Pedro Domingos, Professor, University of Washington at MLconf ATL - 9/18/15

•

66 likes•16,982 views

The Five Tribes of Machine Learning, and What You Can Take from Each: There are five main schools of thought in machine learning, and each has its own master algorithm – a general-purpose learner that can in principle be applied to any domain. The symbolists have inverse deduction, the connectionists have backpropagation, the evolutionaries have genetic programming, the Bayesians have probabilistic inference, and the analogizers have support vector machines. What we really need, however, is a single algorithm combining the key features of all of them. In this talk I will describe my work toward this goal, including in particular Markov logic networks, and speculate on the new applications that such a universal learner will enable, and how society will change as a result.

Technology

And What You Can
Take from Each
Pedro Domingos
University of Washington

Most of the knowledge in the world in the
future is going to be extracted by machines
and will reside in machines.
– Yann LeCun, Director of AI Research, Facebook

1. Fill in gaps in existing knowledge
2. Emulate the brain
3. Simulate evolution
4. Systematically reduce uncertainty
5. Notice similarities between old and new

Tribe Origins Master Algorithm
Symbolists Logic, philosophy Inverse deduction
Connectionists Neuroscience Backpropagation
Evolutionaries Evolutionary biology Genetic programming
Bayesians Statistics Probabilistic inference
Analogizers Psychology Kernel machines

Tom Mitchell Steve Muggleton Ross Quinlan

Addition Subtraction
2
+ 2
―――
= ?
――
2
+ ?
―――
= 4
――

Deduction
Socrates is human
+ Humans are mortal .
―――――――――――
= ?
Induction
Socrates is human
+ ?
―――――――――――
= Socrates is mortal
―――――――――― ――――――――――

David Heckerman Judea Pearl Michael Jordan

Peter Hart Vladimir Vapnik Douglas Hofstadter

Tribe Problem Solution
Symbolists Knowledge composition Inverse deduction
Connectionists Credit assignment Backpropagation
Evolutionaries Structure discovery Genetic programming
Bayesians Uncertainty Probabilistic inference
Analogizers Similarity Kernel machines

Representation
Probabilistic logic (e.g., Markov logic networks)
Weighted formulas → Distribution over states
Evaluation
Posterior probability
User-defined objective function
Optimization
Formula discovery: Genetic programming
Weight learning: Backpropagation

Much remains to be done . . .
We need your ideas

Home Robots
Cancer Cures 360o Recommenders
World Wide Brains

If we used all our technology resources,
we could actually give people personalized
recommendations for every step of your life.
– Aneesh Chopra, former CTO of the U.S.

Pedro Domingos, Professor, University of Washington at MLconf ATL - 9/18/15

What's hot

The presentation is made on CNN's which is explained using the image classification problem, the presentation was prepared in perspective of understanding computer vision and its applications. I tried to explain the CNN in the most simple way possible as for my understanding. This presentation helps the beginners of CNN to have a brief idea about the architecture and different layers in the architecture of CNN with the example. Please do refer the references in the last slide for a better idea on working of CNN. In this presentation, I have also discussed the different types of CNN(not all) and the applications of Computer Vision.

Convolution Neural Network (CNN)

Suraj Aavula

Computer vision has started to achieve some very impressive results over the last 5-10 years. It is now possible to quickly and reliably detect faces, recognize and localize target images, and even classify pictures of objects into generic categories. Unfortunately, knowledge of these techniques remains largely confined to academia. In this session we’ll go over some of the tools available, placing an emphasis on exploring the ideas and algorithms behind their design. To show how these components can be put together, a sample system will be developed over the course of the presentation. Starting with standard image descriptors, we’ll first see how to do direct image recognition. We’ll then extend that into a simple object classifier, which will be able to distinguish (for example) between images which contain a bicycle and those that don’t.

An Introduction to Computer Vision

guestd1b1b5

Computational Thinking

showslidedump

Introduction to pattern recognization

Ajharul Abedeen

Deep Neural Networks (DNN)

Sir Syed University of Engineering & Technology

Technical Quiz (Basic concepts of computers)

Manpreet Kaur

Machine Learning vs Deep Learning vs Artificial Intelligence | ML vs DL vs AI...

Simplilearn

K - Nearest neighbor ( KNN )

Mohammad Junaid Khan

CAPTCHA

Dhruv Patel

https://telecombcn-dl.github.io/2017-dlcv/ Deep learning technologies are at the core of the current revolution in artificial intelligence for multimedia data analysis. The convergence of large-scale annotated datasets and affordable GPU hardware has allowed the training of neural networks for data analysis tasks which were previously addressed with hand-crafted features. Architectures such as convolutional neural networks, recurrent neural networks and Q-nets for reinforcement learning have shaped a brand new scenario in signal processing. This course will cover the basic principles and applications of deep learning to computer vision problems, such as image classification, object detection or image captioning.

Image classification on Imagenet (D1L4 2017 UPC Deep Learning for Computer Vi...

