD
ā¢ Apriori algorithm
ā¢ Eclat algorithm
ā¢ FP-growth algorithm
ā¢ Single-linkage clustering
ā¢ Conceptual clustering
ā¢ K-means algorithm
ā¢ Fuzzy clustering
ā¢ Temporal difference learning
ā¢ Q-learning
ā¢ Learning Automata
ā¢ AODE
ā¢ Artificial neural network
ā¢ Backpropagation
ā¢ Naive Bayes classifier
ā¢ Bayesian network
ā¢ Bayesian knowledge base
ā¢ Case-based reasoning
ā¢ Decision trees
ā¢ Inductive logic
programming
ā¢ Gaussian process regression
ā¢ Gene expression
programming
ā¢ Group method of data
handling (GMDH)
ā¢ Learning Automata
ā¢ Learning Vector
Quantization
ā¢ Logistic Model Tree
ā¢ Decision tree
ā¢ Decision graphs
ā¢ Lazy learning
ā¢ Monte Carlo Method
ā¢ SARSA
ā¢ Instance-based learning
ā¢ Nearest Neighbor Algorithm
ā¢ Analogical modeling
ā¢ Probably approximately correct learning
(PACL)
ā¢ Symbolic machine learning algorithms
ā¢ Subsymbolic machine learning algorithms
ā¢ Support vector machines
ā¢ Random Forest
ā¢ Ensembles of classifiers
ā¢ Bootstrap aggregating (bagging)
ā¢ Boosting (meta-algorithm)
ā¢ Ordinal classification
ā¢ Regression analysis
ā¢ Information fuzzy networks (IFN)
ā¢ Linear classifiers
ā¢ Fisher's linear discriminant
ā¢ Logistic regression
ā¢ Naive Bayes classifier
ā¢ Perceptron
ā¢ Support vector machines
ā¢ Quadratic classifiers
ā¢ k-nearest neighbor
ā¢ Boosting
Pick another algorithm
78. ā¢ C4.5
ā¢ Random forests
ā¢ Bayesian networks
ā¢ Hidden Markov models
ā¢ Artificial neural network
ā¢ Data clustering
ā¢ Expectation-maximization
algorithm
ā¢ Self-organizing map
ā¢ Radial basis function network
ā¢ Vector Quantization
ā¢ Generative topographic map
ā¢ Information bottleneck method
ā¢ IBSEAD
ā¢ Apriori algorithm
ā¢ Eclat algorithm
ā¢ FP-growth algorithm
ā¢ Single-linkage clustering
ā¢ Conceptual clustering
ā¢ K-means algorithm
ā¢ Fuzzy clustering
ā¢ Temporal difference learning
ā¢ Q-learning
ā¢ Learning Automata
ā¢ AODE
ā¢ Artificial neural network
ā¢ Backpropagation
ā¢ Naive Bayes classifier
ā¢ Bayesian network
ā¢ Bayesian knowledge base
ā¢ Case-based reasoning
ā¢ Decision trees
ā¢ Inductive logic
programming
ā¢ Gaussian process regression
ā¢ Gene expression
programming
ā¢ Group method of data
handling (GMDH)
ā¢ Learning Automata
ā¢ Learning Vector
Quantization
ā¢ Logistic Model Tree
ā¢ Decision tree
ā¢ Decision graphs
ā¢ Lazy learning
ā¢ Monte Carlo Method
ā¢ SARSA
ā¢ Instance-based learning
ā¢ Nearest Neighbor Algorithm
ā¢ Analogical modeling
ā¢ Probably approximately correct learning
(PACL)
ā¢ Symbolic machine learning algorithms
ā¢ Subsymbolic machine learning algorithms
ā¢ Support vector machines
ā¢ Random Forest
ā¢ Ensembles of classifiers
ā¢ Bootstrap aggregating (bagging)
ā¢ Boosting (meta-algorithm)
ā¢ Ordinal classification
ā¢ Regression analysis
ā¢ Information fuzzy networks (IFN)
ā¢ Linear classifiers
ā¢ Fisher's linear discriminant
ā¢ Logistic regression
ā¢ Naive Bayes classifier
ā¢ Perceptron
ā¢ Support vector machines
ā¢ Quadratic classifiers
ā¢ k-nearest neighbor
ā¢ Boosting
Pick another algorithm