Výsledky vyhledávání - "Eric G. Nestler"

A 64-Tile 2.4-Mb In-Memory-Computing CNN Accelerator Employing Charge-Domain Compute

Autor: Peter J. Ramadge, Hossein Valavi, Naveen Verma, Eric G. Nestler

Publikováno v: IEEE Journal of Solid-State Circuits. 54:1789-1799

Large-scale matrix-vector multiplications, which dominate in deep neural networks (DNNs), are limited by data movement in modern VLSI technologies. This paper addresses data movement via an in-memory-computing accelerator that employs charged-domain

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::a4858b738fce96c31fa0089ae005b5c3
https://doi.org/10.1109/jssc.2019.2899730

Zobrazit plný text záznamu

A Mixed-Signal Binarized Convolutional-Neural-Network Accelerator Integrating Dense Weight Storage and Multiplication for Reduced Data Movement

Autor: Eric G. Nestler, Peter J. Ramadge, Hossein Valavi, Naveen Verma

Publikováno v: VLSI Circuits

We present a 65nm CMOS mixed-signal accelerator for first and hidden layers ofbinarized CNNs. Hidden layers support up to 512, 3 ×3 ×512 binary - input filters, and first layers support up to 64, 3×3 ×3 analog-input filters. Weight storage and mu

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::15339947214a1d6e6ee043785d8b1330
https://doi.org/10.1109/vlsic.2018.8502421

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání