Unsupervised Learning -- Local Synaptic Learning Rules Suffice to Maximize Mutual Information in a Linear Network -- Convergent Algorithm for Sensory Receptive Field Development -- Emergence of Position-Independent Detectors of Sense of Rotation and Dilation with Hebbian Learning: An Analysis -- Learning Invariance from Transformation Sequences -- Learning Perceptually Salient Visual Parameters Using Spatiotemporal Smoothness Constraints -- What Is the Goal of Sensory Coding? -- An Information-Maximization Approach to Blind Separation and Blind Deconvolution -- Natural Gradient Works Efficiently in Learning -- A Fast Fixed-Point Algorithm for Independent Component Analysis -- Feature Extraction Using an Unsupervised Neural Network -- Learning Mixture Models of Spatial Coherence -- Bayesian Self-Organization Driven by Prior Probability Distributions -- Finding Minimum Entropy Codes -- Learning Population Codes by Minimizing Description Length -- The Helmholtz Machine -- Factor Analvsis Using Delta-Rule Wake-Sleep Learning -- Dimension Reduction by Local Principal Component Analysis -- A Resource-Allocating Network for Function Interpolation -- Learning with Preknowledge: Clustering with Point and Graph Matching Distance Measures -- Learning to Generalize from Single Examples in the Dynamic Link Architecture.

Since its founding in 1989 by Terrence Sejnowski, Neural Computation has become the leading journal in the field. Foundations of Neural Computation collects, by topic, the most significant papers that have appeared in the journal over the past nine years. This volume of Foundations of Neural Computation, on unsupervised learning algorithms, focuses on neural network learning algorithms that do not require an explicit teacher. The goal of unsupervised learning is to extract an efficient internal representation of the statistical structure implicit in the inputs. These algorithms provide insights into the development of the cerebral cortex and implicit learning in humans. They are also of interest to engineers working in areas such as computer vision and speech recognition who seek efficient representations of raw input data.

Dr. Meera Ramadas