Part I
The state of ML

Part II
The challenges of AI

Part III
The causal viewpoint

Part IV
The algebraic viewpoint

This is an old revision of the document!

From Machine Learning to Artificial Intelligence

ML2AI Feed

There is a big gap between our Machine Learning techniques and our ambition to make a dent in Artificial Intelligence. The purpose of these pages is to explain the nature of the gap, that is, clarify some of the problem we must solve, and describe conceptual tools to reason about them and maybe lead to solutions.

I am planning to add new pages every so often. The most recent additions are listed below in blog style. Since I expect that all these pages will form a coherent ensemble, the sidebar list them as a table of contents, in the order they are expected to be read in the end.

Michael Littman's AI landscape “The Future of AI Symposium”
Michael Littman, 2016


  namespace = "bibtex"
  title =   {Backgammon Computer Program Beats World Champion},
  author =  {Hans J. Berliner}, 
  year =    1980,
  journal = {Artificial Intelligence},
  volume =  14,
  pages =   {205-220},
  url =     {}
  author =  {Léon Bottou and Jonas Peters and Joaquin Quiñonero-Candela 
             and Denis X. Charles and D. Max Chickering and Elon Portugaly 
             and Dipankar Ray and Patrice Simard and Ed Snelson},
  title =   {Counterfactual Reasoning and Learning Systems: The Example of Computational Advertising},
  journal = {Journal of Machine Learning Research},
  year =    2013,
  volume =  14,
  pages =   {3207-3260},
  month =   {Nov},
  url =     {},
  author =       {Krzysztof Chalupka and Frederik Eberhardt and Pietro Perona},
  title =        {Causal feature learning: an overview},
  journal =      {Behaviormetrika},
  year =         2017,
  volume =       44,
  number =       1,
  pages =        {137-164},
  url =          {}
  author =       {James J Gibson},
  title =        {The Theory of Affordances},
  booktitle =    {The Ecological Approach to Visual Perception},
  publisher =    {Taylor & Francis},
  year =         1977,
  chapter =      8,
  url =          {}
  title =        {Behind Deep Blue, Building the Computer that Defeated the World Chess Champion},
  author =       {Feng-hsiung Hsu},
  year =         2004,
  publisher =    {Princeton University Press},
  url =          {},
  author =       {Guido W. Imbens and Donald B. Rubin},
  title =        {Causal Inference in Statistics, Social, and Biomedical Sciences},
  publisher =    {Cambridge University Press},
  year =         2015,
  url =          {}
  author    = {Alex Krizhevsky and Ilya Sutskever and Geoffrey E. Hinton},
  title     = {ImageNet Classification with Deep Convolutional Neural Networks},
  booktitle = {Advances in Neural Information Processing Systems 25: 26th Annual
               Conference on Neural Information Processing Systems 2012. Proceedings
               of a meeting held December 3-6, 2012, Lake Tahoe, Nevada, United States.},
  pages     = {1106--1114},
  year      = {2012},
  url       = {},
  author =       {David K. Lewis},
  title =        {Counterfactuals},
  publisher =    {Harvard University Press},
  year =         1973,
  url =          {}
  author =       {David Lopez-Paz and Robert Nishihara and Soumith Chintala
                  and Bernhard Schölkopf and Léon Bottou},
  title =        {Discovering causal signals in images},
  OPTcrossref =  {},
  OPTkey =       {},
  OPTbooktitle = {Computer Vision and Pattern Recognition (CVPR)},
  OPTyear =      {2017},
  url = {}
  author    = {Ofer Matan and
               Christopher J. C. Burges and
               Yann LeCun and
               John S. Denker},
  title     = {Multi-Digit Recognition Using a Space Displacement Neural Network},
  booktitle = {Advances in Neural Information Processing Systems 4]},
  pages     = {488--495},
  year      = {1991},
  url       = {},
  author = {McCarthy, John and Minsky, Marvin and Rochester, Nat and Shannon, Claude E.},
  title =  {A Proposal for the Dartmouth Summer Research Project on Artificial Intelligence},
