RUS  ENG
Full version
JOURNALS // Intelligent systems. Theory and applications // Archive

Intelligent systems. Theory and applications, 2022 Volume 26, Issue 1, Pages 220–224 (Mi ista359)

Part 5. Artificial neural networks and machine intelligence

Hardware for neural networks

D. A. Ivanovab

a Lomonosov Moscow State University, Faculty of CMC
b Neuromorphic Computing Group, PI Cifrum, Rosatom

Abstract: The current success in the field of neural networks is largely due to the availability of a sufficient amount of hardware resources. The paper analyzes the main modern hardware solutions for AI (CPU, GPU, TPU), considers their advantages and disadvantages.

Keywords: GPU, TPU, hardware, neural networks.



© Steklov Math. Inst. of RAS, 2024