June 9, 2020 - 2:00 pm
Hossein Mobahi, Google Research
Improving Generalization Performance by Self-Training and Self-Distillation
In supervised learning we often seek a model which minimizes (to epsilon optimality) a loss function over a training set, possibly subject to some (implicit or explicit) regularization. Suppose you train...
Photo of Noga Zaslavsky
May 19, 2020 - 2:00 pm
Noga Zaslavsky
Title: Efficient compression and linguistic meaning in humans and machines
Abstract: In this talk, I will argue that efficient compression may provide a fundamental principle underlying the human capacity to communicate and reason about meaning, and may help to inform machines with similar...
Photo of Max Tegmark
May 5, 2020 - 4:00 pm
Max Tegmark, MIT
Title: AI for physics & physics for AI
Abstract: After briefly reviewing how machine learning is becoming ever-more widely used in physics, I explore how ideas and methods from physics can help improve machine learning, focusing on automated discovery of mathematical formulas from data. I...
Photo of Youssef Mroueh
April 28, 2020 - 2:00 pm
Youssef Mroueh, MIT-IBM Watson AI lab
Title of the talk: Sobolev Independence Criterion: Non-Linear Feature Selection with False Discovery Control.    
Abstract: In this talk I will show how learning gradients help us designing new non-linear algorithms for feature selection, black box sampling and also, in understanding neural...
April 14, 2020 - 2:00 pm
Tomaso Poggio (CBMM), Mikhail Belkin (Ohio State University), Constantinos Daskalakis (CSAIL), Gil Strang (...
Developing theoretical foundations for learning is a key step towards understanding intelligence. Supervised learning is a paradigm in which natural or artificial networks learn a functional relationship from a set of n input-output training examples. A main challenge for the theory is...
April 7, 2020 - 2:00 pm
Sam Gershman, Harvard/CBMM
Abstract: In this talk, I will present a theory of reinforcement learning that falls in between "model-based" and "model-free" approaches. The key idea is to represent a "predictive map" of the environment, which can then be used to efficiently compute values. I show how such a map explains many...
March 10, 2020 - 4:00 pm
MIT 46-5165
There will be no meeting on Tues., March 10, 2020
February 18, 2020 - 4:00 pm
MIT 46-5165
Andrei Barbu, Katz Lab
February 11, 2020 - 4:00 pm
MIT 46-5165
Tiago Marques
Abstract: Object recognition relies on the hierarchical processing of visual information along the primate ventral stream. Artificial neural networks (ANNs) recently achieved unprecedented accuracy in predicting neuronal responses in different cortical areas and primate behavior. In this talk, I...
Jacob Andreas
December 17, 2019 - 4:00 pm
MIT 46-5165
Jacob Andreas
Title: Language as a scaffold for learning
Research on constructing and evaluating machine learning models is driven
almost exclusively by examples. We specify the behavior of sentiment classifiers
with labeled documents, guide learning of robot policies by assigning scores to...
November 26, 2019 - 4:00 pm
MIT 46-5165
Nick Watters (Tenenbaum Lab)
Title:  Unsupervised Learning and Structured Representations in Neural Networks
Sample efficiency, transfer, and flexibility are hallmarks of biological intelligence and long-standing challenges for artificial learning systems. Core to these capacities is the reuse of structured...
November 19, 2019 - 4:00 pm
MIT 46-5165
Shimon Ullman
Topic: Combining vision and cognition by BU-TD visual routines ​
November 12, 2019 - 4:00 pm
MIT 46-5165
Katharina Dobs(Kanwisher Lab)
Using task-optimized neural networks to understand why brains have specialized processing for faces
Previous research has identified multiple functionally specialized regions of the human visual cortex and has started to characterize the precise function of these regions. But why do brains have...
October 8, 2019 - 4:00 pm
MIT 46-5165
Mengmi Zhang and Jie Zheng, Kreiman Lab
October 1, 2019 - 4:00 pm
MIT 46-5165
Andrzej Banburski, Poggio Lab , Title: Biologically-inspired defenses against adversarial attacks   Abstract: Adversarial examples are a...