Skip to content (access key 's')
Logo of Technion
Logo of CS Department
Logo of CS4People

The Taub Faculty of Computer Science Events and Talks

Pixel Club: SimNets: A Generalization of Convolutional Networks
event speaker icon
Nadav Cohen (The Hebrew University of Jerusalem)
event date icon
Tuesday, 06.01.2015, 11:30
event location icon
Room 337-8 Taub Bld.
We present a deep layered architecture that generalizes classical convolutional neural networks (ConvNets). The architecture, called SimNets, is driven by two operators, one being a similarity function whose family contains the convolution operator used in ConvNets, and the other is a new soft max-min-mean operator called MEX that realizes classical operators like ReLU and max pooling, but has additional capabilities that make SimNets a powerful generalization of ConvNets. Three interesting properties emerge from the architecture: (i) the basic input to hidden layer to output machinery contains as special cases kernel machines with the Exponential and Generalized Gaussian kernels, the output units being "neurons in feature space" (ii) in its general form, the basic machinery has a higher abstraction level than kernel machines, and (iii) initializing networks using unsupervised learning is natural. Experiments demonstrate the capability of achieving state of the art accuracy with networks that are an order of magnitude smaller than comparable ConvNets.

Joint work with Amnon Shashua, implementation with Nitzan Guberman and Or Sharir.