I am interested in a quantitative understanding of intelligence, both artificial and biological — and in the possible relationship between the two. I am mainly focused on neural network models, which are a canonical model for neural computation in the brain and are a central part of many modern artificial intelligence systems. 

Such artificial neural networks with deep architectures have dramatically improved the state-of-the-art in computer vision, speech recognition, natural language processing, and many other domains. 

Despite this impressive progress, artificial neural networks are still far behind the capabilities of biological neural networks in most areas: even the simplest fly is far more resourceful than our most advanced robots. This indicates we have much to improve! 

At the same time, if we wish to understand biological neural networks we must first be able to understand learning in the simplest non-linear artificial neural network – which still remains a mystery.

Therefore, my current research aims to uncover the fundamental mathematical principles governing both types of neural networks.

Research interests

My research covers all aspects of neural networks and deep learning. 

Click below for more information on a few open questions that interest me.

Neuroscience Methods

Selected Publications (according to area)

A more complete list of publications is available here, and in my google scholar page.

Choose area: