Past Events

Aligning neural network representations with brain activity measurements is a promising approach for studying the brain. However, it is not always clear what the ability to predict brain activity from neural network representations entails. In this talk, I will describe a line of work that utilizes computational controls (control procedures used after data collection) and other procedures to understand how the brain constructs complex meaning. I will describe experiments aimed at studying the representation of the composed meaning of words during language processing, and the representation of high-level visual semantics during visual scene understanding. These experiments shed new light on meaning representation in language and vision.

More than two decades after her death, Eleanor Gibson still may be the best experimental psychologist ever to work in the developmental cognitive sciences, yet her work appears to have been forgotten, or never learned, by many students and investigators today. Here, drawing on three of Gibson’s autobiographies, together with her published research and a few personal recollections, Spelke aims to paint a portrait of her life and science.

Quantifying and Understanding Memorization in Deep Neural Networks Abstract: Deep learning algorithms are well-known to have a propensity for fitting the training data very well and memorize idiosyncratic properties in the training examples. From a scientific perspective, understanding memorization in deep neural networks shed light on how those models generalize. From a practical perspective, understanding memorization is crucial to address privacy and security issues related to deploying models in real world applications.

Join the MIT Quest for Intelligence and the Artificial Intelligence @ MIT Student Group for a Panel Discussion! This event will focus on MIT Quest for Intelligence Research Missions and Engineering Projects. Speakers include: Ila Fiete, Associate Investigator, McGovern Institute, Katherine Fairchild, Engineering Team Lead, MIT Quest for Intelligence, and Martin Schrimpf, Research Scientist, MIT Quest for Intelligence.

Leyla Isik is the Clare Boothe Luce Assistant Professor in the Department of Cognitive Science at Johns Hopkins University. Her research aims to answer the question of how humans extract complex information using a combination of human neuroimaging, intracranial recordings, machine learning, and behavioral techniques. Before joining Johns Hopkins, Isik was a postdoctoral researcher at MIT and Harvard in the Center for Brains, Minds, and Machines working with Nancy Kanwisher and Gabriel Kreiman. Isik completed her PhD at MIT where she was advised by Tomaso Poggio.

Recordings are now posted from the talks in which researchers from MIT's Quest for Intelligence and its science driver — the Center for Brains, Minds, and Machines — shared the latest progress on understanding natural intelligence and how we aim to use that scientific progress to drive the future of AI and other impact areas. We were happy to welcome supporters, industry collaborators, and members of the MIT community to a day-long series of presentations and conversations about our vision, our most recent progress, and the future of research on the Science and Engineering of Intelligence.

George Konidaris is an Associate Professor of Computer Science and director of the Intelligent Robot Lab at Brown, which forms part of bigAI (Brown Integrative, General AI). He is also the Chief Roboticist of Realtime Robotics, a startup based on his research on robot motion planning. Konidaris focuses on understanding how to design agents that learn abstraction hierarchies that enable fast, goal-oriented planning. He develops and applies techniques from machine learning, reinforcement learning, optimal control and planning to construct well-grounded hierarchies that result in fast planning for common cases, and are robust to uncertainty at every level of control.

Sizhe Yuen is a final year PhD Student at the University of Southampton. His work focuses on the development of Evolutionary Algorithms using modern biological concepts from the Extended Evolutionary Synthesis. This talk will focus on the concept of epigenetic inheritance. Using a contemporary biological framework based on the Extended Evolutionary Synthesis, epigenetic inheritance is shown as a missing gap despite being a key building block in modern interpretations of how evolution occurs.