Logo image
Learning to Approximate: Circuit Learning and Deep Reinforcement Learning for Approximate Logic Synthesis with an Error Rate Guarantee

Learning to Approximate: Circuit Learning and Deep Reinforcement Learning for Approximate Logic Synthesis with an Error Rate Guarantee

Chi-Wei Chen, Yi-Ting Li, Wuqian Tang, Yung-Chih Chen, Jian-Meng Yang Chun-Yao Wang
Proceedings - Design, Automation, and Test in Europe Conference and Exhibition, pp.1-7
20/04/2026
Aluminum Backtracking Circuits Delays Design automation Error analysis Learning (artificial intelligence) Printing Training Optimization
Approximate computing is an emerging design paradigm for error-tolerant applications, such as multimedia processing and neural network acceleration, which enables significant reductions in circuit area, delay, or power consumption through controlled accuracy trade-offs. This paper presents a novel deep reinforcement learning (DRL)-based framework for approximate logic synthesis (ALS) augmented with a backtracking mechanism, aimed at minimizing the area-delay product (ADP) while satisfying error rate constraints. The experimental results demonstrate that our approach can reduce the ADP by up to 92.83%, and 56.79% on average under a 5% error rate constraint.
1
Logo image