Back

Speaker "Tsvi Achler" Details Back

 

Topic

Illuminated AI using brain-motivated neural networks

Abstract

Feedforward networks have been the basis of Artificial Neural Networks (AI) such as Deep, Convolution, Regression, Random Forest, and Recurrent Networks.  However the internal decision processes of feedforward networks are difficult to explain: they are known to be a "black-box". 

This is especially problematic in applications where consequences of an error can be severe such as" Medicine, Banking, or Self-Driving Cars.

We have developed a new type of neural network motivated by neuroscience.  This allows the network to be more updatable, and the internal decision process easier to understand.  We convert feedforward networks to our Illuminated form and explain their internal workings, helping developers, regulators, and customers better understand feedforward networks and reduce risk.  We will demonstrate some of these benefits.

Profile

Tsvi Achler has a unique background focusing on the neural mechanisms of recognition from a multidisciplinary perspective. He has done extensive work in theory and simulations, human cognitive experiments, animal neurophysiology experiments, and clinical training. He has an applied engineering background, has received bachelor degrees from UC Berkeley in Electrical Engineering, Computer Science and advanced

degrees from University of Illinois at Urbana-Champaign in Neuroscience (PhD), Medicine (MD) and worked as a postdoc in Computer Science, and at Los Alamos National Labs, and IBM Research. He now heads his own startup Optimizing Mind whose goal is to provide the

next generation of machine learning algorithms