CSCI 2951X: Reintegrating AI
(Spring 2018)
Overview

Schedule

Assignments

Grading

Resources

Overview


The primary goal of Artificial Intelligence has always been to build complete intelligent agents. However, the field has also always been fragmented into a collection of problem-specific areas of study. This seminar course will survey efforts made, over several decades, to produce "big picture" theories and architectures for reintegrating the various component technologies into complete, generally-capable, intelligent agents. The class will read and discuss two papers per week. Grading will be based on two written essays, and a substantial open-ended final project.

Instructor
George Konidaris
Office: CIT 447
Email: gdk at cs dot brown dot edu

[Back to top]

Schedule


The first class is on Thursday January 25th. The class meets on a Tuesday-Thursday schedule, from 1:00pm to 2:20pm in CIT 506.

Note that the schedule below is tentative, and may be revised as we go along.

DateAssigned Reading
January 25th Elephants Don't Play Chess, R.A. Brooks.
January 30th Class cancelled
February 1st Computer science as empirical inquiry: symbols and search.
A. Newell and H.A. Simon, CACM 1976.

Also read: Report on a general problem solver.
A. Newell, J.C. Shaw, and H.A. Simon. Technical report, Carnegie Institute of Technology, 1959.
February 6th CYC: Using Common Sense Knowledge to Overcome Brittleness and Knowledge Acquisition Bottlenecks. Lenat, Prakash, Shepherd. AI Magazine, 1985.
February 8th Extending the Soar Cognitive Architecture. Laird, GAIC 2008.
February 13th From Micro-Worlds to Knowledge Representation: AI at an Impasse. H.L. Dreyfus. In Mind Design II, Haugeland.
February 15th Shakey the Robot. N. Nilsson, ed. Technical Note 323, SRI International, April 1985.
February 20th Long weekend
February 22nd The Architecture of Mind: A Connectionist Approach, D.E. Rumelhart. In Mind Design II, chapter 8.
February 27th Connectionism and cognitive architecture: a critical analysis. J.A. Fodor and Z.W. Pylyshyn. In Mind Design II, chapter 12.
March 1st The Presence of a Symbol, A. Clark. In Mind Design II, chapter 14.
March 6th Quantifying Uncertainty, Chapter 13, Russell and Norvig.
March 8th On Chomsky and the Two Cultures of Statistical Learning, by Peter Norvig.
March 13th Snow day
March 15th How to Grow a Mind: Statistics, Structure, and Abstraction, Tenenbaum et al., Science, 2011.
March 20th No class
March 22nd Building Machines That Learn and Think Like People, Lake et al., 2017.
March 27th Spring break
March 29th Spring break
April 3rd Behaviour: perception, action and intelligence - the view from situated robotics, J.C.T. Hallam and C.A. Malcolm, Philosophical Transactions of the Royal Society A.
April 5th The Animat Path to AI, S.W. Wilson
Autonomous Mental Development by Robots and Animals, Weng et al.
April 10th Class discussion: embodiment, the modern AI method, and MDPs/POMDPs
April 12th No class
April 17th Hierarchically organized behavior and its neural foundations: A reinforcement learning perspective, Botvinick, Niv, and Barto, Cognition 2008.
April 19th Building Portable Options: Skill Transfer in Reinforcement Learning, Konidaris and Barto 2007, and Autonomous Skill Acquisition on a Mobile Manipulator, Konidaris et al., 2011.
April 24th From Skills to Symbols: Learning Symbolic Representations for Abstract High-Level Planning, Konidaris, Kaelbling, and Lozano-Perez, JAIR 2018.
April 26th Discussion


[Back to top]

Assignments


Assignment 1

GOFAI and connectionism are generally conceived of as direct competitors. However, their relationship is not quite that simple, since they are usually not applicable to the same sorts of problems. I'd like you to think about a specific type of problem - two player, zero-sum games, like chess and Go - where both approaches have been tried.

Your aim is to discuss the relative merits, successes, and failures of both GOFAI-like (which we'll take to include all search, knowledge-based, and explicit reasoning systems) and connectionist (which we'll take to include the direct prediction of best move or value using a neural net, of whatever type) systems. Where both types of methods have been combined in a single system, I'd like you to explain why, and to analyze what specific advantages the combination brings to the game. Your goal is to try and characterize what specific aspects of a two-player game GOFAI-style and connectionist approaches are best suited to, or to demonstrate that one approach has decisively "won".

