Título: Radial Neural Networks

Palestrante: Carlos Tadeu Pagani Zanini (DME - UFRJ)
Data: 24/02/2021
Horario: 15:30h
Local: Transmissão online

Confira AQUI o link para a transmissão.

Resumo: This work proposes a very simple extension of the usual fully connected hidden layers in deep neural networks for classification. The objective is to transform the latent space on the hidden layers to be more suitable for the linear separation that occurs in the sigmoid/softmax output layer. We call such architectures radial neural networks because they use projections of fully connected hidden layers onto the surface of a hypersphere. We provide a geometrical motivation for the proposed method and show that it helps achieve convergence faster than the analogous architectures that they are built upon. As a result, we can significantly reduce training time on neural networks for classification that use fully connected hidden layers. The method is illustrated as an application to image classification, although it can be used for other classification tasks.

A sala será aberta sempre 10 minutos antes do início de cada sessão.