Description
Title: SENTIMENT COMPRESSION ANALYSIS Models for effective hardware processing from CNN
Abstract: The development of convolutional neural networks (CNNs) began with the goal of classifying images. Soon after they were developed, they were used in other fields, such as natural language processing (NLP). Artificial intelligence-based solutions are now found on embedded systems and mobile devices, which places restrictions on things like memory usage and power consumption. As a result of CNN’s memory and processing demands, they must be compressed in order to be mapped to the hardware. The outcomes of compressing effective CNNs for sentiment analysis are shown in this paper. The two main steps are quantization and pruning. The method for mapping a compressed network to an FPGA is described, as well as the implementation’s outcomes. According to the simulations that were run, the network’s 5-bit width is sufficient to prevent accuracy losses when compared to the floating-point version. Additionally, a significant decrease in memory footprint (between 85 and 93% as compared to the original model) was made.
Keywords: natural language processing, convolutional neural networks, FPGA, compression
Paper Quality: SCOPUS / Web of Science Level Research Paper
Paper type: Analysis Based Research Paper
Subject: Computer Science
Writer Experience: 20+ Years
Plagiarism Report: Turnitin Plagiarism Report will be less than 10%
Restriction: Only one author may purchase a single paper. The paper will then indicate that it is out of stock.
What will I get after the purchase?
A turnitin plagiarism report of less than 10% in a pdf file and a full research paper in a word document.
In case you have any questions related to this research paper, please feel free to call/ WhatsApp on +919726999915
Reviews
There are no reviews yet.