This site may earn chapter commissions from the links on this page. Terms of use.

intel-nervana-neural-network-processor-2x1

Science-fiction authors and modernistic engineering mega-corporations concur on one thing–artificial intelligence is the hereafter. Everyone from Google to Facebook is designing artificial neural networks to tackle big problems like estimator vision and speech synthesis. Well-nigh of these projects are using existing computer hardware, just Intel has something big on the style. The chip maker has announced the first defended neural network processor, the Intel Nervana Neural Network Processor (NNP).

A neural network is designed to process information and solve problems in a way that's more than like a brain. They consist of layers of artificial neurons that process inputs and pass the data down the line to the adjacent neuron in the network. At the end, you take an output that'southward informed by all the transformations applied by the network, which is more efficient than creature force ciphering. These systems can learn over time by grooming with large batches of data. This is how Google perfected the AlphaGo network that managed to defeat the best human Get players in the world.

The Nervana NNP is designed from the footing up with this type of calculating in mind. This is what's known equally an application specific integrated circuit (ASIC), so it's not useful for general computing tasks. Notwithstanding, if you're trying to run or train a neural network, Nervana could be many times faster than existing hardware. Nervana will be good at matrix multiplication, convolutions, and other mathematical operations used in neural networks.

Interestingly, there'due south no enshroud on the chip like you'd find on a CPU. Instead, Nervana will use a software-defined memory management system, which can conform performance based on the needs of the neural network. Intel has also implemented its own numerical format called Flexpoint. This is less precise than regular integer math, but Intel says that's no trouble for neural networks. They're naturally resistant to racket, and in some cases noise in the information tin even aid in grooming neurons. The lower precision besides helps brand the fleck ameliorate at parallel computing, and then the overall network tin can have higher bandwidth and lower latency.

Intel is not alone in its quest to speed up neural networks. Google has developed cloud-based silicon called Tensor Processing Units, and Nvidia is pushing its GPUs as a solution to neural network processing. Facebook has gotten on board with Intel'due south hardware and made some contributions to the design. Intel says the Nervana NNP will ship past the end of 2017.

Now read: What are neural networks?