Schedule

Sessions and suggested reading (subject to change)

February 8th: Introduction: Mind as Machine
Boden, M. (2007): Mind as Machine, ch. 4, 16

Slides. Joscha Bach: Cognitive AI Orientation.ppt

Tuesday (shift due to President’s Day) February 16th: On the relationship between symbolic and connectionist AI
Carey, S., Gleitman, L., Marcus, G. F., Newport, E. L., Spelke, E. S. (2003): The Algebraic Mind, ch. 4

Slides. Ben Berman: Marcus Presentation.pptx, Adam Marblestone: SymbolicConnectionist_Marblestone, Henry Lieberman: Symbolic vs. Subsymbolic.pptx

February 22nd: Theories of Representation, Perception and Symbol Grounding
Sowa, J. R. (1987, 2015). Semantic Networks. http://www.jfsowa.com/pubs/semnet.pdf

Harnad, S. (1990) The Symbol Grounding Problem. Physica D 42: 335-346. http://users.ecs.soton.ac.uk/harnad/Papers/Harnad/harnad90.sgproblem.html
Barsalou, L. (1999). Perceptual Symbol Systems. Behavioral and Brain Sciences 22, 577–660. http://www.cogsci.ucsd.edu/~coulson/203/barsalou.pdf
Baum, E. B. (2003). What is thought? MIT Press

Slides. Kenny Friedman: FutureAIPresentation

February 29th: Learning
Ullman, S., Harari, D., & Dorfman, N. (2012). From simple innate biases to complex visual concepts. Proceedings of the National Academy of Sciences of the United States of America, 109(44), 18215–20. http://doi.org/10.1073/pnas.1207690109
O’Reilly, R. C., Wyatte, D., & Rohrlich, J. (2014). Learning Through Time in the Thalamocortical Loops, 37. Neurons and Cognition. http://arxiv.org/abs/1407.3432

Shimon Ullman, Liay Assif, Ethan Fetaya, Daniel Harari. (2016). Atoms of recognition in human and computer vision. http://www.pnas.org/content/early/2016/02/09/1513198113
Slides. Colin McDonnell: Learning , Adam Marblestone: Feb29th2016_Marblestone

Reading guide (questions to think about while/after reading):
“How might human learning differ from back-propagation-based training of neural nets?”
“What kinds of heuristics can we rely on, to bootstrap learning about the human world?”
“How can we interrogate those differences scientifically?”

March 7th: The MicroPsi architecture
Bach, J. (2009). Principles of Synthetic Intelligence http://micropsi.com/publications/assets/Draft-MicroPsi-JBach-07-03-30.pdf
Slides. Joscha Bach: MicroPsi FutureAI Spring 2016

March 14th: Social cognition and theory of mind
Saxe, R. (in press). The Neural Basis of Consciousness. http://saxelab.mit.edu/resources/papers/in_press/Saxe,%20R.%20(in%20press).%20Theory%20of%20mind%20-%20neural%20basis%20(Encyclopedia%20of%20Consciousness).pdf
Zawidzki, T. W. (2013): Mindshaping. A New Framework for Understanding Human Social Cognition. MIT Press http://cognet.mit.edu/book/mindshaping
Slides. Manushaqe Muco: Social Cognition and Theory of Mind , Joscha Bach: Social Cognition FutureAI March 14.ppt

March 28th: Cortical organization
Franzius, M., Sprekeler, H., & Wiskott, L. (2007). Slowness and sparseness lead to place, head-direction, and spatial-view cells. PLoS Computational Biology, 3(8), e166. http://doi.org/10.1371/journal.pcbi.0030166
Dileep George, Jeff Hawkins. (2009) Towards a Mathematical Theory of Cortical Micro-Circuits. http://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1000532
Gary F. Marcus, Adam H. Marblestone, Thomas L. Dean. (2014). Frequently Asked Questions for: The Atoms of Neural Computation. http://arxiv.org/abs/1410.8826
Hopfield, J. J. (2009). Neurodynamics of mental exploration. Proceedings of the National Academy of Sciences, 107(4), 1648–1653. http://doi.org/10.1073/pnas.0913991107
Slides. Adam Marblestone: cortical organization marblestone, Keeley Erhardt & Daniel Fitzgerald: MAS.S63 — Cortical Organization

