• Publications
  • Influence
Early experiments with neural diversity machines
  • T. Maul
  • Computer Science
  • Neurocomputing
  • 1 August 2013
TLDR
The current paper introduces the concept of neural diversity machines (NDM) which, refers to hybrid artificial neural networks (HANN) with conditions on the minimum number of functions available to the network, amongst several other properties. Expand
  • 9
  • 4
  • PDF
A parallel circuit approach for improving the speed and generalization properties of neural networks
TLDR
We propose a simple parallel design inspired by the parallel circuits found in the human retina to reduce training time of neural networks. Expand
  • 6
  • 2
  • PDF
Local receptive field constrained deep networks
TLDR
Novel biologically inspired deep network models (LRF-DBN and LRF-DNN) with features of gradually increasing size. Expand
  • 15
  • 1
  • PDF
A review of modularization techniques in artificial neural networks
TLDR
We investigate the different levels at which modularization techniques act on MNNs and propose a taxonomy that captures the essential properties and relationships of the different variants of MNN. Expand
  • 14
  • 1
  • PDF
DropCircuit : A Modular Regularizer for Parallel Circuit Networks
TLDR
We propose Parallel Circuits (PCs), a biologically inspired architecture based on the design of the retina, to solve the problem of lengthy training times. Expand
  • 3
  • 1
Improving Neural Network Generalization by Combining Parallel Circuits with Dropout
TLDR
In an attempt to solve the lengthy training times of neural networks, we proposed Parallel Circuits (PCs), a biologically inspired architecture. Expand
  • 3
  • 1
  • PDF
An Empirical Study on Improving the Speed and Generalization of Neural Networks Using a Parallel Circuit Approach
TLDR
In this paper we consider an algorithmic approach to speeding up the training time of neural networks, proposing a simple parallel design which is inspired by the parallel circuits found in the human retina. Expand
  • 3
  • 1
Path Capsule Networks
TLDR
Capsule network (CapsNet) was introduced as an enhancement over convolutional neural networks, supplementing the latter’s invariance properties with equivariance. Expand
  • 10
  • PDF
a Review of Retinal Prosthesis Approaches
Age-related macular degeneration and retinitis pigmentosa are two of the most common diseases that cause degeneration in the outer retina, which can lead to several visual impairments up toExpand
  • 13
  • PDF
Towards Evolutionary Deep Neural Networks
TLDR
This paper is concerned with the problem of optimizing deep neural networks with diverse transfer functions using evolutionary methods. Expand
  • 10
  • PDF
...
1
2
3
4
5
...