The Hebbian-LMS Learning Algorithm

Hebbian learning is widely accepted in the fields of psychology, neurology, and neurobiology. It is one of the fundamental premises of neuroscience. The LMS (least mean square) algorithm of Widrow and Hoff is the world's most widely used adaptive algorithm, fundamental in the fields of signal processing, control systems, pattern recognition, and artificial neural networks. These are very different learning paradigms. Hebbian learning is unsupervised. LMS learning is supervised. However, a form of LMS can be constructed to perform unsupervised learning and, as such, LMS can be used in a natural way to implement Hebbian learning. Combining the two paradigms creates a new unsupervised learning algorithm that has practical engineering applications and provides insight into learning in living neural networks. A fundamental question is, how does learning take place in living neural networks? "Nature's little secret," the learning algorithm practiced by nature at the neuron and synapse level, may well be the Hebbian-LMS algorithm.

[1]  H. Sompolinsky,et al.  Chaos in Neuronal Networks with Balanced Excitatory and Inhibitory Activity , 1996, Science.

[2]  R. W. Lucky,et al.  Techniques for adaptive equalization of digital communication systems , 1966 .

[3]  S. Thomas Alexander,et al.  Adaptive Signal Processing , 1986, Texts and Monographs in Computer Science.

[4]  Jürgen Schmidhuber,et al.  Incremental Slow Feature Analysis: Adaptive Low-Complexity Slow Feature Updating from High-Dimensional Input Streams , 2012, Neural Computation.

[5]  J. A. Hartigan,et al.  A k-means clustering algorithm , 1979 .

[6]  Amir Hussain,et al.  Novel Biologically Inspired Approaches to Extracting Online Information from Temporal Data , 2014, Cognitive Computation.

[7]  S. Nelson,et al.  Hebb and homeostasis in neuronal plasticity , 2000, Current Opinion in Neurobiology.

[8]  A. Hall,et al.  Adaptive Switching Circuits , 2016 .

[9]  G. Bi,et al.  Synaptic Modifications in Cultured Hippocampal Neurons: Dependence on Spike Timing, Synaptic Strength, and Postsynaptic Cell Type , 1998, The Journal of Neuroscience.

[10]  Hans-Peter Kriegel,et al.  A Density-Based Algorithm for Discovering Clusters in Large Spatial Databases with Noise , 1996, KDD.

[11]  G. Turrigiano The Self-Tuning Neuron: Synaptic Scaling of Excitatory Synapses , 2008, Cell.

[12]  L. Abbott,et al.  Competitive Hebbian learning through spike-timing-dependent synaptic plasticity , 2000, Nature Neuroscience.

[13]  E. Capaldi,et al.  The organization of behavior. , 1992, Journal of applied behavior analysis.

[14]  R K Powers,et al.  Amplification and linear summation of synaptic effects on motoneuron firing rate. , 2001, Journal of neurophysiology.

[15]  Yoonsuck Choe Anti-Hebbian Learning , 2014, Encyclopedia of Computational Neuroscience.

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

[17]  G. Bi,et al.  Synaptic modification by correlated activity: Hebb's postulate revisited. , 2001, Annual review of neuroscience.

[18]  R. Malenka,et al.  NMDA receptor-dependent long-term potentiation and long-term depression (LTP/LTD). , 2012, Cold Spring Harbor perspectives in biology.

[19]  R. Malenka,et al.  Synaptic scaling mediated by glial TNF-α , 2006, Nature.

[20]  New York Dover,et al.  ON THE CONVERGENCE PROPERTIES OF THE EM ALGORITHM , 1983 .

[21]  Y. Goda,et al.  The interplay between Hebbian and homeostatic synaptic plasticity , 2013, The Journal of cell biology.

[22]  J. Cowan,et al.  Excitatory and inhibitory interactions in localized populations of model neurons. , 1972, Biophysical journal.

[23]  B. Widrow,et al.  "Cognitive" memory , 2013, Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005..

[24]  Niraj S. Desai,et al.  Activity-dependent scaling of quantal amplitude in neocortical neurons , 1998, Nature.

[25]  F. K. Becker,et al.  Automatic equalization for digital communication , 1965 .

[26]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[27]  T. Teyler Long-term potentiation and memory. , 1987, International journal of neurology.

[28]  Bernard Widrow,et al.  The No-Prop algorithm: A new learning algorithm for multilayer neural networks , 2013, Neural Networks.