The edge-of-chaos dynamics of wide randomly initialized low-rank feedfor...
We investigate properties of neural networks that use both ReLU and x^2 ...
The requirement to repeatedly move large feature maps off- and on-chip d...
Purpose: To develop a tuning-free method for multi-coil compressed sensi...
The activation function deployed in a deep neural network has great infl...
That neural networks may be pruned to high sparsities and retain high
ac...
The ability to train randomly initialised deep neural networks is known ...
We perform a comprehensive study on the performance of derivative free
o...
Expressing a matrix as the sum of a low-rank matrix plus a sparse matrix...
We introduce a novel class of matrices which are defined by the factoriz...
The Approximate Message Passing (AMP) algorithm efficiently reconstructs...
We demonstrate that model-based derivative free optimisation algorithms ...
This paper considers the growth in the length of one-dimensional traject...
For certain sensing matrices, the Approximate Message Passing (AMP) algo...
Snapshot mosaic multispectral imagery acquires an undersampled data cube...
Robust Principal Component Analysis (PCA) (Candes et al., 2011) and low-...
Deep Convolutional Sparse Coding (D-CSC) is a framework reminiscent of d...
We revisit the asymptotic analysis of probabilistic construction of adja...
The convolution of a discrete measure, x=∑_i=1^ka_iδ_t_i, with
a local w...