An energy-efficient digital ReRAM-crossbar-based CNN with bitwise parallelism

L Ni, Z Liu, H Yu, RV Joshi - IEEE Journal on Exploratory solid …, 2017 - ieeexplore.ieee.org
There is great attention to develop hardware accelerator with better energy efficiency, as
well as throughput, than GPUs for convolutional neural network (CNN). The existing …

LTNN: A layerwise tensorized compression of multilayer neural network

H Huang, H Yu - IEEE transactions on neural networks and …, 2018 - ieeexplore.ieee.org
An efficient deep learning requires a memory-efficient construction of a neural network. This
paper introduces a layerwise tensorized formulation of a multilayer neural network, called …

MCS HOG features and SVM based handwritten digit recognition system

HA Khan - Journal of Intelligent Learning Systems and …, 2017 - eprints.go4mailburst.com
Digit Recognition is an essential element of the process of scanning and converting
documents into electronic format. In this work, a new Multiple-Cell Size (MCS) approach is …

An energy-efficient and high-throughput bitwise CNN on sneak-path-free digital ReRAM crossbar

L Ni, Z Liu, W Song, JJ Yang, H Yu… - 2017 IEEE/ACM …, 2017 - ieeexplore.ieee.org
Convolutional neural network (CNN) based machine learning requires a highly parallel as
well as low power consumption (including leakage power) hardware accelerator. In this …

Energy-efficient machine learning accelerator for binary neural networks

W Mao, Z Xiao, P Xu, H Ren, D Liu, S Zhao… - Proceedings of the …, 2020 - dl.acm.org
Binary neural network (BNN) has shown great potential to be implemented with power
efficiency and high throughput. Compared with its counterpart, the convolutional neural …

Design and implementation of deep neural network for edge computing

J Zhang, Y Guo, X Hu, R Li - IEICE TRANSACTIONS on Information …, 2018 - search.ieice.org
In recent years, deep learning based image recognition, speech recognition, text translation
and other related applications have brought great convenience to people's lives. With the …

[PDF][PDF] Efficient handwritten digit classification using user-defined classification algorithm

RVK Reddy, UR Babu - International Journal on …, 2018 - pdfs.semanticscholar.org
In automatic numeral digit recognition system, feature selection is most important factor for
achieving high recognition performance. To achieve this, the present paper3 proposed3 …

Enhancing Scene Text Recognition by Strengthening Attention Alignment

S Qing, L Chen, L Lin, J Zhang - 2023 6th International …, 2023 - ieeexplore.ieee.org
Scene text recognition (STR) refers to recognizing text instance images from natural scenes
as text. STR has been a hot area of computer vision because it has various applications. The …

Oster: an orientation sensitive scene text recognizer with centerline rectification

Z Feng, C Du, Y Wang, B Xiao - … , New Zealand, November 26–29, 2019 …, 2020 - Springer
Scene texts in China are always arbitrarily arranged in two forms: horizontally and vertically.
These two forms of texts exhibit distinctive features, making it difficult to recognize them …

In-memory computing by RRAM for machine learning

L Ni - 2018 - dr.ntu.edu.sg
The Internet data has reached exa-scale (1018 bytes), which has introduced emerging need
to re-examine the state-of-the-art hardware architectures for data-oriented computing. There …