Manage Deep Learning Networks with Caffe* Optimized for Intel® Architecture

How to optimize Caffe* for Intel® Architecture, train deep network models, and deploy networks.
Authored by Andres Rodriguez (Intel) Last updated on 03/11/2019 - 13:17
Blog post

Mode collapse in GANs

Hello everyone! 

Authored by Last updated on 12/12/2018 - 18:00
Blog post

Track Reconstruction with Deep Learning at the CERN CMS Experiment

This blog post is part of a series that describes my summer school project at CERN openlab.

Authored by Last updated on 03/21/2019 - 12:00

Brain Tumor Segmentation using Fully Convolutional Tiramisu Deep Learning Architecture

The aim of the work was to implement, train and evaluate the quality of automated brain tumor multi-label segmentation technique for Magnetic Resonance Imaging based on Tiramisu deep learning architecture.
Authored by Kocot, Szymon Last updated on 03/26/2019 - 16:20
Offsite Link

A Progressive Batching L-BFGS Method for Machine Learning

See how an improvement to the L-BFGS algorithm takes advantage of progressive batching, line search, and quasi-Newton updating.

Authored by admin Last updated on 12/31/2018 - 14:00
Offsite Link

An Optimized Architecture for Unpaired Image-to-Image Translation

This paper introduces a new neural network architecture and shows how improvements to a Cycle-GAN significantly reduces training time for translating images across domains.

Authored by admin Last updated on 08/02/2018 - 10:43
Offsite Link

Boost Adversarial Attacks with Momentum

Learn more about an award-wining method that uses noise unnoticeable to humans to confuse neural networks into making enormous mistakes.

Authored by admin Last updated on 08/02/2018 - 10:41
Offsite Link

Break Natural Language Inference (NLI) Systems with Simple Lexical Interfaces

A new test shows that some of the best state-of-the-art natural language models fail by changing even just a few words.

Authored by admin Last updated on 08/02/2018 - 10:40
Offsite Link

DSOD: Deeply Supervised Object Detectors

This research paper introduces DSOD, a framework that outperforms modern variations of regional proposal and classification networks.

Authored by admin Last updated on 08/02/2018 - 10:41
Offsite Link

Explicit Loss-Error-Aware Quantization for Low-Bit Deep Neural Networks

This research shows how training low-bit deep neural networks has a much smaller memory footprint than full-precision models but with a small cost to accuracy.

Authored by admin Last updated on 08/02/2018 - 10:42