Information theory and recovery algorithms for data fusion in Earth observation

DOI10.1007/978-3-031-09745-4_14OpenAlexW4313021077MaRDI QIDQ2106495

Publication date: 14 December 2022

Full work available at URL: https://doi.org/10.1007/978-3-031-09745-4_14

Signal theory (characterization, reconstruction, filtering, etc.) (94A12) Communication theory (94A05) Artificial intelligence (68Txx) Theory of data (68Pxx)

Cites Work

Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers
Learning functions of few arbitrary linear parameters in high dimensions
User-friendly tail bounds for sums of random matrices
Iterative thresholding algorithms
On the complexity of loading shallow neural networks
Reconstructing a neural net from its output
Stable recovery of entangled weights: towards robust identification of deep neural networks from minimal samples
DNN expression rate analysis of high-dimensional PDEs: application to option pricing
Nonlinear approximation and (deep) ReLU networks
Robust and resource-efficient identification of two hidden layer neural networks
Affine symmetries and neural network identifiability
Robust 1-Bit Compressive Sensing via Binary Stable Embeddings of Sparse Vectors
Rate Distortion Behavior of Sparse Sources
Recovery Algorithms for Vector-Valued Data with Joint Sparsity Constraints
Message-Passing De-Quantization With Applications to Compressed Sensing
Fast Fusion of Multi-Band Images Based on Solving a Sylvester Equation
Hyperspectral Image Super-Resolution via Non-Negative Structured Sparse Representation
Blind Hyperspectral Unmixing Using an Extended Linear Mixing Model to Address Spectral Variability
Fusing Hyperspectral and Multispectral Images via Coupled Sparse Tensor Factorization
Hyperspectral Unmixing With Spectral Variability Using a Perturbed Linear Mixing Model
Hyperspectral Super-Resolution: A Coupled Tensor Factorization Approach
On the importance of combining wavelet-based nonlinear approximation with coding strategies
Memory Capacity of Neural Networks with Threshold and Rectified Linear Unit Activations
Learning deep linear neural networks: Riemannian gradient flows and convergence to global minimizers
Robust and resource efficient identification of shallow neural networks by fewest samples
State evolution for general approximate message passing algorithms, with applications to spatial coupling
Optimal Injectivity Conditions for Bilinear Inverse Problems with Applications to Identifiability of Deconvolution Problems
Neural network approximation

This page was built for publication: Information theory and recovery algorithms for data fusion in Earth observation