AnGeL: Fully-Automated Analog Circuit Generator Using a Neural Network Assisted Semi-Supervised Learning Approach

Machine Learning (ML) has shown promising results in predicting the behavior of analog circuits. However, in order to completely cover the design space for today's complicated circuits, supervised ML requires a large number of labeled samples which is time-consuming to provide. Furthermore, a separate dataset must be collected for each circuit topology making all other previously gathered datasets useless. In this paper, we first present a database including labeled and unlabeled data. We use neural networks to determine the behavior of complicated topologies by combining the more simple ones. By generating such unlabeled data, the time for providing the training set is significantly reduced compared to the conventional approaches. Using this database, we propose a fully-automated analog circuit generator framework, AnGeL. AnGeL performs all the schematic circuit design steps from deciding the circuit topology to determining the circuit parameters i.e. sizing. Our results show that for multiple circuit topologies, in comparison to the state-of-the-art works while maintaining the same accuracy, the required labeled data is reduced by 4.7x -1090x. Also, the runtime of AnGeL is 2.9x -75x faster.

Automated summary

Machine learning has shown promise in predicting analog circuit behavior, but supervised learning requires a large amount of labeled samples and separate datasets for each circuit topology. This paper presents a database with both labeled and unlabeled data, using neural networks to determine complex circuit behavior by combining simpler ones. By generating unlabeled data, the training set can be provided much faster. The paper also proposes a fully-automated analog circuit generator framework called AnGeL, achieving equivalent accuracy with reduced labeled data and faster runtime compared to state-of-the-art works.