Short-Term Memory Capacity in Networks via the Restricted Isometry Property
From MaRDI portal
Publication:5383776
DOI10.1162/NECO_a_00590zbMath1416.92006arXiv1307.7970OpenAlexW2159213043WikidataQ50673926 ScholiaQ50673926MaRDI QIDQ5383776
Han Lun Yap, Adam S. Charles, Christopher J. Rozell
Publication date: 20 June 2019
Published in: Neural Computation (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1307.7970
Neural networks for/in biological studies, artificial life and related topics (92B20) Memory and learning in psychology (91E40)
Related Items
A Theory of Sequence Indexing and Working Memory in Recurrent Neural Networks ⋮ Memory and forecasting capacities of nonlinear recurrent networks
Uses Software
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- The restricted isometry property for random block diagonal matrices
- Internal representations for associative memory
- Templates for convex cone problems with applications to sparse signal recovery
- Memory in linear recurrent neural networks in continuous time
- Edge of chaos and prediction of computational performance for neural circuit models
- A Network of Spiking Neurons for Computing Sparse Representations in an Energy-Efficient Way
- Design Strategies for Weight Matrices of Echo State Networks
- Suprema of Chaos Processes and the Restricted Isometry Property
- On sparse reconstruction from Fourier and Gaussian measurements
- Robust uncertainty principles: exact signal reconstruction from highly incomplete frequency information
- Near-Optimal Signal Recovery From Random Projections: Universal Encoding Strategies?
- Connectivity, Dynamics, and Memory in Reservoir Computing with Binary and Analog Neurons
- On the Eigenvalues of Random Matrices
- Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on Perturbations
- Concentration of Measure for Block Diagonal Matrices With Applications to Compressive Signal Processing
- Beyond Nyquist: Efficient Sampling of Sparse Bandlimited Signals
- Toeplitz Compressed Sensing Matrices With Applications to Sparse Channel Estimation
- Randomly Connected Networks Have Short Temporal Memory
- Sparse nonnegative solution of underdetermined linear equations by linear programming
- On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities
