paper-with-me

홈 › Papers

Deep Convolutional Neural Network Inference with Floating-point Weights and Fixed-point Activations

2017-03-08 · Liangzhen Lai, Naveen Suda, Vikas Chandra

Deep convolutional neural network (CNN) inference requires significant amount of memory and computation, which limits its deployment on embedded devices. To alleviate these problems to some extent, prior research utilize low precision fixed-point numbers to represent the CNN weights and activations. However, the minimum required data precision of fixed-point weights varies across different networks and also across different layers of the same network. In this work, we propose using floating-point numbers for representing the weights and fixed-point numbers for representing the activations. We show that using floating-point representation for weights is more efficient than fixed-point representation for the same bit-width and demonstrate it on popular large-scale CNNs such as AlexNet, SqueezeNet, GoogLeNet and VGG-16. We also show that such a representation scheme enables compact hardware multiply-and-accumulate (MAC) unit design. Experimental results show that the proposed scheme reduces the weight storage by up to 36% and power consumption of the hardware multiplier by up to 50%.

📄 PDF Abstract BibTeX arXiv:1703.03073

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Residual Connection 설명 없음
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Average Pooling 설명 없음
Fire Module 설명 없음
Local Response Normalization Local Response Normalization is a normalization layer that implements the idea of lateral inhibition. Lateral inhibition is a concept in neurobiology that refers to the…
Auxiliary Classifier Auxiliary Classifiers are type of architectural component that seek to improve the convergence of very deep networks. They are classifier heads we attach to layers before the…
Inception Module An Inception Module is an image model block that aims to approximate an optimal local sparse structure in a CNN. Put simply, it allows for us to use multiple types of filter…
Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…

Similar Papers 제목 키워드 기반

Quantizing deep convolutional networks for efficient inference: A whitepaper

2018-06-21 · Raghuraman Krishnamoorthi

We present an overview of techniques for quantizing convolutional neural networks for inference with integer weights and activations. Per-channel quantization of weights and per-layer quantization of activations to 8-bit…

Quantization

Hardware-Software Codesign of Accurate, Multiplier-free Deep Neural Networks

2017-05-11 · Hokchhay Tann, Soheil Hashemi, Iris Bahar, Sherief Reda

While Deep Neural Networks (DNNs) push the state-of-the-art in many machine learning applications, they often require millions of expensive floating-point operations for each input classification. This computation overhe…

General Classification

Fixed-Point Convolutional Neural Network for Real-Time Video Processing in FPGA

2018-08-29 · Roman Solovyev, Alexander Kustov, Dmitry Telpukhov, Vladimir Rukhlov 외

Modern mobile neural networks with a reduced number of weights and parameters do a good job with image classification tasks, but even they may be too complex to be implemented in an FPGA for video processing tasks. The a…

image-classificationImage Classification

A scalable and efficient convolutional neural network accelerator using HLS for a System on Chip design

2020-04-27 · Kim Bjerge, Jonathan Horsted Schougaard, Daniel Ejnar Larsen

This paper presents a configurable Convolutional Neural Network Accelerator (CNNA) for a System on Chip design (SoC). The goal was to accelerate inference of different deep learning networks on an embedded SoC platform. …

High-Level Synthesis

ADaPTION: Toolbox and Benchmark for Training Convolutional Neural Networks with Reduced Numerical Precision Weights and Activation

2017-11-13 · Moritz B. Milde, Daniel Neil, Alessandro Aimar, Tobi Delbruck 외

Deep Neural Networks (DNNs) and Convolutional Neural Networks (CNNs) are useful for many practical tasks in machine learning. Synaptic weights, as well as neuron activation functions within the deep network are typically…

Quantization