Trainable and Low-Cost SMO Pattern Classifier Implemented via MCMC and SFBS Technologies

This paper presents a multicore and multichannel (MCMC) technology and a synchronous and forward-backward scheduling (SFBS) for the cost reduction of sequential minimal optimization trainable pattern classifier. The MCMC technology uses multiple processing cores that are self-reconfigurable and preconfigurable. For different functions, five self-configurable modes and four preconfigurable modes can be combined to achieve high flexibility. A multichannel hierarchical architecture enables different transfer rates. To minimize communication cost, the SFBS uses synchronous and forward-backward counting for data scheduling. For implementation in reconfigurable FPGAs, MCMC and SFBS are combined for use in synthesis, placement, and routing. Compared with the baseline design, the emulation results show that the proposed architecture has a low area and low power costs (5755 logic elements and 195 mW), respectively. The experimental results confirm the cost improvement achieved by the proposed architecture and methods.

[1]  Ta-Wen Kuan,et al.  Hardware/software co-design for fast-trainable speaker identification system based on SMO , 2011, 2011 IEEE International Conference on Systems, Man, and Cybernetics.

[2]  J. Durbin.  EFFICIENT ESTIMATION OF PARAMETERS IN MOVING-AVERAGE MODELS , 1959 .

[3]  J. Picone,et al.  Speaker Verification using Support Vector Machines , 2006, Proceedings of the IEEE SoutheastCon 2006.

[4]  Cid C. de Souza,et al.  Efficient datapath merging for partially reconfigurable architectures , 2005, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.

[5]  Cheng-Wen Wu,et al.  Single- and Multi-core Configurable AES Architectures for Flexible Security , 2010, IEEE Transactions on Very Large Scale Integration (VLSI) Systems.

[6]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[7]  Lei Fan,et al.  An incremental learning algorithm for SVM based on voting principle , 2010, 2010 6th International Conference on Advanced Information Management and Service (IMS).

[8]  Ta-Wen Kuan,et al.  REC-STA: Reconfigurable and Efficient Chip Design With SMO-Based Training Accelerator , 2014, IEEE Transactions on Very Large Scale Integration (VLSI) Systems.

[9]  S. Sathiya Keerthi,et al.  Parallel sequential minimal optimization for the training of support vector machines , 2006, IEEE Trans. Neural Networks.

[10]  Shantanu Chakrabartty,et al.  An Energy-Scalable Margin Propagation-Based Analog VLSI Support Vector Machine , 2007, 2007 IEEE International Symposium on Circuits and Systems.

[11]  Ta-Wen Kuan,et al.  VLSI Design of an SVM Learning Core on Sequential Minimal Optimization Algorithm , 2012, IEEE Transactions on Very Large Scale Integration (VLSI) Systems.

[12]  Chin-Teng Lin,et al.  Cost-Effective Triple-Mode Reconfigurable Pipeline FFT/IFFT/2-D DCT Processor , 2008, IEEE Transactions on Very Large Scale Integration (VLSI) Systems.

[13]  Gert Cauwenberghs,et al.  Sub-Microwatt Analog VLSI Support Vector Machine for Pattern Classification and Sequence Estimation , 2004, NIPS.

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

[15]  Sangjin Hong,et al.  Buffer Controller-Based Multiple Processing Element Utilization for Dataflow Synthesis , 2011, IEEE Transactions on Very Large Scale Integration (VLSI) Systems.

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

[17]  Gin-Der Wu,et al.  System-on-Chip Architecture for Speech Recognition , 2010, J. Inf. Sci. Eng..

[18]  Aviral Shrivastava,et al.  Return Data Interleaving for Multi-Channel Embedded CMPs Systems , 2012, IEEE Transactions on Very Large Scale Integration (VLSI) Systems.

[19]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[20]  Jun Guo,et al.  Global Convergence of SMO Algorithm for Support Vector Regression , 2008, IEEE Transactions on Neural Networks.

[21]  Gert Cauwenberghs,et al.  Kerneltron: Support Vector 'Machine' in Silicon , 2002, SVM.

[22]  Vasant Honavar,et al.  Learning Classifiers from Distributional Data , 2013, 2013 IEEE International Congress on Big Data.

[23]  Jhing-Fa Wang,et al.  The design of a speech interactivity embedded module and its applications for mobile consumer devices , 2008, IEEE Transactions on Consumer Electronics.

[24]  David Z. Pan,et al.  UNISM: Unified Scheduling and Mapping for General Networks on Chip , 2012, IEEE Transactions on Very Large Scale Integration (VLSI) Systems.

[25]  Zexin Pan,et al.  Hardware Supported Task Scheduling on Dynamically Reconfigurable SoC Architectures , 2008, IEEE Transactions on Very Large Scale Integration (VLSI) Systems.

[26]  Soo-Won Kim,et al.  A VLSI chip for isolated speech recognition system , 1996 .

[27]  Thorsten Joachims,et al.  Making large-scale support vector machine learning practical , 1999 .

[28]  William M. Campbell,et al.  Speaker Verification Using Support Vector Machines and High-Level Features , 2007, IEEE Transactions on Audio, Speech, and Language Processing.

[29]  S. Chakrabartty,et al.  Sub-Microwatt Analog VLSI Trainable Pattern Classifier , 2007, IEEE Journal of Solid-State Circuits.

[30]  Chang-Hsing Lee,et al.  Continuous Birdsong Recognition Using Gaussian Mixture Modeling of Image Shape Features , 2013, IEEE Transactions on Multimedia.

[31]  Ming-Der Shieh,et al.  A High-Performance Unified-Field Reconfigurable , 2010 .

[32]  Zhiyi Yu,et al.  A Low-Area Multi-Link Interconnect Architecture for GALS Chip Multiprocessors , 2010, IEEE Transactions on Very Large Scale Integration (VLSI) Systems.

[33]  Kiyoung Choi,et al.  Design Space Exploration for Efficient Resource Utilization in Coarse-Grained Reconfigurable Architecture , 2010, IEEE Transactions on Very Large Scale Integration (VLSI) Systems.