A Post-training Quantization Method for the Design of Fixed-Point-Based FPGA/ASIC Hardware Accelerators for LSTM/GRU Algorithms

Recurrent Neural Networks (RNNs) have become important tools for tasks such as speech recognition, text generation, or natural language processing. However, their inference may involve up to billions of operations and their large number of parameters leads to large storage size and runtime memory us...

Descripción completa

Detalles Bibliográficos
Autores principales: Rapuano, Emilio, Pacini, Tommaso, Fanucci, Luca
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Hindawi 2022
Materias:
Research Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9117057/
https://www.ncbi.nlm.nih.gov/pubmed/35602644
http://dx.doi.org/10.1155/2022/9485933

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9117057/
https://www.ncbi.nlm.nih.gov/pubmed/35602644
http://dx.doi.org/10.1155/2022/9485933

Ejemplares similares