Please use this identifier to cite or link to this item:
http://hdl.handle.net/2080/4599
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Oraon, Pawan | - |
dc.contributor.author | Mangaraj, Soumyashree | - |
dc.contributor.author | Swain, Ayas Kanta | - |
dc.contributor.author | Mahapatra, Kamalakanta | - |
dc.date.accessioned | 2024-07-02T11:58:05Z | - |
dc.date.available | 2024-07-02T11:58:05Z | - |
dc.date.issued | 2024-06 | - |
dc.identifier.citation | Great Lakes Symposium on VLSI 2024 (GLSVLSI 24), 12-14 June 2024 | en_US |
dc.identifier.uri | http://hdl.handle.net/2080/4599 | - |
dc.description | Copyright belongs to proceeding publisher | en_US |
dc.description.abstract | Convolutional Neural Networks (CNNs) have demonstrated re-markable success in image recognition tasks, but their deployment on resource-constrained devices remains challenging due to their computational complexity and memory requirements. This abstract presents an overview of hardware accelerator implementations for CNN-based image recognition, focusing on techniques to optimize performance, energy efficiency, and resource utilization. Hardware accelerators such as Field-Programmable Gate Arrays (FPGAs) offer parallel processing capabilities that can exploit the inherent paral-lelism in CNN computations. Design considerations include optimiz-ing memory access patterns, and minimizing communication over-head between processing elements. Techniques such as pipelining, unrolling, quantization, and network compression are employed to reduce the computational and memory footprint of CNN models without significantly compromising accuracy. Hardware-software co-design methodologies enable seamless integration of CNN in-ference engines with host systems, facilitating real-time image recognition applications. The computational time of the proposed CNN is lower compared to that of the recent research works. Addi-tionally, the proposed hardware design exhibits reduced memory, power consumption, and resource utilization as compared with recent literarture for MNIST digit recognition with 98.9% accuracy. | en_US |
dc.subject | FPGA | en_US |
dc.subject | Convolutional Neural Network | en_US |
dc.subject | Hardware Accelerator | en_US |
dc.subject | Python, PYNQ-Z2 | en_US |
dc.subject | High Level Synthesis | en_US |
dc.subject | Pipelining | en_US |
dc.subject | Unrolling | en_US |
dc.title | Hardware Accelerated Quantized Hand Written Digit Recognition via High Level Synthesis | en_US |
dc.type | Article | en_US |
Appears in Collections: | Conference Papers |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
2024_GSLVLSI_POraon_Hardware.pdf | 3.48 MB | Adobe PDF | View/Open Request a copy |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.