Probabilistic Siamese Networks for Learning Representations

Probabilistic Siamese Networks for Learning Representations

Show other versions (1)

We explore the training of deep neural networks to produce vector representations using weakly labelled information in the form of binary similarity labels for pairs of training images. Previous methods such as siamese networks, IMAX and others, have used fixed cost functions such as $L_1$, $L_2$-no...

Full description

Bibliographic Details
Main Author: Liu, Chen
Other Authors: Frey, Brendan J.
Language:en_ca
Published: 2013
Subjects:
Machine Learning
Neural Networks
0544
Online Access:http://hdl.handle.net/1807/43097

Internet

http://hdl.handle.net/1807/43097

Similar Items