Compressive sensing with un-trained neural networks: Gradient descent finds the smoothest approximation.
Reinhard HeckelMahdi SoltanolkotabiPublished in: CoRR (2020)
Keyphrases
- compressive sensing
- trained neural networks
- neural network
- random projections
- sparse representation
- neural learning
- compressive sampling
- artificial neural networks
- rule extraction
- image representation
- signal processing
- trained neural network
- orthogonal matching pursuit
- neural network model
- linguistic rules
- multiscale
- feature selection
- computer vision
- machine learning