Memory Capacities for Synaptic and Structural Plasticity
From MaRDI portal
Publication:5189861
DOI10.1162/neco.2009.08-07-588zbMath1183.92017OpenAlexW2126076951WikidataQ37635148 ScholiaQ37635148MaRDI QIDQ5189861
Andreas Knoblauch, Friedrich T. Sommer, Günther Palm
Publication date: 11 March 2010
Published in: Neural Computation (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1162/neco.2009.08-07-588
Related Items (13)
GXNOR-Net: training deep neural networks with ternary weights and activations without full-precision memory under a unified discretization framework ⋮ Learning hierarchically-structured concepts ⋮ Growth strategy determines the memory and structural properties of brain networks ⋮ Binary Willshaw learning yields high synaptic capacity for long-term familiarity memory ⋮ Estimation of vectors similarity by their randomized binary projections ⋮ Storing structured sparse memories in a multi-modular cortical network model ⋮ Storing Object-Dependent Sparse Codes in a Willshaw Associative Network ⋮ Iterative Retrieval and Block Coding in Autoassociative and Heteroassociative Memory ⋮ Efficient Associative Computation with Discrete Synapses ⋮ Multiassociative Memory: Recurrent Synapses Increase Storage Capacity ⋮ Integer sparse distributed memory: analysis and results ⋮ Neural Associative Memory with Optimal Bayesian Learning ⋮ Spike-Based Winner-Take-All Computation: Fundamental Limits and Order-Optimal Circuits
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Neural associative memory for brain modeling and information retrieval
- On associative memory
- Optimising synaptic learning rules in linear associative memories
- Improving recall from an associative memory
- The existence of persistent states in the brain
- Binding and Normalization of Binary Sparse Distributed Representations by Context-Dependent Thinning
- Die Lernmatrix
- Neural Associative Memory and the Willshaw–Palm Probability Distribution
- A model of cortical associative memory based on a horizontal network of connected columns
- Informational characteristics of neural networks capable of associative learning based on Hebbian plasticity
- Memory Capacity of Balanced Networks
- Computing and Stability in Cortical Networks
- What determines the capacity of autoassociative memories in the brain?
- Neural networks and physical systems with emergent collective computational abilities.
- Neurons with graded response have collective computational properties like those of two-state neurons.
- Run-length encodings (Corresp.)
- Associative memory: on the (puzzling) sparse coding limit
This page was built for publication: Memory Capacities for Synaptic and Structural Plasticity
