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 ...

This convolutional neural network analyzes the desired chip properties then designs backward. Much of AI news is hype, but this is open access, peer reviewed research in a reputable journal.

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.

Technical Innovation: The research team developed a sophisticated CMOS chip that introduces several ... it provides an unprecedented window into neural network operation. Looking ahead, the ...

The new silicon chip, which captures 70,000 plausible synaptic connections, enables scientists to read neural network activity at a significantly higher sensitivity and construct a more accurate ...

Thirty years ago, neural nets on a chip were created by a few companies around Boston, until someone realized these neural nets could be simulated on a desktop PC much more efficiently.

For now, the company is selling the device as a way to train "biological AI," meaning neural networks that rely on actual neurons. In other words, the neurons can be "taught" via the silicon chip.

Intel is firing back at Nvidia's growing prominence in artificial intelligence with the launch of its Nervana Neural Network processors ... processors when the chip comes out in the first half ...

During the automotive portion of CEO Jensen Huang’s speech, he referred to AlexNet, a neural network architecture that gained ...

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 ...