A simplified neuron model as a principal component analyzer

DOI10.1007/BF00275687zbMath0488.92012WikidataQ28279493 ScholiaQ28279493MaRDI QIDQ1166458

Publication date: 1982

Published in: Journal of Mathematical Biology (Search for Journal in Brave)

stochastic approximation synaptic plasticity principal component constrained Hebbian-type synaptic modification linear neuron model new class of unconstrained learning rules

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Applications of statistics (62P99) Survival analysis and censored data (62N99) General biology and biomathematics (92B05) Other natural sciences (mathematical treatment) (92F05) Physiological, cellular and medical topics (92Cxx)

Related Items (only showing first 100 items - show all)

Generalized neural networks for spectral analysis: dynamics and Liapunov functions ⋮ Convergence analysis of Oja's iteration for solving online PCA with nonzero-mean samples ⋮ Hebbian errors in learning: an analysis using the Oja model ⋮ A new method to represent speech signals via predefined signature and envelope sequences ⋮ A global competitive neural network ⋮ Hebbian crosstalk and input segregation ⋮ Continuous neural network with windowed Hebbian learning ⋮ Nonlinear differential equations in \({\mathcal{B}(\mathcal{H})}\) motivated by learning models ⋮ Neural networks as set-valued dynamical systems and the universality of the windowed Fourier transform ⋮ Nonlinear data structure extraction using simple hebbian networks ⋮ Convergence analysis of a simple minor component analysis algorithm ⋮ Hold your horses: a dynamic computational role for the subthalamic nucleus in decision making ⋮ Global convergence of Oja's PCA learning algorithm with a non-zero-approaching adaptive learning rate ⋮ A theoretical network model to analyse neurogenesis and synaptogenesis in the dentate gyrus ⋮ Convergence of solutions to equations arising in neural networks ⋮ Dynamics and stochastic resonance in a thermosensitive neuron ⋮ Organization of receptive fields in networks with Hebbian learning: The connection between synaptic and phenomenological models ⋮ Oja's algorithm for graph clustering, Markov spectral decomposition, and risk sensitive control ⋮ Quadrature and the development of orientation selective cortical cells by Hebb rules ⋮ Biologically plausible learning in neural networks with modulatory feedback ⋮ Convergence analysis of the OJAn MCA learning algorithm by the deterministic discrete time method ⋮ On principal subspace analysis ⋮ Connectionist interpretation of the association between cognitive dissonance and attention switching ⋮ Learning transform invariant object recognition in the visual system with multiple stimuli present during training ⋮ Associative Learning Using Ising-Like Model ⋮ A Canonical Neural Circuit for Cortical Nonlinear Operations ⋮ Influence Function Analysis of PCA and BCM Learning ⋮ Map learning with uninterpreted sensors and effectors ⋮ Complex-valued autoencoders ⋮ Convergence analysis of deterministic discrete time system of a unified self-stabilizing algorithm for PCA and MCA ⋮ Continuous attractors of a class of neural networks with a large number of neurons ⋮ Convergence proof of matrix dynamics for online linear discriminant analysis ⋮ Discriminative Bayesian filtering lends momentum to the stochastic Newton method for minimizing log-convex functions ⋮ Self-organized formation of topologically correct feature maps ⋮ Networks that learn the precise timing of event sequences ⋮ Slow feature analysis with spiking neurons and its application to audio stimuli ⋮ Chaoticity generated by a learning model ⋮ Multiple limit cycle bifurcations of the FitzHugh-Nagumo neuronal model ⋮ Cognitive swarming in complex environments with attractor dynamics and oscillatory computing ⋮ A computational model for grid maps in neural populations ⋮ Hot coffee: associative memory with bump attractor cell assemblies of spiking neurons ⋮ A Riemannian derivative-free Polak-Ribiére-Polyak method for tangent vector field ⋮ Widening the scope of an eigenvector stochastic approximation process and application to streaming PCA and related methods ⋮ Generalization in Interactive Networks: