With the new variety of Artificial Intelligence chips, Intel would like to give machine and deep learning jobs their own specialized processors, separate of traditional chipsets.
- January 2nd, 2017
- Other Hardware
- ai training, artificial intelligence chips, deep learning job, intel specialized processor, machine learning
These days, Intel Corporation belongs to almost every AI utilization, but in advanced neural network setups, GPUs (graphic processor units, like nVidia) are doing the majority of the work for deep neural network training. For that reason, in august, Intel acquired Nervana for an estimated $400M.
Nervana Platform is the company's first specialized speeding up platform for artificial intelligence. Intel said they were including Nervana silicon technological innovation into Xeons that clients could use in late 2017. It's very near this and it wasn't clear how Nervana innovation was integrated.
They introduced a variety of new products, solutions and investments from the edge to the data center to assist expand and boost the growth of artificial intelligence (AI). Intel sees AI changing the way companies operate and how people interact with the world. Intel is putting together the widest set of technology options to drive AI capabilities in all from smart production lines and drones to sports, fraud prognosis and autonomous cars.
The AI chips pertain to Intel's strategy created to anticipate a rush of applications and web services that will be using neural networks. The specialized chips will form component of the first-generation range but will give way to new chips that Intel aims to develop as small modules within the main computing processors in the future.
“We expect the Intel Nervana platform to produce breakthrough performance and dramatic reductions in the time to train complex neural networks,”
Diane Bryant, executive vice president and general manager of the Data Center Group at Intel, said.
“Before the end of the decade, Intel will deliver a 100-fold increase in performance that will turbocharge the pace of innovation in the emerging deep learning space.”
They announce Intel Saffron Technology ™ platform which utilize memory-based reasoning techniques and transparent analysis of polymorphous data. This technology is also especially well-suited to small devices, making smart local analytics possible across IoT and assisting advance state-of the-art collaborative AI.
To further AI investigation and strategy, they introduced the formation of the Intel Nervana AI board, which will include leading industry and university thought leaders. Intel announced four founding members: Yoshua Bengio (University of Montreal), Bruno Olshausen (UC Berkeley), Jan Rabaey (UC Berkeley) and Ron Dror (Stanford University).