Neural network accelerator design using computing in memory
Image Processing has become an extremely popular field of application for Neural Networks. Convolution is a basic and critical operation for pattern recognition and breaking down images into feature maps. Similarly, “Deconvolution” is a critical step for constructing new data points out of given inp...
Saved in:
Main Author: | |
---|---|
Other Authors: | |
Format: | Final Year Project |
Language: | English |
Published: |
Nanyang Technological University
2021
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/148415 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-148415 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1484152021-05-01T13:23:00Z Neural network accelerator design using computing in memory Seah, Leon Shin Yang Weichen Liu School of Computer Science and Engineering liu@ntu.edu.sg Engineering::Computer science and engineering::Hardware::Memory structures Image Processing has become an extremely popular field of application for Neural Networks. Convolution is a basic and critical operation for pattern recognition and breaking down images into feature maps. Similarly, “Deconvolution” is a critical step for constructing new data points out of given inputs for tasks such as image recovery in generative adversarial networks. With new emerging technology, Resistive Random-Access-Memory (ReRAM) based architectures have been widely tested and delivers good performance in accelerating the convolution operation through a process of “Computing-in-Memory”. The “Deconvolution” operation, however, still suffers from high overheads due to significant redundancies (>80%) involving zero-multiplications and/or incompatibility with the existing ReRAM based accelerator designs. In this project, we will explore various state-of-the-art Computing-in-Memory accelerator designs that have been proposed and focus our efforts on evaluating and implementing a design for a “Deconvolution” accelerator called RED. Bachelor of Engineering (Computer Engineering) 2021-05-01T13:23:00Z 2021-05-01T13:23:00Z 2021 Final Year Project (FYP) Seah, L. S. Y. (2021). Neural network accelerator design using computing in memory. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/148415 https://hdl.handle.net/10356/148415 en SCSE20-0520 application/pdf Nanyang Technological University |
institution |
Nanyang Technological University |
building |
NTU Library |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
NTU Library |
collection |
DR-NTU |
language |
English |
topic |
Engineering::Computer science and engineering::Hardware::Memory structures |
spellingShingle |
Engineering::Computer science and engineering::Hardware::Memory structures Seah, Leon Shin Yang Neural network accelerator design using computing in memory |
description |
Image Processing has become an extremely popular field of application for Neural Networks. Convolution is a basic and critical operation for pattern recognition and breaking down images into feature maps. Similarly, “Deconvolution” is a critical step for constructing new data points out of given inputs for tasks such as image recovery in generative adversarial networks. With new emerging technology, Resistive Random-Access-Memory (ReRAM) based architectures have been widely tested and delivers good performance in accelerating the convolution operation through a process of “Computing-in-Memory”. The “Deconvolution” operation, however, still suffers from high overheads due to significant redundancies (>80%) involving zero-multiplications and/or incompatibility with the existing ReRAM based accelerator designs. In this project, we will explore various state-of-the-art Computing-in-Memory accelerator designs that have been proposed and focus our efforts on evaluating and implementing a design for a “Deconvolution” accelerator called RED. |
author2 |
Weichen Liu |
author_facet |
Weichen Liu Seah, Leon Shin Yang |
format |
Final Year Project |
author |
Seah, Leon Shin Yang |
author_sort |
Seah, Leon Shin Yang |
title |
Neural network accelerator design using computing in memory |
title_short |
Neural network accelerator design using computing in memory |
title_full |
Neural network accelerator design using computing in memory |
title_fullStr |
Neural network accelerator design using computing in memory |
title_full_unstemmed |
Neural network accelerator design using computing in memory |
title_sort |
neural network accelerator design using computing in memory |
publisher |
Nanyang Technological University |
publishDate |
2021 |
url |
https://hdl.handle.net/10356/148415 |
_version_ |
1698713713340579840 |