[ABE-L] Webinar High Dimensional Data Analysis

[Ronaldo Dias]

Relembrando: Webinar Prof. Carlos Zanini, DME-UFRJ.

Prezados(as)
Gostaria de convidá-los(as) a assistir mais um seminário em Análise de
Dados em Alta Dimensão. Ocorrerá às 13hs, 25/11/2020. Os links para este
seminário e a gravação do anterior (google meet e youtube) estão abaixo.
Desta vez teremos como palestrante, Prof. Carlos Zanini, DME-UFRJ.
abs.

*Webinar:* 25/11/2020
https://meet.google.com/bzx-pbva-imx

Title: Radial Neural Networks
Prof. Carlos Zanini, DME-UFRJ.

Abstract: 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.

*Webinar: *18/11/2020
https://youtu.be/uYdAaRi2DRc



-- 
Ronaldo Dias, Ph.D.
Professor
Dept. of Statistics-IMECC, UNICAMP
www.ime.unicamp.br/~dias
-------------- Próxima Parte ----------
Um anexo em HTML foi limpo...
URL: <http://lists.ime.usp.br/pipermail/abe/attachments/20201124/ef4426c3/attachment-0001.htm>