Universitat Politècnica de Catalunya

https://telecombcn-dl.github.io/2017-dlai/ Deep learning technologies are at the core of the current revolution in artificial intelligence for multimedia data analysis. The convergence of large-scale annotated datasets and affordable GPU hardware has allowed the training of neural networks for data analysis tasks which were previously addressed with hand-crafted features. Architectures such as convolutional neural networks, recurrent neural networks or Q-nets for reinforcement learning have shaped a brand new scenario in signal processing. This course will cover the basic principles of deep learning from both an algorithmic and computational perspectives.

Loss functions (DLAI D4L2 2017 UPC Deep Learning for Artificial Intelligence)

Universitat Politècnica de Catalunya

Extraction of region of interest in an image

Harsukh Chandak

The presentation briefly answers the questions: 1. What is Machine Learning? 2. Ideas behind Neural Networks? 3. What is Deep Learning? How different is it from NN? 4. Practical examples of applications. For more information: https://www.quora.com/How-does-deep-learning-work-and-how-is-it-different-from-normal-neural-networks-and-or-SVM http://stats.stackexchange.com/questions/114385/what-is-the-difference-between-convolutional-neural-networks-restricted-boltzma https://www.youtube.com/watch?v=n1ViNeWhC24 - presentation by Ng http://techtalks.tv/talks/deep-learning/58122/ - deep learning tutorial and slides - http://www.cs.nyu.edu/~yann/talks/lecun-ranzato-icml2013.pdf Deep learning for NLP - http://www.socher.org/index.php/DeepLearningTutorial/DeepLearningTutorial papers: http://www.cs.toronto.edu/~hinton/science.pdf http://machinelearning.wustl.edu/mlpapers/paper_files/AISTATS2010_ErhanCBV10.pdf http://arxiv.org/pdf/1206.5538v3.pdf http://arxiv.org/pdf/1404.7828v4.pdf More recommendations - https://www.quora.com/What-are-the-best-resources-to-learn-about-deep-learning

Deep learning - what is it and why now?

Natalia Konstantinova

BIG DATA AND MACHINE LEARNING

Umair Shafique

Computer Vision Introduction

Camera Culture Group, MIT Media Lab

Pattern Recognition

Talal Alsubaie

An Introduction to Image Processing and Artificial Intelligence

Wasif Altaf

Autoencoder

Mehrnaz Faraz

hands on machine learning Chapter 6&7 decision tree, ensemble and random forest

Jaey Jeong

Gaussian Bayes Classifiers

guestfee8698

What's hot (20)

Convolution Neural Network (CNN)

An Introduction to Computer Vision

Computational Thinking

Introduction to pattern recognization

Deep Neural Networks (DNN)

Technical Quiz (Basic concepts of computers)

Machine Learning vs Deep Learning vs Artificial Intelligence | ML vs DL vs AI...

K - Nearest neighbor ( KNN )

CAPTCHA

Image classification on Imagenet (D1L4 2017 UPC Deep Learning for Computer Vi...

Loss functions (DLAI D4L2 2017 UPC Deep Learning for Artificial Intelligence)

Extraction of region of interest in an image

Deep learning - what is it and why now?

BIG DATA AND MACHINE LEARNING

Computer Vision Introduction

Pattern Recognition

An Introduction to Image Processing and Artificial Intelligence

Autoencoder

hands on machine learning Chapter 6&7 decision tree, ensemble and random forest

Gaussian Bayes Classifiers

Similar to Pedro Domingos, Professor, University of Washington at MLconf ATL - 9/18/15

superintelligence

Alakesh Dhibar

In "Homo Deus", Yuval Harari proposes two speculations as answers to these questions: Techno-humanism and Data Religion. The former is growing from our urge to improve ourselves, the latter growing from our belief in everything that is measurable. What are the strengths and weaknesses of these ideologies? How do they relate to current local and global problems: are there any connections at all? Shall humanity proactively seek new healthy narratives? How about today's religions: will they stand the test of time?

"Homo Deus": Emerging Narratives for the Future

Paweł Skorupiński

Humanism, Transhumanism and Posthumanism The Humanist and the transhumanist propose different methods for cultivating human capacities. The transhumanists claims that traditional techniques favoured by the humanist run up against the limits of our biology. She believes that prospective technologies could further the humanist cause by improving our nature. However, the transhumanist faces a difficulty. Her policies could produce posthumans. Evaluating posthuman lives might be impossible for us. But discounting them is not an option because she will share responsibility for their creation. I argue that one way through this impasse is for the transhumanist to produce posthumans or to become posthuman.

