XMOS and Plumerai partner collaborate on binarised neural networks
Plumerai’s Larq software library for training BNNs will be combined with the xcore.ai crossover processor from XMOS which provides native support for inference of BNNs. The combination of the technologies is expected to provide a BNN capability that’s 2 to 4x more efficient than existing edge AI solutions.
BNNs are expected to be the most efficient form of deep learning, by going all the way down to just a single bit. However, to make BNNs commercially viable requires specific attention in chip design for efficient inference and new software algorithms for training.
More information
Related news
XMOS 2-mic dev kit qualified by Amazon
Machine-learning processor startup born in Bristol
Infineon fuses Radar and MEMS microphone data through XMOS’ audio processor
Infineon backs XMOS to work where audio meets AI
If you enjoyed this article, you will like the following ones: don't miss them by subscribing to :