INTERNATIONAL SPECIAL SESSION

Machine Learning for EDA

We are organizing a special session on " Machine Learning for EDA " for TAAI2023, held in National Yunlin University of Science and Technology, Yunlin County, in Taiwan on December 1-2, 2023.

In recent years, the development of semiconductor technology has led to exponential growth in the scale of integrated circuits (ICs), challenging the scalability and reliability of the circuit design process. To deal with extremely large search spaces with low latency, Electronic Design Automation (EDA) software needs to be more effective and efficient. Machine learning (ML) models have been extensively used to automate the design of digital circuits, replacing pure optimization algorithms. This has significantly reduced the time complexity associated with designing a robust digital IC.

The use of ML for EDA has become a trending topic, with numerous studies proposing the use of ML to improve EDA methods. These studies cover almost all stages of the chip design process, including design space reduction and exploration, logic synthesis, placement, routing, testing, verification, manufacturing, etc. The special session on Machine Learning for EDA aims to apply ML techniques to accelerate EDA tasks. ML methods show great potential in generating high-quality solutions

Session Information

Session Title :

Machine Learning for EDA

Session Organizer :

Prof. Dun-Wei Cheng

Institution :

National Yunlin University of Science and Technology

E-mail :

dunwei@yuntech.edu.tw

Topics / Areas

We invite academic researchers and industry professionals from a broad range of disciplines to submit to this special issue. Topics of interest include, but are not limited to:
  1. Machine Learning for Logic Synthesis
  2. Machine Learning for Placement and Routing Prediction
  3. Machine Learning for Circuit Topology Design Automation
  4. Machine Learning for Device Sizing Automation
  5. Machine Learning for Analog Layout
  6. Machine Learning for Test Set Redundancy Reduction
  7. Machine Learning for Test & Diagnosis Complexity Reduction

Important Information

Accepted papers will be submitted for inclusion into the Communications in Computer and Information Science (CCIS) by Springer. CCIS is indexed in DBLP, Google Scholar, EI-Compendex, and Scopus. Please note that papers must submit via the submission system website and meet the format of TAAI2023.

Scroll to Top