CLASS NOTES, SLIDES, READING MATERIAL, AND VIDEO
01/28/2025 Gabriel Kreiman Introduction to biological and artificial intelligence Are you ready to create suprahuman intelligence? Do you want to understand how intelligent computations emerge from the neuronal orchestra in the brain? How can we leverage millions of years of evolution to transform engineering systems that perform intelligent computations? How concerned should we be about the singularity? How is information represented and transformed in biological circuits? How can machines learn?
Reading Video (ID required, 2020) 02/04/2025 Richard Born Biological and artificial vision We understand the biological and computational underpinnings of our prodigious ability to see better than any other aspect of our brain's function. Beginning with the seminal work of Hubel and Wiesel, we have discovered many of the biological principles that operate in the primate visual system. And computational models inspired by these principles have enjoyed tremendous success in object recognition and other visual capacities, sometimes outperforming humans. Yet these models also fail in spectacular and occasionally embarrassing ways, leading to the overwhelming question: What are they missing? We will explore the history of biological and machine vision, learn how they productively interact in present-day vision science and discuss whether Mother Nature might still have a few tricks up her sleeve that could spur the development of improved machine vision systems in the future.
Slides Reading No video available 02/11/2025 Haim Sompolinsky The geometry of concept learning This class will present a theory of manifold separation in high-dimensional spaces, few-shot learning in visual representations, and aspects of visual reasoning.
Slides Reading No video available 02/18/2025 Thomas Serre State of the art in computer vision
Slides Reading No video available 02/25/2025 Bill Lotter Real-world impact of AI and computer vision
Slides Reading No video available 03/04/2025 Tomer Ullman
The development of intuitive physics and intuitive psychology
The central metaphor of cognitive science is that of the mind as a computer, but what sort of program is the mind running, and how does it construct this program? From an evolutionary perspective it would make sense to build in certain primitives and functions to allow the mind to get an 'early start' on understanding the world. These primitives would most helpfully be those that are generalizable across many scenarios, such as an understanding of people and things, agents and objects, psychology and physics. And indeed, we can see early evidence for an understanding of physics and psychology even in young children. I will briefly go over the evidence for an early understanding of physics and psychology, what representations could account for that understanding, and how they may develop over time into adult representations.
Slides Reading Video (ID required, 2020) 03/11/2025 Isaac Kohane AI for good
Slides Reading No video available 03/18/2025 Spring break Slides Reading No video available 03/25/2025 Cass Sunstein Does AI have the right to free speech?
Artificial intelligence (AI), including generative AI, is not human, but restrictions on the activity or use of AI, or on the dissemination of material by or from AI, might raise serious first amendment issues if those restrictions (1) apply to or affect human speakers and writers or (2) apply to or affect human viewers, listeners, and readers. Here as elsewhere, it is essential to distinguish among viewpoint-based restrictions, content-based but viewpoint-neutral restrictions, and content-neutral restrictions. Much of free speech law, as applied to AI, is in the nature of “the law of the horse”: established principles of multiple kinds applied to a novel context. But imaginable cases raise unanswered questions, including (1) whether AI as such has constitutional rights, (2) whether and which person or persons might be a named defendant if AI is acting in some sense autonomously, and (3) whether and in what sense AI has a right to be free from (for example) viewpoint-based restrictions, or whether it would be better, and correct, to say that human viewers, listeners, and readers have the relevant rights, even if no human being is speaking. Most broadly, it remains an unanswered question whether the First Amendment protects the rights of human viewers, listeners, and readers, seeking to see, hear, or read something from AI.
Slides Reading No video available 04/01/2025 Kanaka Rajan Unlocking Brain Dynamics: The Power of Recurrent Neural Networks in Neuroscience
Dr. Rajan will discuss the basic design elements, or "building blocks," of neural network models, highlighting the role of recurrent connections, linear and non-linear activity, and the types of time-varying activity ("dynamics") produced by RNNs, including input-driven versus spontaneous dynamics. The main goal of this lecture is to explore both the tractability and computational power of RNN models, to appreciate why they have become a crucial part of the neuroscientific arsenal, and to understand the insights that can be gained by "training RNNs to do something" in a manner consistent with experimental data from the biological brain. We will also review how RNNs have been applied in neuroscience to leverage existing experimental data, infer mechanisms inaccessible from measurements alone, and make predictions that guide experimental design.
Slides Reading No video available 04/08/2025 Jan Drugowitsch
The Bayesian brain: ideal observer models for perceptual decisions
The aim of both biological and artificial intelligence is to find efficient solutions to hard problems. Ideal observer models use this parallel to formulate theories of how our nervous system achieves certain tasks based on how they have been approached by artificial intelligence research. A basic tenant of ideal observer models is that the world we inhabit is noisy and ambiguous. The ideal way to deal with the arising uncertainty is by Bayesian decision theory. I will introduce Bayesian decision theory and how it has been used to inquire about the cognitive and neural processes that underlie humans and animal behavior. Specific focus will be put on the study of perceptual decisions and the relation between the speed and accuracy of such decisions.
Slides Reading Video (ID required, 2020) 04/15/2025 Andrei Barbu Language in brains and machines
Slides Reading No video available 04/22/2025 Cengiz Pehlevan
Why is it that biological and artificial neural networks do not overfit?
Slides Reading No video available 04/29/2025 Gabriel Kreiman Ask-me-anything session and participative debate on the future of AI Slides Reading No video available 05/06/2025 Students Student presentations Sign up here 05/13/2025 Students Student presentations Sign up here
