On the complexity of learning for spiking neurons with temporal coding.

DOI10.1006/inco.1999.2806zbMath1045.68598OpenAlexW2064003821WikidataQ114961245 ScholiaQ114961245MaRDI QIDQ1854302

Michael Schmitt, Wolfgang Maass

Publication date: 14 January 2003

Published in: Information and Computation (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1006/inco.1999.2806

zbMATH Keywords

computational complexitybiological neural systems

Mathematics Subject Classification ID

Analysis of algorithms and problem complexity (68Q25) Learning and adaptive systems in artificial intelligence (68T05) Neural biology (92C20) Biophysics (92C05)

Related Items

Learning neural connectivity from firing activity: efficient algorithms with provable guarantees on topology ⋮ General-Purpose Computation with Neural Networks: A Survey of Complexity Theoretic Results ⋮ A basic compositional model for spiking neural networks ⋮ Neural Networks with Local Receptive Fields and Superlinear VC Dimension ⋮ Hardware-Amenable Structural Learning for Spike-Based Pattern Classification Using a Simple Model of Active Dendrites ⋮ Event-based simulation of networks with pulse delayed coupling ⋮ On the relevance of time in neural computation and learning ⋮ Investigating the computational power of spiking neurons with non-standard behaviors ⋮ On the Nonlearnability of a Single Spiking Neuron ⋮ On computation with pulses

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Neural networks with quadratic VC dimension
• Decision theoretic generalizations of the PAC model for neural net and other learning applications
• Toward efficient agnostic learning
• Robust trainability of single neurons
• Bounding the Vapnik-Chervonenkis dimension of concept classes parameterized by real numbers
• Fast Sigmoidal Networks via Spiking Neurons
• Learnability and the Vapnik-Chervonenkis dimension
• A theory of the learnable
• Introduction to Theoretical Neurobiology
• Learning Boolean formulas
• Finiteness results for sigmoidal “neural” networks
• Reduction of the Number of Columns in Flow Table Minimization
• Enumeration of Seven-Argument Threshold Functions