Skip to content

Commit 315909f

Browse files
committed
144
1 parent 1f0e63a commit 315909f

8 files changed

+91
-84
lines changed

Artificial Intelligence.md

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -538,12 +538,12 @@
538538
#### ["Building Machines That Learn and Think Like People"](http://arxiv.org/abs/1604.00289) Lake, Ullman, Tenenbaum, Gershman
539539
> "Recent progress in artificial intelligence has renewed interest in building systems that learn and think like people. Many advances have come from using deep neural networks trained end-to-end in tasks such as object recognition, video games, and board games, achieving performance that equals or even beats humans in some respects. Despite their biological inspiration and performance achievements, these systems differ from human intelligence in crucial ways. We review progress in cognitive science suggesting that truly human-like learning and thinking machines will have to reach beyond current engineering trends in both what they learn, and how they learn it. Specifically, we argue that these machines should (a) build causal models of the world that support explanation and understanding, rather than merely solving pattern recognition problems; (b) ground learning in intuitive theories of physics and psychology, to support and enrich the knowledge that is learned; and (c) harness compositionality and learning-to-learn to rapidly acquire and generalize knowledge to new tasks and situations. We suggest concrete challenges and promising routes towards these goals that can combine the strengths of recent neural network advances with more structured cognitive models."
540540

541+
- `video` <https://youtube.com/watch?v=9PSQduoSNo0> (Lake)
541542
- `video` <https://youtube.com/watch?v=7ROelYvo8f0> (Tenenbaum)
542543
- `video` <https://youtube.com/watch?v=O0MF-r9PsvE> (Gershman)
543-
- `video` <https://www.technologyreview.com/video/610657/ingredients-of-intelligence/> (Lake)
544544
- `notes` <http://pemami4911.github.io/paper-summaries/2016/05/13/learning-to-think.html>
545545
- `paper` <https://cims.nyu.edu/~brenden/LakeEtAl2017BBS.pdf> ("Behavioral and Brain Sciences")
546-
- <https://github.com/brylevkirill/notes/blob/master/Knowledge%20Representation%20and%20Reasoning.md#reasoning---commonsense-reasoning>
546+
- [**bayesian reasoning**](https://github.com/brylevkirill/notes/blob/master/Knowledge%20Representation%20and%20Reasoning.md#reasoning---bayesian-reasoning)
547547

548548

549549
#### ["Thinking Required"](http://arxiv.org/abs/1512.01926) Rocki

Bayesian Inference and Learning.md

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -639,6 +639,7 @@
639639
- `video` <http://youtube.com/watch?v=Sz6VoPly45o> (Lake)
640640
- `video` <http://youtube.com/watch?v=kzl8Bn4VtR8> (Lake)
641641
- `video` <http://techtalks.tv/talks/one-shot-learning-of-simple-fractal-concepts/63049/> (Lake)
642+
- `video` <http://youtube.com/watch?v=p1VpvOFJg6A> (Lake)
642643
- `video` <http://youtu.be/quPN7Hpk014?t=21m5s> (Tenenbaum)
643644
- `notes` <https://casmls.github.io/general/2017/02/08/oneshot.html>
644645
- `code` <https://github.com/brendenlake/BPL>

Causal Inference.md

Lines changed: 19 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -9,7 +9,7 @@
99
---
1010
### overview
1111

12-
["The Seven Tools of Causal Inference with Reflections on Machine Learning"](https://dl.acm.org/citation.cfm?id=3241036) by Judea Pearl `paper`
12+
["The Seven Tools of Causal Inference with Reflections on Machine Learning"](https://dl.acm.org/citation.cfm?id=3241036) by Judea Pearl `paper` ([talk](https://youtube.com/watch?v=nWaM6XmQEmU) `video`)
1313
["Theoretical Impediments to Machine Learning"](http://web.cs.ucla.edu/~kaoru/theoretical-impediments.pdf) by Judea Pearl `paper`
1414

1515
["Causality for Machine Learning"](https://arxiv.org/abs/1911.10500) by Bernhard Scholkopf `paper`
@@ -61,6 +61,7 @@
6161

6262
["The Foundations of Causal Inference with Reflections on Machine Learning and Artificial Intelligence"](https://youtube.com/watch?v=nWaM6XmQEmU) by Judea Pearl `video`
6363
["The New Science of Cause and Effect"](https://youtube.com/watch?v=ZaPV1OSEpHw) by Judea Pearl `video`
64+
["The Mathematics of Causal Inference with Reflections on Machine Learning"](https://youtube.com/watch?v=bcRl7sXR1hE) by Judea Pearl `video`
6465
["The Mathematics of Causal Inference, with Reflections on Machine Learning and the Logic of Science"](https://youtube.com/watch?v=zHjdd--W6o4) by Judea Pearl `video`
6566

6667
["Causal Data Science: A General Framework for Data Fusion and Causal Inference"](https://youtube.com/watch?v=dUsokjG4DHc) by Elias Bareinboim `video`
@@ -174,6 +175,23 @@
174175

175176

176177
----
178+
#### ["The Seven Tools of Causal Inference with Reflections on Machine Learning"](https://dl.acm.org/citation.cfm?id=3241036) Pearl
179+
> "The dramatic success in machine learning has led to an explosion of artificial intelligence applications and increasing expectations for autonomous systems that exhibit human-level intelligence. These expectations have, however, met with fundamental obstacles that cut across many application areas. One such obstacle is adaptability, or robustness. Machine learning researchers have noted current systems lack the ability to recognize or react to new circumstances they have not been specifically programmed or trained for."
180+
181+
- `video` <https://youtube.com/watch?v=nWaM6XmQEmU> (Pearl)
182+
183+
184+
#### ["Causality for Machine Learning"](https://arxiv.org/abs/1911.10500) Scholkopf
185+
> "Graphical causal inference as pioneered by Judea Pearl arose from research on artificial intelligence, and for a long time had little connection to the field of machine learning. This article discusses where links have been and should be established, introducing key concepts along the way. It argues that the hard open problems of machine learning and AI are intrinsically related to causality, and explains how the field is beginning to understand them."
186+
187+
188+
#### ["Causal Inference and the Data-fusion Problem"](https://pnas.org/content/113/27/7345) Bareinboim, Pearl
189+
> "We review concepts, principles, and tools that unify current approaches to causal analysis and attend to new challenges presented by big data. In particular, we address the problem of data fusion - piecing together multiple datasets collected under heterogeneous conditions (i.e., different populations, regimes, and sampling methods) to obtain valid answers to queries of interest. The availability of multiple heterogeneous datasets presents new opportunities to big data analysts, because the knowledge that can be acquired from combined data would not be possible from any individual source alone. However, the biases that emerge in heterogeneous environments require new analytical tools. Some of these biases, including confounding, sampling selection, and cross-population biases, have been addressed in isolation, largely in restricted parametric models. We here present a general, nonparametric framework for handling these biases and, ultimately, a theoretical solution to the problem of data fusion in causal inference tasks."
190+
191+
- `video` <https://youtube.com/watch?v=_cNbWuErsoI> (Bareinboim)
192+
- `video` <https://youtube.com/watch?v=dUsokjG4DHc> (Bareinboim)
193+
194+
177195
#### ["On Causal and Anticausal Learning"](https://arxiv.org/abs/1206.6471) Schoelkopf et al.
178196
`ICML 2012`
179197
> "We consider the problem of function estimation in the case where an underlying causal model can be inferred. This has implications for popular scenarios such as covariate shift, concept drift, transfer learning and semi-supervised learning. We argue that causal knowledge may facilitate some approaches for a given problem, and rule out others. In particular, we formulate a hypothesis for when semi-supervised learning can help, and corroborate it with empirical results."

Deep Learning.md

Lines changed: 7 additions & 10 deletions
Original file line numberDiff line numberDiff line change
@@ -1,4 +1,4 @@
1-
Deep Learning is learning a composition of differentiable functions as a knowledge representation through gradient-based optimization method.
1+
Deep Learning is learning a composition of functions (differentiable or otherwise) as a knowledge representation (through gradient-based optimization methods or otherwise).
22

33

44
* [**overview**](#overview)
@@ -41,7 +41,9 @@
4141

4242
#### introduction
4343

44-
[overview](http://www.deeplearningbook.org/contents/intro.html) by Ian Goodfellow, Yoshua Bengio, Aaron Courville
44+
[overview](http://www.deeplearningbook.org/contents/intro.html) by Ian Goodfellow, Yoshua Bengio, Aaron Courville
45+
46+
["What's Deep Learning?"](https://twitter.com/fchollet/status/1210031900695449600) by Francois Chollet
4547

4648
["Deep Learning And Shallow Data"](https://blog.piekniewski.info/2019/04/07/deep-learning-and-shallow-data) by Filip Piekniewski
4749
["The Limitations of Deep Learning for Vision and How We Might Fix Them"](https://thegradient.pub/the-limitations-of-visual-deep-learning-and-how-we-might-fix-them) by Alan Yuille and Chenxi Liu
@@ -431,15 +433,10 @@
431433

432434
["Do we still need models or just more data and compute?"](https://staff.fnwi.uva.nl/m.welling/wp-content/uploads/Model-versus-Data-AI-1.pdf) by Max Welling
433435

434-
["Round-up of Strenghts and Weaknesses"](https://youtube.com/watch?v=7o9dT6puHHg) by Aravind Srinivas `video`
435-
436-
[overview](http://videolectures.net/deeplearning2017_goodfellow_generative_models/) by Ian Goodfellow `video`
437-
[overview](http://videolectures.net/deeplearning2017_courville_generative_models/) by Aaron Courville `video`
438-
[overview](https://youtube.com/watch?v=JrO5fSskISY) by Shakir Mohamed and Danilo Rezende `video`
439-
440-
["Building Machines that Imagine and Reason: Principles and Applications of Deep Generative Models"](http://videolectures.net/deeplearning2016_mohamed_generative_models/) by Shakir Mohamed `video`
436+
[overview](https://youtube.com/watch?v=oRJ1hJTRs-0) by Danilo Rezende `video`
441437