My night with philosophers presentation - London June 8

David Roden

Jdb code biology and ai final

Joachim De Beule

Software update for human brain, at a large scale

2co

Alien Minds

Luisa Polanco

Future possibilities for education and learning by the year 2030

Associação Brasileira de Mantenedoras de Ensino Superior

Mind in a designed world

Karlos Svoboda

University in the age of smartphone

Mathias Klang

RoRILaunch 3 CAREERS Evans

RoRInstitute

Life, the Universe, and Information Processing

Epi Ludvik Nekaj 宇赫

Life, the Universe, and Information Processing

Crowdsourcing Week

Man’s dreams of ‘intelligences and robots’ go back thousands of years to the worship of gods and statues; mythologies: talisman and puppets; people, places and objects with supposed magical and (often) judgemental/punitive abilities. But it wasn’t until the electronic revolution in 1915, accelerated by WWII that we saw the realisation of two game changing-machines: Colossus (Decoding Machine of Bletchley Park) 1943 and ENIAC (Artillery Computation Engine and Nuclear Bomb Design @ The University of Pennsylvania) 1946. And so in 1950 the modern AI movement was optimistically projecting what machines would be capable of ‘almost anything’ by 1960/70. Unfortunately, there was no understanding of the complexity to be addressed, and all the projections were wildly wrong; leading to a deep trough of disparagement and disillusionment of some 30 years. However, 70 years on and the original AI optimism and projections of what might be had at least been largely achieved with AI outgunning humans at every board and card game including Poker and GO, and of course; general knowledge, medical diagnosis, image and information pattern recognition…

AI Fables, Facts and Futures: Threat, Promise or Saviour

University of Hertfordshire

Transhumanism and Religion

Giulio Prisco

World Future Society panel on Long-term tech and humanity

Jerome Glenn

Presented by Jerome Glenn “The future doesn’t need us,” Bill Joy said in his famous 2001 WIRED article. He warned us of the threats posed by advanced technologies, and suggested we should slow down their advancement. Many today agree with Joy. The evolution of our knowledge about nature and the evolution of nature itself have come to a historic crossroads, others claim. It took billions of years for nature to produce our universe, a planet called Earth and a living species able to ask questions and create answers. It took humans just decades to develop a technology to bring our collective knowledge back to life deep within the brains of super computers and show it on the screens of Ipads and smart phones. With digital technology, an astonishing transformation is taking place right in front of our eyes. Since the Big Bang, nature has been the sole creator of the future. Until humans came along and unraveled nature’s tricks, enough so to take away its monopoly, and bring us to the most important crossroads in the history of our universe.

What If the Future Needs Us?

Cynthia G. Wagner

The Technological Singularity - Prepare for the Disruption of Human Intelligence

Manuel Koelman

iPhone Living: On using and being abused by technology

Mathias Klang

Transhumanismo

Fernando Broncano R

Computers what-about_our_future

Kwame Afreh

Similar to Pedro Domingos, Professor, University of Washington at MLconf ATL - 9/18/15 (20)

superintelligence

"Homo Deus": Emerging Narratives for the Future

My night with philosophers presentation - London June 8

Jdb code biology and ai final

Software update for human brain, at a large scale

Alien Minds

Future possibilities for education and learning by the year 2030

Mind in a designed world

University in the age of smartphone

RoRILaunch 3 CAREERS Evans

Life, the Universe, and Information Processing

AI Fables, Facts and Futures: Threat, Promise or Saviour

Transhumanism and Religion

World Future Society panel on Long-term tech and humanity

What If the Future Needs Us?

The Technological Singularity - Prepare for the Disruption of Human Intelligence

iPhone Living: On using and being abused by technology

Transhumanismo

Computers what-about_our_future

More from MLconf

Understanding Human Impact: Social and Equity Assessments for AI Technologies Social and Equity Impact Assessments have broad applications but can be a useful tool to explore and mitigate for Machine Learning fairness issues and can be applied to product specific questions as a way to generate insights and learnings about users, as well as impacts on society broadly as a result of the deployment of new and emerging technologies. In this presentation, my goal is to advocate for and highlight the need to consult community and external stakeholder engagement to develop a new knowledge base and understanding of the human and social consequences of algorithmic decision making and to introduce principles, methods and process for these types of impact assessments.

Jamila Smith-Loud - Understanding Human Impact: Social and Equity Assessments...

MLconf

The Brain’s Guide to Dealing with Context in Language Understanding Like the visual cortex, the regions of the brain involved in understanding language represent information hierarchically. But whereas the visual cortex organizes things into a spatial hierarchy, the language regions encode information into a hierarchy of timescale. This organization is key to our uniquely human ability to integrate semantic information across narratives. More and more, deep learning-based approaches to natural language understanding embrace models that incorporate contextual information at varying timescales. This has not only led to state-of-the art performance on many difficult natural language tasks, but also to breakthroughs in our understanding of brain activity. In this talk, we will discuss the important connection between language understanding and context at different timescales. We will explore how different deep learning architectures capture timescales in language and how closely their encodings mimic the brain. Along the way, we will uncover some surprising discoveries about what depth does and doesn’t buy you in deep recurrent neural networks. And we’ll describe a new, more flexible way to think about these architectures and ease design space exploration. Finally, we’ll discuss some of the exciting applications made possible by these breakthroughs.

