Neural processing unit: Difference between revisions

Revision as of 16:20, 16 June 2016

Revision as of 16:21, 16 June 2016

Line 15:

* [[SpiNNaker]], a manycure design coming traditional [[ARM]] cores with an enhanced network fabric design specialised for simulating a large neural network.

* [[TrueNorth]] The most unconventional example, a manycore design based on [[spiking neuron]]s rather than traditional arithmetic. Frequency of pulses represents signal intensity. As of 2016 there is no consensus amongst AI researchers if this is the right way to go,<ref>{{cite web|title=yann lecun on IBM truenorth|url=https://www.facebook.com/yann.lecun/posts/10152184295832143}}</ref>but some results are promising, with large energy savings demonstrated for vision tasks.

<ref>{{cite web|title=yann lecun on IBM truenorth|url=https://www.facebook.com/yann.lecun/posts/10152184295832143}}</ref>

but some results are promising, with large energy savings demonstrated for vision tasks.

* [[Zeroth NPU]] a design by Qualcom aimed squarely at bringing speech and image recognition capabilities to mobile devices.