Issue |
E3S Web Conf.
Volume 631, 2025
6th International Conference on Multidisciplinary Design Optimization and Applications (MDOA 2024)
|
|
---|---|---|
Article Number | 02004 | |
Number of page(s) | 8 | |
Section | Materials and Optimal Design | |
DOI | https://doi.org/10.1051/e3sconf/202563102004 | |
Published online | 26 May 2025 |
Higher-order HDL: Applied to MLP neural network hardware implementation
1 CNAM – CEDERIC – LAETITIA Paris, France
2 DGUT – CNAM Institute, Dongguan university of Technology, Dongguan, China
a) Corresponding author: samuel.garcia@lecnam.net;
b) ming-jun.zhang@lecnam.net;
In this article, we describe a methodology for the rapid implementation of a hardware architecture using a higher-order approach. This methodology uses a combination of TCL and VHDL for higher-order coding (i.e. code produced by code) and is supported by industry-standard HDL development tools. To explore this methodology, we used an FPGA implementation of an artificial neural network (ANN) as a guinea pig application. This enabled us to produce a fully generic multilayer perceptron model where the number of layers, the size of each layer, the types of synaptic signals and the activation function are easily customizable. Not only does this approach make the development of such an application faster, but the high degree of genericity of the model cannot be achieved with conventional VHDL methodology. This article presents feedback from our first steps with this methodology and its application to MLP hardware architecture. Index Terms—VHDL, TCL, Artificial Neural Networks, Multilayer Perceptron, higher-order programming, Methodology
© The Authors, published by EDP Sciences, 2025
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.