Research groups
Websites
Andrew Saxe
Associate Professor
- Sir Henry Dale Fellow
Research Interests
I study principles of learning in the brain and mind. The interactions of billions of neurons ultimately give rise to our thoughts and actions. Remarkably, much of our behavior is learned starting in infancy and continuing throughout our lifespan. Understanding how learning at the level of behavior is linked to changes at the level of neurons and synapses is a key challenge for theory.
My lab aims to develop a mathematical toolkit suitable for analyzing and describing learning in complex multi-regional brain networks. Our current focus is on the theory of deep learning, a class of artificial neural network models that take inspiration from the brain.
Alongside this theoretical work, we develop close collaborations with experimentalists to test principles of learning in biological organisms.
Recent publications
-
If deep learning is the answer, what is the question?
Journal article
Saxe A. et al, (2021), Nat Rev Neurosci, 22, 55 - 67
-
Qualitatively characterizing neural network optimization problems
Conference paper
SAXE A., (2020)
-
A Critique of Pure Hierarchy: Uncovering Cross-Cutting Structure in a Natural Dataset
Journal article
SAXE A., (2020), Neurocomputational Models of Cognitive Development and Processing
-
Dynamics of stochastic gradient descent for two-layer neural networks in the teacher-student setup
Journal article
Goldt S. et al, (2020), ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019), 32
-
Energy-entropy competition and the effectiveness of stochastic gradient
descent in machine learning
Journal article
Zhang Y. et al, (2020), Molecular Physics: An International Journal at the Interface Between Chemistry and Physics