Compressing VG-RAM WNN memory for lightweight applications

The Virtual Generalizing Random Access Memory Weightless Neural Network (VG-RAM WNN) is an effective machine learning technique that offers simple implementation and fast training. One disadvantage of VG-RAM WNN, however, is the test time for applications with many training samples, i.e. large multi-class classification applications. In such cases, the test time tends to be high, since it increases with the size of the memory of each neuron. In this paper, we present a new methodology for handling such applications using VG-RAM WNN. By employing data clustering techniques to reduce the overall size of the neurons' memory, we were able to reduce the network's memory footprint and the system's runtime, while maintaining a high and acceptable classification performance. We evaluated the performance of our VG-RAM WNN system with compressed memory on the problem of traffic sign recognition. Our experimental results showed that, after compression, the system was able to run at very fast response times in standard computers. Also, we were able to load and run the system at interactive rates in small low-power systems, experiencing only a small reduction in classification performance.

[1]  I. Aleksander,et al.  WISARD·a radical step forward in image recognition , 1984 .

[2]  Anil K. Jain,et al.  Data clustering: a review , 1999, CSUR.

[3]  Alberto Ferreira de Souza,et al.  Face Recognition with VG-RAM Weightless Neural Networks , 2008, ICANN.

[4]  J. MacQueen.  Some methods for classification and analysis of multivariate observations , 1967 .

[5]  Igor Aleksander,et al.  FROM WISARD TO MAGNUS: A FAMILY OF WEIGHTLESS VIRTUAL NEURAL MACHINES , 1998 .

[6]  John Mark Bishop,et al.  Comparison of some methods for processing Grey Level data in weightless networks , 1998 .

[7]  Alberto Ferreira de Souza,et al.  Improving VG-RAM WNN Multi-label Text Categorization via Label Correlation , 2008, 2008 Eighth International Conference on Intelligent Systems Design and Applications.

[8]  Johannes Stallkamp,et al.  Man vs. computer: Benchmarking machine learning algorithms for traffic sign recognition , 2012, Neural Networks.

[9]  Alberto Ferreira de Souza,et al.  Traffic sign recognition with VG-RAM Weightless Neural Networks , 2012, 2012 12th International Conference on Intelligent Systems Design and Applications (ISDA).

[10]  Lior Rokach,et al.  Data Mining And Knowledge Discovery Handbook , 2005 .

[11]  Edilson de Aguiar,et al.  Traffic sign detection with VG-RAM weightless neural networks , 2013, The 2013 International Joint Conference on Neural Networks (IJCNN).

[12]  Igor Aleksander,et al.  Self-adaptive universal logic circuits , 1966 .

[13]  Rui Xu,et al.  Survey of clustering algorithms , 2005, IEEE Transactions on Neural Networks.

[14]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[15]  Johannes Stallkamp,et al.  The German Traffic Sign Recognition Benchmark: A multi-class classification competition , 2011, The 2011 International Joint Conference on Neural Networks.

[16]  Claudine Badue,et al.  VG-RAM Weightless Neural Networks for Face Recognition , 2010 .

[17]  Claudine Badue,et al.  CONTROL BASED ON VG-RAM WEIGHTLESS NEURAL NETWORKS , 2011 .

[18]  W. Marsden.  I and J , 2012 .

[19]  Lior Rokach,et al.  A survey of Clustering Algorithms , 2010, Data Mining and Knowledge Discovery Handbook.

[20]  Alberto Ferreira de Souza,et al.  Automated multi-label text categorization with VG-RAM weightless neural networks , 2009, Neurocomputing.