The Benefits of Inhibitory Competition and Hebbian Learning ⋮ Phenomenological models of synaptic plasticity based on spike timing ⋮ Computational modelling of memory retention from synapse to behaviour ⋮ Effective Neuronal Learning with Ineffective Hebbian Learning Rules ⋮ Complexity Pursuit: Separating Interesting Components from Time Series ⋮ Stability and chaos of LMSER PCA learning algorithm ⋮ Convergence analysis of Chauvin's PCA learning algorithm with a constant learning rate ⋮ A mathematical justification of the grandmother cell hypothesis in neurobiology ⋮ Robust learning in a partial least-squares neural network ⋮ Global convergence of a PCA learning algorithm with a constant learning rate ⋮ Near-optimal stochastic approximation for online principal component estimation ⋮ Robust hebbian learning and noisy principal component analysis ⋮ Multiscale analysis of slow-fast neuronal learning models with noise ⋮ Emulating biological strategies for uncontrolled face recognition ⋮ Role of Homeostasis in Learning Sparse Representations ⋮ Estimation of degraded composite laminate properties using acoustic wave propagation model and a reduction‐prediction network ⋮ A comparative investigation on subspace dimension determination ⋮ Grassmannian spectral shooting ⋮ Intrinsic Stabilization of Output Rates by Spike-Based Hebbian Learning ⋮ Global analysis of planar neural networks ⋮ Differential equations in spaces of compact operators ⋮ Clustering Based on Conditional Distributions in an Auxiliary Space ⋮ Optimality Model of Unsupervised Spike-Timing-Dependent Plasticity: Synaptic Memory and Weight Distribution ⋮ Isotropic Sequence Order Learning ⋮ The method of proper orthogonal decomposition for dynamical characterization and order reduction of mechanical systems: an overview ⋮ Differential equations in Schatten classes of operators ⋮ The modified natural power method for principal component computation ⋮ The Neuronal Replicator Hypothesis ⋮ A dual purpose principal and minor component flow ⋮ Modelling brain emergent behaviours through coevolution of neural agents ⋮ Dictionary Learning for L1-Exact Sparse Coding ⋮ High-dimensional brain: a tool for encoding and rapid learning of memories by single neurons ⋮ On the Asymptotic Equivalence Between Differential Hebbian and Temporal Difference Learning ⋮ Stability analysis of a neural field self-organizing map ⋮ Design of IIR all-pass filters using a neural-based learning algorithm ⋮ Image compression based on the neural network art ⋮ Emergence of orientation selective simple cells simulated in deterministic and stochastic neural networks ⋮ A Geometric Newton Method for Oja's Vector Field ⋮ Combining stochastic adaptive cubic regularization with negative curvature for nonconvex optimization ⋮ Concentration inequalities for random matrix products ⋮ The application of a two-step AI model to an automated pneumatic drilling process ⋮ Classification and characterization of gene expression data with generalized eigenvalues ⋮ Incremental Slow Feature Analysis: Adaptive Low-Complexity Slow Feature Updating from High-Dimensional Input Streams ⋮ Feedforward neural networks for principal components extraction. ⋮ Two-phase incremental kernel PCA for learning massive or online datasets ⋮ Recognition by Variance: Learning Rules for Spatiotemporal Patterns ⋮ A model of STDP based on spatially and temporally local information: derivation and combination with gated decay ⋮ On an integrable discretization of the Rayleigh quotient gradient system and the power method with a shift ⋮ Object recognition using a neural network with optimal feature extraction. ⋮ Matrix concentration for products ⋮ Unsupervised learning in neural computation. ⋮ A learning rule with generalized Hebbian synapses ⋮ Stabilization of Hebbian neural nets by inhibitory learning ⋮ Image processing with neural networks -- a review ⋮ Dynamical systems that perform the singular value decomposition ⋮ A hybrid stochastic optimization framework for composite nonconvex optimization ⋮ Neurodynamics and nonlinear integrable systems of Lax type

Cites Work

This page was built for publication: A simplified neuron model as a principal component analyzer