Search Results for author:
Found 6 papers, 0 papers with code
Representation and decomposition of functions in DAG-DNNs and structural network pruning
In the current study, we demonstrate that DAG-DNNs can be used to derive all functions defined on various sub-architectures of the DNN.
Analysis of function approximation and stability of general DNNs in directed acyclic graphs using un-rectifying analysis
In this paper, we made a number of basic assumptions pertaining to activation functions, non-linear transformations, and DNN architectures in order to use the un-rectifying method to analyze DNNs via directed acyclic graphs (DAGs).
Learning DNN networks using un-rectifying ReLU with compressed sensing application
However, we demonstrate that the optimal solution to a combinatorial optimization problem can be preserved by relaxing the discrete domains of activation variables to closed intervals.
Deep Representation with ReLU Neural Networks
We consider deep feedforward neural networks with rectified linear units from a signal processing perspective.
Frame-based Sparse Analysis and Synthesis Signal Representations and Parseval K-SVD
Our findings demonstrate that this type of dual frame cannot be constructed for over-complete frames, thereby precluding the use of any linear analysis operator in driving the sparse synthesis coefficient for signal representation.
Sparse Representation of a Blur Kernel for Blind Image Restoration
Blind image restoration is a non-convex problem which involves restoration of images from an unknown blur kernel.
