ARM Helium Armv8.1-M architecture, Machine Learning on ARM Cortex-M

Jem Davies, ARM VP, Fellow and GM, Machine Learning Group talks about ARM's new Helium Machine Learning architecture for the ARM Cortex-M based microcontrollers, as a follow on to ARM CMSIS-NN Neural Network Kernels which Boosted Efficiency in Microcontrollers by 5x last year, now ARM launches Helium ARMv8.1-M to improve machine learning performance, with up to 50x on machine learning workloads, about 5x improvement in performance for regular DSP based workloads, as open source software and the new ARMv8.1-M architecture to be integrated in Microcontroller designs to come in the future.

- early access to all hundreds of unpublished videos
- business cards to contact companies and people that I interview
- show your support, member icon next to your username when you comment and in live chat