This is an attempt to change the way a Neural Network is executed and trained. Instead of accellerating parts of the NN execution, the whole NN problem is converted into a new assembly language that can do evaluation and back propagation of any NN. Multiple passages of convolution steps can be combined into a fully parallell pipeline.

http://www.gizmosdk.com/archives/CorTeX/execution_example.pdf

Pin It on Pinterest

Share This

Join Our Newsletter

Sign up to our mailing list to receive the latest news and updates about homeAI.info and the Informed.AI Network of AI related websites which includes Events.AI, Neurons.AI, Awards.AI, and Vocation.AI

You have Successfully Subscribed!