Ted Willke - The Brain’s Guide to Dealing with Context in Language Understanding

MLconf

Applying Computer Vision to Reduce Contamination in the Recycling Stream With China’s recent refusal of most foreign recyclables, North American waste haulers are scrambling to figure out how to make on-shore recycling cost-effective in order to continue providing recycling services. Recyclables that were once being shipped to China for manual sorting are now primarily being redirected to landfills or incinerators. Without a solution, a nearly $5 billion annual recycling market could come to a halt. Purity in the recycling stream is key to this effort as contaminants in the stream can increase the cost of operations, damage equipment and reduce the ability to create pure commodities suitable for creating recycled goods. This market disruption as a result of China’s new regulations, however, provides us the chance to re-examine and improve our current disposal & collection habits with modern monitoring & artificial intelligence technology. Using images from our in-dumpster cameras, Compology has developed an ML-based process that helps identify, measure and alert for contaminants in recycling containers before they are picked-up, helping keep the recycling stream clean. Our convolutional neural network flags potential instances of contamination inside a dumpster, enabling garbage haulers to know which containers have the wrong type of material inside. This allows them to provide targeted, timely education, and when appropriate, assess fines, to improve recycling compliance at the businesses and residences they serve, helping keep recycling services financially viable. In this presentation, we will walk through our ML-based contamination measurement and scoring process by showing how Waste Management, a national waste hauler, has experienced 57% contamination reduction in nearly 2,000 containers over six months, This progress shows significant strides towards financially viable recycling services.

Justin Armstrong - Applying Computer Vision to Reduce Contamination in the Re...

MLconf

Quantum Computing: a Treasure Hunt, not a Gold Rush Quantum computers promise a significant step up in computational power over conventional computers, but also suffer a number of counterintuitive limitations --- both in their computational model and in leading lab implementations. In this talk, we review how quantum computers compete with conventional computers and how conventional computers try to hold their ground. Then we outline what stands in the way of successful quantum ML applications.

Igor Markov - Quantum Computing: a Treasure Hunt, not a Gold Rush

MLconf

Data Labeling as Religious Experience One of the most common places to deploy a production machine learning systems is as a replacement for a legacy rules-based system that is having a hard time keeping up with new edge cases and requirements. I'll be walking through the process and tooling we used to help us design, train, and deploy a model to replace a set of static rules we had for handling invite spam at Slack, talk about what we learned, and discuss some problems to solve in order to make these migrations easier for everyone.

Josh Wills - Data Labeling as Religious Experience

MLconf

Project GaitNet: Ushering in the ImageNet moment for human Gait kinematics The emergence of the upright human bipedal gait can be traced back 4 to 2.8 million years ago, to the now extinct hominin Australopithecus afarensis. Fine grained analysis of gait using the modern MEMS sensors found on all smartphones not just reveals a lot about the person’s orthopedic and neuromuscular health status, but also has enough idiosyncratic clues that it can be harnessed as a passive biometric. While there were many siloed attempts made by the machine learning community to model Bipedal Gait sensor data, these were done with small datasets oft collected in restricted academic environs. In this talk, we will introduce the ImageNet moment for human gait analysis by presenting 'Project GaitNet', the largest ever planet-sized motion sensor based human bipedal gait dataset ever curated. We’ll also present the associated state-of-the-art results in classifying humans harnessing novel deep neural architectures and the related success stories we have enjoyed in transfer-learning into disparate domains of human kinematics analysis.

Vinay Prabhu - Project GaitNet: Ushering in the ImageNet moment for human Gai...

MLconf

Machine Learning Methods in Detecting Alzheimer’s Disease from Speech and Language Alzheimer's disease affects millions of people worldwide, and it is important to predict the disease as early and as accurate as possible. In this talk, I will discuss development of novel ML models that help classifying healthy people from those who develop Alzheimer's, using short samples of human speech. As an input to the model, features of different modalities are extracted from speech audio samples and transcriptions: (1) syntactic measures, such as e.g. production rules extracted from syntactic parse trees, (2) lexical measures, such as e.g. features of lexical richness and complexity and lexical norms, and (3) acoustic measures, such as e.g. standard Mel-frequency cepstral coefficients. I will present the ML model that detects cognitive impairment by reaching agreement among modalities. The resulting model is able to achieve state of the art performance in both supervised and semi-supervised manner, using manual transcripts of human speech. Additionally, I will discuss potential limitations of any fully-automated speech-based Alzheimer's disease detection model, focusing mostly on the analysis of the impact of a not-so-accurate automatic speech recognition (ASR) on the classification performance. To illustrate this, I will present the experiments with controlled amounts of artificially generated ASR errors and explain how the deletion errors affect Alzheimer's detection performance the most, due to their impact on the features of syntactic and lexical complexity.

Jekaterina Novikova - Machine Learning Methods in Detecting Alzheimer’s Disea...

MLconf

Optimized Image Classification on the Cheap In this talk, we anchor on building an image classifier trained on the Stanford Cars dataset to evaluate two approaches to transfer learning -fine tuning and feature extraction- and the impact of hyperparameter optimization on these techniques. Once we define the most performant transfer learning technique for Stanford Cars, we will double the size of the dataset through image augmentation to boost the classifier’s performance. We will use Bayesian optimization to learn the hyperparameters associated with image transformations using the downstream image classifier’s performance as the guide. In conjunction with model performance, we will also focus on the features of these augmented images and the downstream implications for our image classifier. To both maximize model performance on a budget and explore the impact of optimization on these methods, we apply a particularly efficient implementation of Bayesian optimization to each of these architectures in this comparison. Our goal is to draw on a rigorous set of experimental results that can help us answer the question: how can resource-constrained teams make trade-offs between efficiency and effectiveness using pre-trained models?

