|
Sensing, Imaging and Signal Processing 16 Team Lead: Luis El Srouji Advisor: Prof. Yoo
|
|
Mehmet Berkay leads a discussion on the potential biological basis for backpropagation and a justification for its uses in spiking neural networks.
|
|
In this talk, we offer an entirely “white box’’ interpretation of deep (convolution) networks from the perspective of data compression (and group invariance). In particular, we show…
|
|
Dr. Farhad Shokraneh goes over his recent work on an optical processor for neural networks, and describes the features which make this architecture more fault- and loss-tolerant than other similar…
|
|
Professor Randy O'Reilly presented on Predictive Error-Driven Learning in the Brain; this method approximates backpropagation in rate-approximated neural networks and will be soon extended to…
|