- Visão geral
Deep neural networks are capable of amazing levels of representation power resulting in state-of-the-art accuracy in areas such as computer vision, speech recognition, natural language processing, and various data analytic domains. Intel is optimizing popular frameworks such as neon, Caffe*, TensorFlow*, Theano*, and others to significantly improve performance, reducing the overall time to train on a single node. In this webinar, we’ll review the Intel® Nervana™ Solution Stack from hardware, to low level libraries, to deep learning frameworks. We’ll also give an overview of neon.