Median Binary-Connect Method and a Binary Convolutional Neural Nework for Word Recognition

2018-11-07 · Spencer Sheen, Jiancheng Lyu

We propose and study a new projection formula for training binary weight convolutional neural networks. The projection formula measures the error in approximating a full precision (32 bit) vector by a 1-bit vector in the l_1 norm instead of the standard l_2 norm. The l_1 projector is in closed analytical form and involves a median computation instead of an arithmatic average in the l_2 projector. Experiments on 10 keywords classification show that the l_1 (median) BinaryConnect (BC) method outperforms the regular BC, regardless of cold or warm start. The binary network trained by median BC and a recent blending technique reaches test accuracy 92.4%, which is 1.1% lower than the full-precision network accuracy 93.5%. On Android phone app, the trained binary network doubles the speed of full-precision network in spoken keywords recognition.

📄 PDF Abstract BibTeX arXiv:1811.02784

Code (0)

등록된 구현이 없습니다.

Tasks

General Classification

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Nearest Neighbor Median Shift Clustering for Binary Data

2019-02-11 · Gaël Beck, Tarn Duong, Mustapha Lebbah, Hanane Azzag

We describe in this paper the theory and practice behind a new modal clustering method for binary data. Our approach (BinNNMS) is based on the nearest neighbor median shift. The median shift is an extension of the well-k…

Clustering

XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks

2016-03-16 · Mohammad Rastegari, Vicente Ordonez, Joseph Redmon, Ali Farhadi

We propose two efficient approximations to standard convolutional neural networks: Binary-Weight-Networks and XNOR-Networks. In Binary-Weight-Networks, the filters are approximated with binary values resulting in 32x mem…

Binarization Classification with Binary Neural Network General Classification

Structured Convolution Matrices for Energy-efficient Deep learning

2016-06-08 · Rathinakumar Appuswamy, Tapan Nayak, John Arthur, Steven Esser 외

We derive a relationship between network representation in energy-efficient neuromorphic architectures and block Toplitz convolutional matrices. Inspired by this connection, we develop deep convolutional networks using a…

Deep Learning General Classification

SoFAr: Shortcut-based Fractal Architectures for Binary Convolutional Neural Networks

2020-09-11 · Zhu Baozhou, Peter Hofstee, Jinho Lee, Zaid Al-Ars

Binary Convolutional Neural Networks (BCNNs) can significantly improve the efficiency of Deep Convolutional Neural Networks (DCNNs) for their deployment on resource-constrained platforms, such as mobile and embedded syst…

Binarization

BiMLP: Compact Binary Architectures for Vision Multi-Layer Perceptrons

2022-12-29 · Yixing Xu, Xinghao Chen, Yunhe Wang

This paper studies the problem of designing compact binary architectures for vision multi-layer perceptrons (MLPs). We provide extensive analysis on the difficulty of binarizing vision MLPs and find that previous binariz…