April 4th: Computational models of cortical function
Hayworth, K. J. (2012). Dynamically partitionable autoassociative networks as a solution to the neural binding problem. Frontiers in Computational Neuroscience, 6, 73. http://doi.org/10.3389/fncom.2012.00073
Kurach, K., Andrychowicz, M., & Sutskever, I. (2015). Neural Random-Access Machines, 13. Learning; Neural and Evolutionary Computing. http://arxiv.org/abs/1511.06392?
Kriete, T., Noelle, D. C., Cohen, J. D., & O’Reilly, R. C. (2013). Indirection and symbol-like processing in the prefrontal cortex and basal ganglia. Proceedings of the National Academy of Sciences of the United States of America, 110(41), 16390–5. http://doi.org/10.1073/pnas.1303547110

Slides. Eric Chu & Archana Ram: Computational Models of Cortical Function

April 11th: Modeling imagination and creativity in computational models
Schank, R. (1993): Making Machines Creative http://psych.utoronto.ca/users/reingold/courses/ai/cache/creativity\_article,\_v2.html
McCormack, J. and d’Inverno, M. (eds.) (2012). “Computers and Creativity”. Springer, Berlin.
http://www.springer.com/us/book/9783642317262
Veale, T., Feyaerts, K. and Forceville, C. (2013) “Creativity and the Agile Mind: A Multidisciplinary study of a Multifaceted phenomenon”. Mouton de Gruyter 
http://prosecco-network.eu

Slides. Kane Hadley: CreativityFutureAI

April 25nd:  The Spaun cognitive architecture
Eliasmith, C. (2013). How to build a brain: A neural architecture for biological cognition Oxford University Press, 2013, Chris Eliasmith
Slides. 
Adam Marblestone: SPAUN ,
Bret Fontecchio: Generative Memory

May 2nd: The Leabra architecture
O’Reilly, R.C. et al (2014). Computational Cognitive Neuroscience https://grey.colorado.edu/CompCogNeuro/index.php/CCNBook/Main
O’Reilly, R. C., Hazy, T. E., Mollick, J., Mackie, P., & Herd, S. (2014). Goal-Driven Cognition in the Brain: A Computational Framework. http://arxiv.org/abs/1404.7591
O’Reilly, R.C. (2006). Biologically Based Computational Models of High-Level Cognition. Science, 314, 91-94
 https://grey.colorado.edu/mediawiki/sites/CompCogNeuro/images/a/a5/OReilly06.pdf
O’Reilly, R.C., Bhattacharyya, R., Howard, M.D. & Ketz, N. (2014). Complementary Learning Systems. Cognitive Science, 38,1229-1248. https://grey.colorado.edu/mediawiki/sites/CompCogNeuro/images/8/83/OReillyBhattacharyyaHowardEtAl14.pdf

Slides.
Michael Chang:Draft 9 Clean.pptx ,
Daniel Goodwin: LEABRA-Presentation-DRG

May 6th: The Design Space of Cognitive Architectures

May 9th: Final Student Presentations
Joscha Bach:
Cognitive AI Summary

Kane Hadley: Chinese Character Learning Assistant

Daniel Goodwin: Exploring Impact of Diversity in Multilayer, Multitask Neural Networks

Ben Berman: Realtime Deep Dream, Reenacting hallucinations in VR

Colin McDonnell: DefinitionLearning

Archana Ram: Visual Abstraction as a Means of Image Category Generalization and Recognition Under Partial Occlusion

Kenny Friedman: Escaping the Local Minimum

Michael Chang: Learning Predictive Models of Physics

Keeley Erhardt: An attempt at understanding the differences between the features used by deep convolutional neural nets and those used by humans for image identification

Eric Chu: GRID-LSTM.pptx