Approximations in Deep Learning
Résumé
The design and implementation of Deep Learning (DL) models is currently receiving a lot of attention from both industrials and academics. However, the computational workload associated with DL is often out of reach for low-power embedded devices and is still costly when run on datacenters. By relaxing the need for fully precise operations, Approximate Computing (AxC) substantially improves performance and energy efficiency. DL is extremely relevant in this context, since playing with the accuracy needed to do adequate computations will significantly enhance performance, while keeping the quality of results in a user-constrained range. This chapter will explore how AxC can improve the performance and energy efficiency of hardware accelerators in DL applications during inference and training.
Mots clés
Pruning
Quantization
Weight sharing
Binary neural network
Low precision
Mixed precision training
Computer arithmetic
Number representations
Fixed-point arithmetic
Floating-point arithmetic
Support for approximation in DNN accelerators
Low energy
High performance
Low power
Approximate computing
Deep learning
Deep neural networks
Approximation for inference
Approximation for training
Origine | Fichiers produits par l'(les) auteur(s) |
---|