  year =   {1955},
  url =    {}
  author =    {Stephen Mumford and Rani Lill Anjum},
  title =     {Getting Causes from Powers},
  publisher = {OUP Oxford},
  year =      2011,
  url =       {},
  author =       {Judea Pearl},
  title =        {Causality},
  publisher =    {Cambridge University Press},
  year =         2009,
  address =      {New York},
  url =          {}
  author    = {Arthur L. Samuel},
  title     = {Some Studies in Machine Learning Using the Game of Checkers},
  journal   = {{IBM} Journal of Research and Development},
  volume    = {3},
  number    = {3},
  pages     = {210--229},
  year      = {1959},
  url       = {}
	author = {Silver, David and Huang, Aja and Maddison, Chris J. and Guez, Arthur
                  and Sifre, Laurent and van den Driessche, George and Schrittwieser, Julian
                  and Antonoglou, Ioannis and Panneershelvam, Veda and Lanctot, Marc 
                  and Dieleman, Sander and Grewe, Dominik and Nham, John 
                  and Kalchbrenner, Nal and Sutskever, Ilya and Lillicrap, Timothy 
                  and Leach, Madeleine and Kavukcuoglu, Koray and Graepel, Thore 
                  and Hassabis, Demis},
	journal = {Nature},
	pages = {484-489},
	title = {Mastering the game of Go with deep neural networks and tree search},
	url = {},
	volume = {529},
	year = {2016}
  author =       {Peter Spirtes and Clark Glymour and Richard Scheines},
  title =        {Causation, Prediction, and Search, 2nd edition},
  publisher =    {MIT Press},
  address =      {Cambridge, MA},
  year =         {2001},
  url =          {}
  author    = {Yaniv Taigman and
               Ming Yang and
               Marc'Aurelio Ranzato and
               Lior Wolf},
  title     = {DeepFace: Closing the Gap to Human-Level Performance in Face Verification},
  booktitle = {Computer Vision and Pattern Recognition (CVPR)},
  pages     = {1701--1708},
  year      = {2014},
  url       = {},
  title =    {Temporal Difference Learning and TD-Gammon},
  author =   {Gerald Tesauro},
  journal =  {Communications of the ACM},
  month =    {March},
  year =     1995,
  volume =   38,
  number =   3,
  url =      {},
 author =    {Alan M. Turing},
 year =      1950,
 title =     {Computing Machinery and Intelligence},
 journal =   {Mind},
 volume =    49,
 pages =     {433-460},
 url =       {}
  author =    {Terry Winograd},
  title =     {Procedures as a representation of data in a computer 
               program for understanding natural language},
  publisher = {PhD thesis, Massachusets Institute of Technology},
  month =     {January},
  year =      {1971},
  url =       {}
2018/08/14 14:16 · leonb

Three views on causation

Although causation is a crucial component of the human cognitive experience, giving a precise and complete definition of causation has proven surprisingly challenging. The purpose of this page is to outline three very different viewpoints on causation that I believe relevant for Artificial Intelligence and inadequately addressed by Machine Learning techniques.

→

2018/08/14 13:54 · leonb

AI for the open world

We propose that a 2 month, 10 man study of artificial intelligence be carried out during the summer of 1956 at Dartmouth College in Hanover, New Hampshire. The study is to proceed on the basis of the conjecture that every aspect of learning or any other feature of intelligence can in principle be so precisely described that a machine can be made to simulate it. An attempt will be made to find how to make machines use language, form abstractions and concepts, solve kinds of problems now reserved for humans, and improve themselves. We think that a significant advance can be made in one or more of these problems if a carefully selected group of scientists work on it together for a summer. McCarthy, Minsky, Rochester, and Shannon, 1955 [1]

It is well known that things did not go that easily.

→

2018/05/24 11:41 · leonb
feuilleton/start.1527367038.txt.gz · Last modified: 2018/05/26 16:37 by leonb

Page Tools