442-
["Differentiable Inference and Generative Models"](http://www.cs.toronto.edu/~duvenaud/courses/csc2541/index.html) course by David Duvenaud
438+
["Round-up of Strenghts and Weaknesses"](https://youtube.com/watch?v=7o9dT6puHHg) by Aravind Srinivas `video`
439+
["Building Machines that Imagine and Reason: Principles and Applications of Deep Generative Models"](http://videolectures.net/deeplearning2016_mohamed_generative_models/) by Shakir Mohamed `video`
443440

444441
----
445442

Knowledge Representation and Reasoning.md

Lines changed: 5 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -721,7 +721,7 @@
721721

722722
----
723723

724-
[**"Building Machines That Learn and Think Like People"**](https://github.com/brylevkirill/notes/blob/master/Artificial%20Intelligence.md#building-machines-that-learn-and-think-like-people-lake-ullman-tenenbaum-gershman) by Lake, Ullman, Tenenbaum, Gershman `paper` `overview`
724+
[**"Building Machines That Learn and Think Like People"**](https://github.com/brylevkirill/notes/blob/master/Artificial%20Intelligence.md#building-machines-that-learn-and-think-like-people-lake-ullman-tenenbaum-gershman) by Lake, Ullman, Tenenbaum, Gershman `paper` `summary`
725725
["Simulation as an Engine of Physical Scene Understanding"](http://www.pnas.org/content/110/45/18327.short) by Battaglia, Hamrick, Tenenbaum `paper`
726726
["Computational Rationality: A Converging Paradigm for Intelligence in Brains, Minds and Machines"](https://goo.gl/jWaJVf) by Gershman, Horvitz, Tenenbaum `paper`
727727
["Concepts in a Probabilistic Language of Thought"](https://web.stanford.edu/~ngoodman/papers/ConceptsChapter-final.pdf) by Goodman, Tenenbaum, Gerstenberg `paper`
@@ -738,9 +738,10 @@
738738
- ["Building Machines That See, Learn and Think Like People"](https://youtube.com/watch?v=7ROelYvo8f0) `video`
739739
- ["Building Machines That Learn and Think Like People"](https://facebook.com/icml.imls/videos/432412777273243?t=4362) `video`
740740
- ["The Cognitive Science Perspective: Reverse-engineering the Mind"](https://youtube.com/watch?v=Z3mFBEOH2y4) `video`
741-
- ["Engineering & Reverse-Engineering Human Common Sense"](https://youtube.com/watch?v=hfoeRiZU5YQ) `video`
742-
- ["Cognitive Foundations for Common-sense Knowledge Representation and Reasoning"](https://youtube.com/watch?v=oSAG57plHnI) `video`
741+
- ["Modeling Human Intelligence with Probabilistic Programs and Program Induction"](https://youtube.com/watch?v=c_hUBLsicSY) `video`
743742
- ["Building Machines That Learn Like Humans"](https://youtube.com/watch?v=quPN7Hpk014) `video`
743+
- ["Cognitive Foundations for Common-sense Knowledge Representation and Reasoning"](https://youtube.com/watch?v=oSAG57plHnI) `video`
744+
- ["Engineering & Reverse-Engineering Human Common Sense"](https://youtube.com/watch?v=hfoeRiZU5YQ) `video`
744745
- ["Towards More Human-like Machine Learning of Word Meanings"](http://techtalks.tv/talks/towards-more-human-like-machine-learning-of-word-meanings/54913/) `video`
745746
- ["How to Grow a Mind: Statistics, Structure, and Abstraction"](http://videolectures.net/aaai2012_tenenbaum_grow_mind/) `video`
746747
- ["Development of Intelligence: Bayesian Inference"](http://youtube.com/watch?v=icEdI0AIOlU) `video`
@@ -782,7 +783,7 @@
782783
["The Future of Deep Learning"](http://blog.keras.io/the-future-of-deep-learning.html) by Francois Chollet ([talk](https://youtu.be/MUF32XHqM34?t=11m43s) `video`)
783784

784785
["From Machine Learning to Machine Reasoning"](http://research.microsoft.com/pubs/192773/tr-2011-02-08.pdf) by Leon Bottou `paper`
785-
([talk](http://youtube.com/watch?v=tzp_BikdgyM) `video`)
786+
([talk](http://youtube.com/watch?v=tzp_BikdgyM) `video`, [talk](https://slideslive.com/38921894/retrospectives-a-venue-for-selfreflection-in-ml-research-1?t=524))
786787

787788
["Cognitive Architectures"](https://machinethoughts.wordpress.com/2016/06/20/cognitive-architectures/) by David McAllester
788789

0 commit comments

Comments
 (0)