Self-adaptive quasi-Gaussian circuits for analog on-chip-trainable multi-class classifiers

Self-adaptive quasi-Gaussian circuits have been developed and introduced to an analog multi-class classifier in order to enhance its classification performance. By applying a floating threshold scheme to the quasi-Gaussian kernel, the kernel can extend its tail region adaptively according to the characteristics of input data. As a result, the misclassification problem due to the zero tail region in the quasi-Gaussian kernel has been completely eliminated, and the classification accuracy is significantly improved. Software simulation showed the performance is comparable to complex Gaussian-kernel Support Vector Machines. A proof-of-concept chip implementing an analog on-chip-trainable multi-class classifier which employs 64-dimensional self-adaptive quasi-Gaussian circuits was designed in a 0.18-μm CMOS technology and is now under fabrication. Its successful operation was confirmed by Nanosim simulation.

[1]  J. Silva-Martinez,et al.  A fully-programmable temperature-compensated analogue circuit for Gaussian functions , 1999, Proceedings of the Third International Workshop on Design of Mixed-Mode Integrated Circuits and Applications (Cat. No.99EX303).

[2]  Davide Anguita,et al.  Feed-Forward Support Vector Machine Without Multipliers , 2006, IEEE Transactions on Neural Networks.

[3]  Paul E. Hasler,et al.  Analog VLSI implementation of support vector machine learning and classification , 2008, 2008 IEEE International Symposium on Circuits and Systems.

[4]  Francesca Bovolo,et al.  A Novel Technique for Subpixel Image Classification Based on Support Vector Machine , 2010, IEEE Transactions on Image Processing.

[5]  Tadashi Shibata,et al.  An On-Chip-Trainable Gaussian-Kernel Analog Support Vector Machine , 2010, IEEE Transactions on Circuits and Systems I: Regular Papers.

[6]  Tadashi Shibata,et al.  Multiple-clue face detection algorithm using edge-based feature vectors , 2004, 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[7]  Jean-Philippe Thiran,et al.  Text identification in complex background using SVM , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[8]  M. Ogawa,et al.  NMOS-based gaussian-element-matching analog associative memory , 2001, Proceedings of the 27th European Solid-State Circuits Conference.

[9]  Tadashi Shibata,et al.  A self-learning multiple-class classifier using multi-dimensional quasi-Gaussian analog circuits , 2010, Proceedings of 2010 IEEE International Symposium on Circuits and Systems.

[10]  Yi Liu,et al.  One-against-all multi-class SVM classification using reliability measures , 2005, Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005..

[11]  Václav Hlavác,et al.  Multi-class support vector machine , 2002, Object recognition supported by user interaction for service robots.