Meghana Ravikumar - Optimized Image Classification on the Cheap

MLconf

The Importance of Modeling Data Collection Data sets used in machine learning are often collected in a systematically biased way - certain data points are more likely to be collected than others. We call this "observation bias". For example, in health care, we are more likely to see lab tests when the patient is feeling unwell than otherwise. Failing to account for observation bias can, of course, result in poor predictions on new data. By contrast, properly accounting for this bias allows us to make better use of the data we do have. In this presentation, we discuss practical and theoretical approaches to dealing with observation bias. When the nature of the bias is known, there are simple adjustments we can make to nonparametric function estimation techniques, such as Gaussian Process models. We also discuss the scenario where the data collection model is unknown. In this case, there are steps we can take to estimate it from observed data. Finally, we demonstrate that having a small subset of data points that are known to be collected at random - that is, in an unbiased way - can vastly improve our ability to account for observation bias in the rest of the data set. My hope is that attendees of this presentation will be aware of the perils of observation bias in their own work, and be equipped with tools to address it.

Noam Finkelstein - The Importance of Modeling Data Collection

MLconf

The Uncanny Valley of ML Every so often, the conundrum of the Uncanny Valley re-emerges as advanced technologies evolve from clearly experimental products to refined accepted technologies. We have seen its effects in robotics, computer graphics, and page load times. The debate of how to handle the new technology detracts from its benefits. When machine learning is added to human decision systems a similar effect can be measured in increased response time and decreased accuracy. These systems include radiology, judicial assignments, bus schedules, housing prices, power grids and a growing variety of applications. Unfortunately, the Uncanny Valley of ML can be hard to detect in these systems and can lead to degraded system performance when ML is introduced, at great expense. Here, we'll introduce key design principles for introducing ML into human decision systems to navigate around the Uncanny Valley and avoid its pitfalls.

June Andrews - The Uncanny Valley of ML

MLconf

Deep Learning Architectures for Semantic Relation Detection Tasks Recognizing and distinguishing specific semantic relations from other types of semantic relations is an essential part of language understanding systems. Identifying expressions with similar and contrasting meanings is valuable for NLP systems which go beyond recognizing semantic relatedness and require to identify specific semantic relations. In this talk, I will first present novel techniques for creating labelled datasets required for training deep learning models for classifying semantic relations between phrases. I will further present various neural network architectures that integrate morphological features into integrated path-based and distributional relation detection algorithms and demonstrate that this model outperforms state-of-the-art models in distinguishing semantic relations and is capable of efficiently handling multi-word expressions.

Sneha Rajana - Deep Learning Architectures for Semantic Relation Detection Tasks

MLconf

Building an Incrementally Trained, Local Taste Aware, Global Deep Learned Recommender System Model At Netflix, our main goal is to maximize our members’ enjoyment of the selected show by minimizing the amount of time it takes for them to find it. We try to achieve this goal by personalizing almost all the aspects of our product -- from what shows to recommend, to how to present these shows and construct their home-pages to what images to select per show, among many other things. Everything is recommendations for us and as an applied Machine Learning group, we spend our time building models for personalization that will eventually increase the joy and satisfaction of our members. In this talk we will primarily focus our attention on a) making a global deep learned recommender model that is regional tastes and popularity aware and b) adapting this model to changing taste preferences as well as dynamic catalog availability. We will first go through some standard recommender system models that use Matrix Factorization and Topic Models and then compare and contrast them with more powerful and higher capacity deep learning based models such as sequence models that use recurrent neural networks. We will show what it entails to build a global model that is aware of regional taste preferences and catalog availability. We will show how models that are built on simple Maximum Likelihood principle fail to do that. We will then describe one solution that we have employed in order to enable the global deep learned models to focus their attention on capturing regional taste preferences and changing catalog.In the latter half of the talk, we will discuss how we do incremental learning of deep learned recommender system models. Why do we need to do that ? Everything changes with time. Users’ tastes change with time. What’s available on Netflix and what’s popular also change over time. Therefore, updating or improving recommendation systems over time is necessary to bring more joy to users. In addition to how we apply incremental learning, we will discuss some of the challenges we face involving large-scale data preparation, infrastructure setup for incremental model training as well as pipeline scheduling. The incremental training enables us to serve fresher models trained on fresher and larger amounts of data. This helps our recommender system to nicely and quickly adapt to catalog and users’ taste changes, and improve overall performance.

Anoop Deoras - Building an Incrementally Trained, Local Taste Aware, Global D...

