Electric Analog Circuit Design with Hypernetworks And A Differential Simulator

The manual design of analog circuits is a tedious task of parameter tuning that requires hours of work by human experts. In this work, we make a significant step towards a fully automatic design method that is based on deep learning. The method selects the components and their configuration, as well as their numerical parameters. By contrast, the current literature methods are limited to the parameter fitting part only. A two-stage network is used, which first generates a chain of circuit components and then predicts their parameters. A hypernetwork scheme is used in which a weight generating network, which is conditioned on the circuit’s power spectrum, produces the parameters of a primal RNN network that places the components. A differential simulator is used for refining the numerical values of the components. We show that our model provides an efficient design solution, and is superior to alternative solutions.

[1]  Enrique J. Carmona,et al.  Automatic design of analog electronic circuits using grammatical evolution , 2018, Appl. Soft Comput..

[2]  Franziska Hoffmann,et al.  Design Of Analog Cmos Integrated Circuits , 2016 .

[3]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[4]  Song Han,et al.  Learning to Design Circuits , 2018, ArXiv.

[5]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[6]  Ronald J. Williams,et al.  A Learning Algorithm for Continually Running Fully Recurrent Neural Networks , 1989, Neural Computation.

[7]  Behzad Razavi,et al.  Design of Analog CMOS Integrated Circuits , 1999 .

[8]  Joseph Suarez,et al.  Language Modeling with Recurrent Highway Hypernetworks , 2017, NIPS.

[9]  Quoc V. Le,et al.  HyperNetworks , 2016, ICLR.

[10]  Lior Wolf,et al.  Deep Meta Functionals for Shape Representation , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[11]  K. S. Suresh Kumar.  Electric Circuits and Networks , 2008 .

[12]  L. Dumitriu,et al.  On analog circuit parameter estimation , 2012, 2012 International Conference on Applied and Theoretical Electricity (ICATE).

[13]  Mourad Loulou,et al.  Design of Analog Circuits through Symbolic Analysis , 2018 .

[14]  Fei Wang,et al.  CSI-Net: Unified Human Body Characterization and Action Recognition , 2018, 1810.03064.

[15]  Zhang He,et al.  Parameter estimation of analog circuits based on the fractional wavelet method , 2015 .

[16]  Luca Antiga,et al.  Automatic differentiation in PyTorch , 2017 .

[17]  Lior Wolf,et al.  Hyper-Graph-Network Decoders for Block Codes , 2019, NeurIPS.