Accession Number:

AD1096472

Title:

Sticky Reasoning within Learning Representations

Descriptive Note:

Technical Report,15 Sep 2015,14 Sep 2018

Corporate Author:

New York University New York United States

Personal Author(s):

• LeCun,Yann

Report Date:

2019-09-18

Pagination or Media Count:

8.0

Abstract:

We first proposed an architecture and learning procedure that automatically learns representations of images in which the content is separated from the pose. The method is completely unsupervised, not requiring that the pose or the identity of the object in the image be provided Mathieu NIPS 2016.While this work used generative adversarial networks GAN, we found the concept wanting and proposed a new formulation of GAN scalled Energy-Based GAN. Our method was the first to allow the generation of realistic images at 128x128 resolution. Generative models, such as GANs are a key component of unsupervised procedures that can generate complex patterns from latent variables drawn from a simple distribution Zhao ICLR 2017 over 550 citations to date.

Descriptors:

• deep learning
• reasoning
• information systems
• machine learning
• neural networks
• model predictive control
• predictive modeling
• generative models
• computer languages
• coders

Subject Categories:

• Cybernetics

Distribution Statement:

APPROVED FOR PUBLIC RELEASE