MLconf

Vito Ostuni - The Voice: New Challenges in a Zero UI World The adoption of voice-enabled devices has seen an explosive growth in the last few years and music consumption is among the most popular use cases. Music personalization and recommendation plays a major role at Pandora in providing a daily delightful listening experience for millions of users. In turn, providing the same perfectly tailored listening experience through these novel voice interfaces brings new interesting challenges and exciting opportunities. In this talk we will describe how we apply personalization and recommendation techniques in three common voice scenarios which can be defined in terms of request types: known-item, thematic, and broad open-ended. We will describe how we use deep learning slot filling techniques and query classification to interpret the user intent and identify the main concepts in the query. We will also present the differences and challenges regarding evaluation of voice powered recommendation systems. Since pure voice interfaces do not contain visual UI elements, relevance labels need to be inferred through implicit actions such as play time, query reformulations or other types of session level information. Another difference is that while the typical recommendation task corresponds to recommending a ranked list of items, a voice play request translates into a single item play action. Thus, some considerations about closed feedback loops need to be made. In summary, improving the quality of voice interactions in music services is a relatively new challenge and many exciting opportunities for breakthroughs still remain. There are many new aspects of recommendation system interfaces to address to bring a delightful and effortless experience for voice users. We will share a few open challenges to solve for the future.

Vito Ostuni - The Voice: New Challenges in a Zero UI World

MLconf

Anna choromanska - Data-driven Challenges in AI: Scale, Information Selection...

MLconf

Janani Kalyanam - Machine Learning to Detect Illegal Online Sales of Prescrip...

MLconf

Esperanza Lopez Aguilera - Using a Bayesian Neural Network in the Detection o...

MLconf

Neel Sundaresan - Teaching a machine to code

MLconf

Rishabh Mehrotra - Recommendations in a Marketplace: Personalizing Explainabl...

MLconf

Soumith Chintala - Increasing the Impact of AI Through Better Software

MLconf

Roy Lowrance - Predicting Bond Prices: Regime Changes

MLconf

More from MLconf (20)

Jamila Smith-Loud - Understanding Human Impact: Social and Equity Assessments...

Ted Willke - The Brain’s Guide to Dealing with Context in Language Understanding

Justin Armstrong - Applying Computer Vision to Reduce Contamination in the Re...

Igor Markov - Quantum Computing: a Treasure Hunt, not a Gold Rush

Josh Wills - Data Labeling as Religious Experience

Vinay Prabhu - Project GaitNet: Ushering in the ImageNet moment for human Gai...

Jekaterina Novikova - Machine Learning Methods in Detecting Alzheimer’s Disea...

Meghana Ravikumar - Optimized Image Classification on the Cheap

Noam Finkelstein - The Importance of Modeling Data Collection

June Andrews - The Uncanny Valley of ML

Sneha Rajana - Deep Learning Architectures for Semantic Relation Detection Tasks

Anoop Deoras - Building an Incrementally Trained, Local Taste Aware, Global D...

Vito Ostuni - The Voice: New Challenges in a Zero UI World

Anna choromanska - Data-driven Challenges in AI: Scale, Information Selection...

Janani Kalyanam - Machine Learning to Detect Illegal Online Sales of Prescrip...

Esperanza Lopez Aguilera - Using a Bayesian Neural Network in the Detection o...

Neel Sundaresan - Teaching a machine to code

Rishabh Mehrotra - Recommendations in a Marketplace: Personalizing Explainabl...

Soumith Chintala - Increasing the Impact of AI Through Better Software

Roy Lowrance - Predicting Bond Prices: Regime Changes

Recently uploaded

Advantages of Hiring UIUX Design Service Providers for Your Business

Pixlogix Infotech

Building Digital Trust in a Digital Economy Veronica Tan, Director - Cyber Security Agency of Singapore Apidays Singapore 2024: Connecting Customers, Business and Technology (April 17 & 18, 2024) ------ Check out our conferences at https://www.apidays.global/ Do you want to sponsor or talk at one of our conferences? https://apidays.typeform.com/to/ILJeAaV8 Learn more on APIscene, the global media made by the community for the community: https://www.apiscene.io Explore the API ecosystem with the API Landscape: https://apilandscape.apiscene.io/

Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...

apidays

Effective data discovery is crucial for maintaining compliance and mitigating risks in today's rapidly evolving privacy landscape. However, traditional manual approaches often struggle to keep pace with the growing volume and complexity of data. Join us for an insightful webinar where industry leaders from TrustArc and Privya will share their expertise on leveraging AI-powered solutions to revolutionize data discovery. You'll learn how to: - Effortlessly maintain a comprehensive, up-to-date data inventory - Harness code scanning insights to gain complete visibility into data flows leveraging the advantages of code scanning over DB scanning - Simplify compliance by leveraging Privya's integration with TrustArc - Implement proven strategies to mitigate third-party risks Our panel of experts will discuss real-world case studies and share practical strategies for overcoming common data discovery challenges. They'll also explore the latest trends and innovations in AI-driven data management, and how these technologies can help organizations stay ahead of the curve in an ever-changing privacy landscape.

TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery

TrustArc

Created by Mozilla Research in 2012 and now part of Linux Foundation Europe, the Servo project is an experimental rendering engine written in Rust. It combines memory safety and concurrency to create an independent, modular, and embeddable rendering engine that adheres to web standards. Stewardship of Servo moved from Mozilla Research to the Linux Foundation in 2020, where its mission remains unchanged. After some slow years, in 2023 there has been renewed activity on the project, with a roadmap now focused on improving the engine’s CSS 2 conformance, exploring Android support, and making Servo a practical embeddable rendering engine. In this presentation, Rakhi Sharma reviews the status of the project, our recent developments in 2023, our collaboration with Tauri to make Servo an easy-to-use embeddable rendering engine, and our plans for the future to make Servo an alternative web rendering engine for the embedded devices industry. (c) Embedded Open Source Summit 2024 April 16-18, 2024 Seattle, Washington (US) https://events.linuxfoundation.org/embedded-open-source-summit/ https://ossna2024.sched.com/event/1aBNF/a-year-of-servo-reboot-where-are-we-now-rakhi-sharma-igalia

A Year of the Servo Reboot: Where Are We Now?

Igalia

presentation ICT roal in 21st century education

jfdjdjcjdnsjd

Partners Life - Insurer Innovation Award 2024

The Digital Insurer

A Domino Admins Adventures (Engage 2024)

Gabriella Davis

Enterprise Knowledge’s Urmi Majumder, Principal Data Architecture Consultant, and Fernando Aguilar Islas, Senior Data Science Consultant, presented "Driving Behavioral Change for Information Management through Data-Driven Green Strategy" on March 27, 2024 at Enterprise Data World (EDW) in Orlando, Florida. In this presentation, Urmi and Fernando discussed a case study describing how the information management division in a large supply chain organization drove user behavior change through awareness of the carbon footprint of their duplicated and near-duplicated content, identified via advanced data analytics. Check out their presentation to gain valuable perspectives on utilizing data-driven strategies to influence positive behavioral shifts and support sustainability initiatives within your organization. In this session, participants gained answers to the following questions: - What is a Green Information Management (IM) Strategy, and why should you have one? - How can Artificial Intelligence (AI) and Machine Learning (ML) support your Green IM Strategy through content deduplication? - How can an organization use insights into their data to influence employee behavior for IM? - How can you reap additional benefits from content reduction that go beyond Green IM?

Driving Behavioral Change for Information Management through Data-Driven Gree...

Enterprise Knowledge

Abhishek Deb(1), Mr Abdul Kalam(2) M. Des (UX) , School of Design, DIT University , Dehradun. This paper explores the future potential of AI-enabled smartphone processors, aiming to investigate the advancements, capabilities, and implications of integrating artificial intelligence (AI) into smartphone technology. The research study goals consist of evaluating the development of AI in mobile phone processors, analyzing the existing state as well as abilities of AI-enabled cpus determining future patterns as well as chances together with reviewing obstacles as well as factors to consider for more growth.

Exploring the Future Potential of AI-Enabled Smartphone Processors

debabhi2

How to Troubleshoot Apps for the Modern Connected Worker

ThousandEyes

Join our latest Connector Corner webinar to discover how UiPath Integration Service revolutionizes API-centric automation in a 'Quote to Cash' process—and how that automation empowers businesses to accelerate revenue generation. A comprehensive demo will explore connecting systems, GenAI, and people, through powerful pre-built connectors designed to speed process cycle times. Speakers: James Dickson, Senior Software Engineer Charlie Greenberg, Host, Product Marketing Manager

Connector Corner: Accelerate revenue generation using UiPath API-centric busi...

DianaGray10

GenCyber Cyber Security Day Presentation

Michael W. Hawkins

Developing An App To Navigate The Roads of Brazil

V3cube

Discord is a free app offering voice, video, and text chat functionalities, primarily catering to the gaming community. It serves as a hub for users to create and join servers tailored to their interests. Discord’s ecosystem comprises servers, each functioning as a distinct online community with its own channels dedicated to specific topics or activities. Users can engage in text-based discussions, voice calls, or video chats within these channels. Understanding Discord Servers Discord servers are virtual spaces where users congregate to interact, share content, and build communities. Servers may revolve around gaming, hobbies, interests, or fandoms, providing a platform for like-minded individuals to connect. Communication Features Discord offers a range of communication tools, including text channels for messaging, voice channels for real-time audio conversations, and video channels for face-to-face interactions. These features facilitate seamless communication and collaboration. What Does NSFW Mean? The acronym NSFW stands for “Not Safe For Work,” indicating content that may be inappropriate for professional or public settings. NSFW Content NSFW content encompasses material that is sexually explicit, violent, or otherwise graphic in nature. It often includes nudity, profanity, or depictions of sensitive topics.

Understanding Discord NSFW Servers A Guide for Responsible Users.pdf

UK Journal

2024: Domino Containers - The Next Step. News from the Domino Container commu...

Martijn de Jong

Data Cloud, More than a CDP by Matt Robison

Anna Loughnan Colquhoun

Strategies for Landing an Oracle DBA Job as a Fresher

Remote DBA Services

🐬 The future of MySQL is Postgres 🐘

RTylerCroy

MySQL Webinar, presented on the 25th of April, 2024. Summary: MySQL solutions enable the deployment of diverse Database Architectures tailored to specific needs, including High Availability, Disaster Recovery, and Read Scale-Out. With MySQL Shell's AdminAPI, administrators can seamlessly set up, manage, and monitor these solutions, ensuring efficiency and ease of use in their administration. MySQL Router, on the other hand, provides transparent routing from the application traffic to the backend servers in the architectures, requiring minimal configuration. Completely built in-house and supported by Oracle, these solutions have been adopted by enterprises of all sizes for their business-critical applications. In this presentation, we'll delve into various database architecture solutions to help you choose the right one based on your business requirements. Focusing on technical details and the latest features to maximize the potential of these solutions.

Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...

Miguel Araújo

In this session, we will delve into strategic approaches for optimizing knowledge management within Microsoft 365, amidst the evolving landscape of Copilot. From leveraging automatic metadata classification and permission governance with SharePoint Premium, to unlocking Viva Engage for the cultivation of knowledge and communities, you will gain actionable insights to bolster your organization's knowledge-sharing initiatives. In this session, we will also explore how to facilitate solutions to enable your employees to find answers and expertise within Microsoft 365. You will leave equipped with practical techniques and a deeper understanding of how there is more to effective knowledge management than just enabling Copilot, but building actual solutions to prepare the knowledge that Copilot and your employees can use.

Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...

Drew Madelung

Recently uploaded (20)

Advantages of Hiring UIUX Design Service Providers for Your Business

Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...

TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery

A Year of the Servo Reboot: Where Are We Now?

presentation ICT roal in 21st century education

Partners Life - Insurer Innovation Award 2024

A Domino Admins Adventures (Engage 2024)

Driving Behavioral Change for Information Management through Data-Driven Gree...

Exploring the Future Potential of AI-Enabled Smartphone Processors

How to Troubleshoot Apps for the Modern Connected Worker

Connector Corner: Accelerate revenue generation using UiPath API-centric busi...

GenCyber Cyber Security Day Presentation

Developing An App To Navigate The Roads of Brazil

Understanding Discord NSFW Servers A Guide for Responsible Users.pdf

2024: Domino Containers - The Next Step. News from the Domino Container commu...

Data Cloud, More than a CDP by Matt Robison

Strategies for Landing an Oracle DBA Job as a Fresher

🐬 The future of MySQL is Postgres 🐘

Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...

Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...

Pedro Domingos, Professor, University of Washington at MLconf ATL - 9/18/15

1. And What You Can Take from Each Pedro Domingos University of Washington

2. Evolution Experience Culture

3. Evolution Experience Culture Computers

4. Most of the knowledge in the world in the future is going to be extracted by machines and will reside in machines. – Yann LeCun, Director of AI Research, Facebook

5. 1. Fill in gaps in existing knowledge 2. Emulate the brain 3. Simulate evolution 4. Systematically reduce uncertainty 5. Notice similarities between old and new

6. Tribe Origins Master Algorithm Symbolists Logic, philosophy Inverse deduction Connectionists Neuroscience Backpropagation Evolutionaries Evolutionary biology Genetic programming Bayesians Statistics Probabilistic inference Analogizers Psychology Kernel machines

7. Tom Mitchell Steve Muggleton Ross Quinlan

8. Addition Subtraction 2 + 2 ――― = ? ―― 2 + ? ――― = 4 ――

9. Deduction Socrates is human + Humans are mortal . ――――――――――― = ? Induction Socrates is human + ? ――――――――――― = Socrates is mortal ―――――――――― ――――――――――

10.

11. Yann LeCun Geoff Hinton Yoshua Bengio

12.

13.

14.

15.

16. John Koza John Holland Hod Lipson

17.

18.

19.

20. David Heckerman Judea Pearl Michael Jordan

21.

22.

23.

24. Peter Hart Vladimir Vapnik Douglas Hofstadter

25.

26.

27.

28. Tribe Problem Solution Symbolists Knowledge composition Inverse deduction Connectionists Credit assignment Backpropagation Evolutionaries Structure discovery Genetic programming Bayesians Uncertainty Probabilistic inference Analogizers Similarity Kernel machines

29. Tribe Problem Solution Symbolists Knowledge composition Inverse deduction Connectionists Credit assignment Backpropagation Evolutionaries Structure discovery Genetic programming Bayesians Uncertainty Probabilistic inference Analogizers Similarity Kernel machines But what we really need is a single algorithm that solves all five!

30. Representation Probabilistic logic (e.g., Markov logic networks) Weighted formulas → Distribution over states Evaluation Posterior probability User-defined objective function Optimization Formula discovery: Genetic programming Weight learning: Backpropagation

31. Much remains to be done . . . We need your ideas

32. Home Robots Cancer Cures 360o Recommenders World Wide Brains

33. If we used all our technology resources, we could actually give people personalized recommendations for every step of your life. – Aneesh Chopra, former CTO of the U.S.

Pedro Domingos, Professor, University of Washington at MLconf ATL - 9/18/15

Recommended

Recommended

More Related Content

What's hot

What's hot (20)

Similar to Pedro Domingos, Professor, University of Washington at MLconf ATL - 9/18/15

Similar to Pedro Domingos, Professor, University of Washington at MLconf ATL - 9/18/15 (20)

More from MLconf

More from MLconf (20)

Recently uploaded

Recently uploaded (20)

Pedro Domingos, Professor, University of Washington at MLconf ATL - 9/18/15