I expect you to do substantial reading outside of the course materials, and to write a properly referenced report. You should cover as many individual games as you feel is necessary to cover the "space" of solutions. (I would be surprised if that is less than three.)

The assignment is due in class, in hardcopy, on March 15th. It may not be more than 8 pages in 11 point font (not including references). Please do NOT feel the need to necessarily use all of those pages; I am grading on insight, analysis, and coverage, NOT length.

Assignment 2

Your second assignment is to compare connectionist and Bayesian approaches to Natural Language Processing.

Here I'd like you to pick a component problem in NLP (e.g., parsing), and find and summarize the state-of-the-art approaches that use deep nets and that use explicit probabilistic models. I'd like you to discuss both the actual performance achieved, and the specific things that each approach makes possible in principle (e.g., semantically meaningful uncertainty) for the specific task you've chosen.

If the leading approaches are hybrid, that's OK, and even interesting! Explain what advantages are imported from each paradigm.

I expect a properly referenced hardcopy report handed in during class on April 17th. It may not be more than 5 pages in 11 point font (not including references). Please do NOT feel the need to necessarily use all of those pages; as usual I am grading on insight, and analysis, NOT length.

Final Project

Your major project will be a substantial creative and original piece of work, in one of the following two categories:

1) A computational research study, in which I expect you to design and implement theory and experiments studying some algorithm or model that is aligned with the course content. I expect it to have approximately the length, form, and content of a conference paper at a good AI conference (though it need not be publishable).

It does not necessarily have to be an original contribution, although that would be nice. If it is not, then I expect at least an original evaluation that is relevant to our topic (e.g., an existing algorithm is tried in a new domain that speaks to what we have discussed).

For example, one might design a new method that combines connectionism and probabilistic reasoning, or one might find such a method and then evaluate it in a domain designed to test one of the critiques of such methods that we have discussed.

The study will be graded on insight, completeness, and clarity. These studies can be completed singly or in pairs. I expect the submitted document to be more substantial for a pair than a similar single-author assignment that earns a similar grade.

2) A philosophical study, in which you propose and defend a proposition about the nature of intelligence. Here I am looking for the sort of argument and analysis that we have been seeing in the papers we've read so far. I expect a well-referenced, thoughtful piece that advanced a coherent and interesting argument and interrogates its implications.

For example, one might propose that (following today's discussion) a text corpus, no matter how large, does not contain the information necessary to discover the meaning of any sentence in natural language. A good essay will describe the proposition, argue for its truth, point to (or argue the irrelevance of) results in the CS literature, and perhaps consider and argue against possible objections.

Again this does not have to be a particularly new idea, but I'd like you you to argue it without relying on the arguments of others. You should cite computational research studies and foundational philosophical studies (e.g., Chomsky), but do not find another essay on a similar topic and use its arguments.

This type of study will be graded on the coherence of the idea, how well it is argued and analyzed, and on writing style. I expect it to be about as long as it needs to be to be complete; 10-20 pages as a ballpark.

The project accounts for 60% of your grade and is due at the end of the reading period (May 8th).

[Back to top]

Grading


Graded components will tentatively include two written homework assignments (20% each), and a substantial final project (60%).

[Back to top]

Resources


Our readings are in large part drawn from the following books, all of which are highly recommended for more in-depth reading into this topic:

  • Mind Design II, J. Haugeland, ed.
  • Computers & Thought, E.A. Feigenbaum and J. Feldman, eds.
  • Mindware, 2nd edition, Andy Clark, ed.
  • Being There, Andy Clark.
  • Cambrian Intelligence, R.A. Brooks.
Also worth reading, but much more about philosophy than CS, is:
  • Mind and Cognition, 2nd ed, W.G. Lycan, ed.

These books and readings will be of interest to students who want to understand the probabilistic foundation of AI more deeply:

  • Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference, by Judea Pearl.
  • Probability Theory: The Logic of Science, by E.T. Jaynes.
  • Probabilistic Logic, by Nils Nilsson. In Artificial Intelligence 28 (1986), 71-85.

[Back to top]