Flexible solutions (up to 16 GPU per node) for every budget: GTX1080 / GTX1080Ti / Tesla P100 / Tesla K80 / Tesla M60 / DGX-1 …

Take your TensorFlow use to the next level - learn how to build high-performance input pipelines using TensorFlow queuing operations and threading.

Learn how to use the exciting Microsoft CNTK deep learning framework. This framework is a real competitor to the currently dominant TensorFlow

This post describes how temporally-sensitive saliency maps can be obtained for deep networks designed for video recognition.
It is evident from the previous works [2, 3, 4] that saliency maps helps visualize why a model produced a given prediction and can uncover
artifacts in the data and point towards a better architecture.

Using CUDAnative.jl, you can access the power of GPU parallelization while still writing high-level Julia code. It’s not unreasonable to get speedups of 20x or more through GPU parallelization.

This article is an end-to-end data visualization exercise, using only ggplot2(). It has been helpful for me to see such pieces online on the endless possibilities of ggplot2(), so I wanted to give back to the community by doing one of my own.

In this post, I will detail how to do transfer learning (using a pre-trained network) to further improve the classification accuracy.

We are looking for skilled Machine Learning Developer. If you have at least three years of experience in C/C++ development and experience in machine learning feel free to apply. 

This repo contains an incremental sequence of notebooks designed to teach deep learning, MXNet, and the gluon interface. Our goal is to leverage the strengths of Jupyter notebooks to present prose, graphics, equations, and code together in one place.

Computer Vision News is written for you, it is 100% free and it is published by RSIP Vision with dedication and passion. It is probably for this reason that the major Conferences in our field, CVPR, ECCV, MICCAI and CARS, decided to partner with us and entrusted us with the task of publishing their Daily magazines during the event (find them below).

The Deep Learning textbook is a resource intended to help students and practitioners enter the field of machine learning in general and deep learning in particular. The online version of the book is now complete and will remain available online for free.