Featured news

March 8, 2023
MIT researchers uncover the structural properties and dynamics of deep classifiers, offering novel explanations for optimization, generalization, and approximation in deep networks. A new study from...

Seminars + events

March 28, 2023 - 4:00 pm
McGovern Reading Room (46-5165)
H. N. Mhaskar - Claremont Graduate University, Claremont.
The fundamental problem of machine learning is often formulated as the problem of function...

CBMM spotlight

Hector Penagos: Memories
Hector Penagos: Memories
Associated Research Thrust(s):

Highlighted publications

Featured video

Embedded thumbnail for 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...

Facebook Feed