It’s a dual-core, RISC-V chip running at 400MHz. There’s 6 MB of SRAM on the CPU, and there’s 2MB for convolutional neural network acceleration. There is, apparently, WiFi on some versions.
Co-fonder and CTO, Paul Masters, described a novel way to arrange the elements of a chip to do both machine learning "training" -- where the neural network is developed -- as well as "inference ...
Why it matters: The achievement changes how scientists can study brain connectivity, enabling unprecedented insights into neural networks that ... a sophisticated CMOS chip that introduces several ...
Intel is firing back at Nvidia's growing prominence in artificial intelligence with the launch of its Nervana Neural Network processors ... NNP-T1000 and NNP-I1000 chips for deep learning training ...
In always-on, at-sensor use cases, Akida can completely offload feed-forward networks without ... local to the chip, independent of the cloud, dramatically reducing latency while improving privacy and ...
The presentation ends with a demonstration of BrainChip’s Akida™ neural processor IP, enabling high performance and ultra-low power on-chip inference and learning and MosChip’s ASIC platform for smart ...