Offsite Link

Accelerate Machine Learning & Deep Learning with Apache Spark*: Talk by Ziya Ma

Deep learning is a fast growing subset of machine learning.

Criado por administrar Última atualização em 11/03/2019 - 13:17
Offsite Link

The Creation of BigDL: An Interview with Ziya Ma

Ziya Ma, Vice President of Big Data at Intel, sits down with Dave Vellante & George Gilbert at Spark Summit East 2017 at the Hynes Convention Center in Bosto

Criado por administrar Última atualização em 11/03/2019 - 13:17
Offsite Link

Soundcloud* Podcast: Understanding Deep Learning for Apache Spark* with Jason Dai

In this episode of the Data Show, O'Reilly Radar spoke with Jason Dai, CTO of big data technologies at Intel, and co-chair of Strata + Hadoop World Beijing.

Criado por administrar Última atualização em 11/03/2019 - 13:17
Offsite Link

Bay Area DevTalk Meetup 2017: Coding with BigDL

Intel:

Tech -Talk-1: Distributed Deep Learning At Scale on Apache Spark* with BigDL Databricks:

Criado por administrar Última atualização em 11/03/2019 - 13:17
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.

Criado por administrar Última atualização em 31/12/2018 - 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.

Criado por administrar Última atualização em 02/08/2018 - 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.

Criado por administrar Última atualização em 02/08/2018 - 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.

Criado por administrar Última atualização em 02/08/2018 - 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.

Criado por administrar Última atualização em 02/08/2018 - 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.

Criado por administrar Última atualização em 02/08/2018 - 10:42