Back to Search
Start Over
Compression of Convolutional Neural Network for Natural Language Processing
- Source :
- Computer Science. 21
- Publication Year :
- 2020
- Publisher :
- AGHU University of Science and Technology Press, 2020.
-
Abstract
- Convolutional Neural Networks (CNNs) were created for image classification tasks. Quickly, they were applied to other domains, including Natural Language Processing (NLP). Nowadays, the solutions based on artificial intelligence appear on mobile devices and in embedded systems, which places constraints on, among others, the memory and power consumption. Due to CNNs memory and computing requirements, to map them to hardware they need to be compressed.This paper presents the results of compression of the efficient CNNs for sentiment analysis. The main steps involve pruning and quantization. The process of mapping the compressed network to FPGA and the results of this implementation are described. The conducted simulations showed that 5-bit width is enough to ensure no drop in accuracy when compared to the floating point version of the network. Additionally, the memory footprint was significantly reduced (between 85% and 93% comparing to the original model).
- Subjects :
- Computer Networks and Communications
Computer science
02 engineering and technology
010501 environmental sciences
computer.software_genre
01 natural sciences
Convolutional neural network
Artificial Intelligence
0202 electrical engineering, electronic engineering, information engineering
Computer Science (miscellaneous)
Quantization (image processing)
0105 earth and related environmental sciences
Contextual image classification
business.industry
Quantization (signal processing)
Sentiment analysis
Process (computing)
020206 networking & telecommunications
Computer Graphics and Computer-Aided Design
Computational Theory and Mathematics
Modeling and Simulation
Memory footprint
Computer Vision and Pattern Recognition
Artificial intelligence
business
computer
Pruning (morphology)
Natural language processing
Subjects
Details
- ISSN :
- 23007036 and 15082806
- Volume :
- 21
- Database :
- OpenAIRE
- Journal :
- Computer Science
- Accession number :
- edsair.doi...........99385b57b76f548cecb7060b0d39c46f