Wolfram Language introduces a high-performance neural network framework with both CPU and GPU training support. A full complement of vision-oriented layers is included, as well as encoders and decoders to make trained networks interoperate seamlessly with the rest of the language. Constructing and training networks often requires only a few lines of code, putting deep learning in the hands of even non-expert users.
Presented by
Farid Pasha joined Wolfram Research in 2011 as a member of the International Business Development group, where he works with customers in Southeast Asian countries and the South Africa and Pakistan regions. Prior to joining Wolfram Research, he worked for ten years in the oil and gas industry.
Farid provides Mathematica trainings and seminars at universities, community colleges, and high schools in his region. He is experienced in working with educators on how to integrate Mathematica into their courses.