Loading Now

Summary of Skip the Benchmark: Generating System-level High-level Synthesis Data Using Generative Machine Learning, by Yuchao Liao et al.


Skip the Benchmark: Generating System-Level High-Level Synthesis Data using Generative Machine Learning

by Yuchao Liao, Tosiron Adegbija, Roman Lysecky, Ravi Tandon

First submitted to arxiv on: 23 Apr 2024

Categories

  • Main: Machine Learning (cs.LG)
  • Secondary: Artificial Intelligence (cs.AI); Hardware Architecture (cs.AR)

     Abstract of paper      PDF of paper


GrooveSquid.com Paper Summaries

GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!

Summary difficulty Written by Summary
High Paper authors High Difficulty Summary
Read the original abstract here
Medium GrooveSquid.com (original content) Medium Difficulty Summary
The paper proposes a novel approach called Vaegan, which employs generative machine learning to generate synthetic data that is robust enough to support complex system-level HLS DSE experiments. The method utilizes Variational Autoencoder (VAE) and Generative Adversarial Network (GAN) architectures to create high-fidelity synthetic datasets for High-Level Synthesis (HLS) Design Space Exploration (DSE). The authors evaluate Vaegan using state-of-the-art datasets and metrics, demonstrating its effectiveness in generating synthetic HLS data that closely mirrors the ground truth’s distribution. This work has significant implications for the efficiency and accuracy of system-level HLS DSE experiments.
Low GrooveSquid.com (original content) Low Difficulty Summary
Vaegan is a new way to create fake but realistic data for High-Level Synthesis (HLS) Design Space Exploration (DSE). Currently, making this kind of data takes a lot of expertise and time. This paper shows that Vaegan can generate synthetic data that’s close enough to real data to help with complex HLS experiments. The method uses special kinds of machine learning called Variational Autoencoder (VAE) and Generative Adversarial Network (GAN). The authors tested Vaegan using well-known datasets and metrics, and it worked well. This means Vaegan can be a helpful tool for researchers who need more data to improve their HLS designs.

Keywords

» Artificial intelligence  » Gan  » Generative adversarial network  » Machine learning  » Synthetic data  » Variational autoencoder