Putting Deep Learning into Production
QR Code Link to This Post Training modern deepnets can take an inordinate amount of time even with the best GPU hardware available. Inception-3 on ImageNet 1000 using 8 NVIDIA Tesla K40s takes about 2 weeks (Google Research Blog).This conference (http://conf.startup.ml) will focus on some best practices for deploying deep learning models into production. Speakers will discuss topics like:Ways to speed up training time Using pre-trained models Transferring knowledge from a different task Reducing model size to improve prediction latency Fitting models onto devices Speakers include:Andres Rodriguez — Intel Nervana Illia Polosukhin — Google / Tensorflow Contributor Abhradeep Guha Thakurta — University of California Santa Cruz Chris Fregly — PipelineIO Alex Miller — YelpRegister by 12/31/2016 using code “Learning17” and save 30%http://conf.startup.ml
Link to Full Article: Putting Deep Learning into Production
Sharing
