From WikiChip
Search results
- '''Artificial Intelligence:''' '''Artificial Intelligence'''9 KB (1,150 words) - 00:03, 2 October 2022
- ...ng]] algorithms, typically by operating on [[predictive models]] such as [[artificial neural network]]s (ANNs) or [[random forest]]s (RFs). ...processing unit'' (''TPU''), ''neural network processor'' (''NNP'') and ''intelligence processing unit'' (''IPU'') as well as ''vision processing unit'' (''VPU'')5 KB (640 words) - 16:27, 26 September 2023
- |market=Artificial Intelligence ...so for training of neural networks, suitable for working with the common [[artificial neural network|ANNs]] such as [[convolutional neural network|CNN]], [[recur4 KB (603 words) - 09:59, 11 August 2018
- * Artificial Intelligence1 KB (171 words) - 20:29, 19 November 2017
- |market=Artificial Intelligence * Holler, Mark, et al. "An electrically trainable artificial neural network (ETANN) with 10240 floating gate synapses." International Jo4 KB (568 words) - 17:12, 11 February 2018
- |market=Artificial Intelligence Loihi is fabricated on Intel's [[14 nm process]] and has a total of 130,000 artificial neurons and 130 million synapses. In addition to the 128 neuromorphic cores12 KB (1,817 words) - 01:28, 1 October 2021
- ...|AVX512VNNI}} which is designed to improve the performance of [[Artificial Intelligence]] workloads by improving the throughput of tight inner convolutional loop o32 KB (4,535 words) - 05:44, 9 October 2022
- ...nce computing designed specifically for the [[acceleration]] of artificial intelligence workloads.3 KB (388 words) - 02:47, 20 May 2019
- ...te [[2017]] specifically designed to [[accelerator|accelerate]] artificial intelligence workloads. This processor, which is fabricated on their own [[14 nm process3 KB (495 words) - 10:28, 10 May 2019
- ...te [[2017]] specifically designed to [[accelerator|accelerate]] artificial intelligence workloads. This processor, which is fabricated on their own [[14 nm process3 KB (495 words) - 10:28, 10 May 2019
- ...te [[2017]] specifically designed to [[accelerator|accelerate]] artificial intelligence workloads. This processor, which is fabricated on their own [[14 nm process3 KB (495 words) - 10:28, 10 May 2019
- ...abless]] [[American]] semiconductor company that specializes in Artificial Intelligence and development of [[neural processors]]. Nervana-based product development ...e of the earliest startups to specialize in the acceleration of Artificial Intelligence workloads. Nervana first-generaiton product sampled in limited quantities a2 KB (194 words) - 09:01, 11 June 2021
- |market=Artificial Intelligence8 KB (1,263 words) - 03:08, 9 December 2019
- |family=Vision Intelligence == Artificial Intelligence Engine ==3 KB (302 words) - 22:05, 12 April 2018
- |family=Vision Intelligence == Artificial Intelligence Engine ==3 KB (302 words) - 22:05, 12 April 2018
- |market=Artificial Intelligence2 KB (215 words) - 10:19, 19 May 2018
- ...features include advanced camera functionalities and Qualcomm's Artificial Intelligence Engine (AIE).3 KB (366 words) - 05:51, 3 October 2022
- ...years, the company has increased its presence in the area of [[artificial intelligence]].721 bytes (79 words) - 00:31, 5 July 2018
- ...neural processors]]. [[Bitmain]] started exploring the field of artificial intelligence and neural processors as early as [[2015]]. By April 2017, their first prod3 KB (413 words) - 12:02, 25 December 2018
- |market=Artificial Intelligence713 bytes (92 words) - 00:44, 16 September 2018
- |market=Artificial Intelligence658 bytes (83 words) - 11:20, 11 August 2018
- |market=Artificial Intelligence652 bytes (83 words) - 11:21, 11 August 2018
- ...ries, while based on the Turing architecture, lacks the Tensor (artificial intelligence) and RT (ray tracing) cores unique to Turing, providing a lower cost altern468 bytes (72 words) - 19:57, 25 March 2019
- ...rocessors]] designed by [[Intel]] for the [[acceleration]] of [[artificial intelligence]] workloads. The name and original architecture originated with the [[Nerva8 KB (1,145 words) - 12:42, 1 February 2020
- |market 2=Artificial Intelligence613 bytes (71 words) - 23:14, 11 October 2019
- ...[[supercomputers]] and [[ASICs]] for the [[acceleration]] of [[artificial intelligence]].765 bytes (77 words) - 09:01, 25 November 2019
- ...ch chip designed for the [[acceleration]] of [[neural processor|artificial intelligence]]. The design and implementation of the chip was said to have taken just ni2 KB (261 words) - 01:14, 21 January 2020
- |market=Artificial Intelligence ...ricated on pre-production [[Intel 4 process]] and has a total of 1,048,576 artificial neurons and 120 million synapses. In addition to the 128 neuromorphic cores4 KB (507 words) - 22:06, 27 November 2022