https://www2.econ.iastate.edu/tesfatsi/DeepLearningInNeuralNetworksOverview.JSchmidhuber2015.pdf

Deep learning in neural networks

Cascade-Correlation is a new architecture and supervised learning algorithm for artificial neural networks. Instead of just adjusting the weights in a network of fixed topology. Cascade-Correlation begins with a minimal network, then automatically trains and adds new hidden units one by one, creating a multi-layer structure. Once a new hidden unit has been added to the network, its input-side weights are frozen. This unit then becomes a permanent feature-detector in the network, available for producing outputs or for creating other, more complex feature detectors. The Cascade-Correlation architecture has several advantages over existing algorithms: it learns very quickly, the network determines its own size and topology, it retains the structures it has built even if the training set changes, and it requires no back-propagation of error signals through the connections of the network.

/pdf/the-cascade-correlation-learning-architecture-i72409omez.pdf

The Cascade-Correlation Learning Architecture

Introduction to neural networks.

https://crl.ucsd.edu/%7Eelman/Papers/elman_cognition1993.pdf

Learning and development in neural networks: the importance of starting small

Publisher Summary This chapter presents a survey of the elementary theory of the basic backpropagation neural network architecture, covering the areas of architectural design, performance measurement, function approximation capability, and learning. The survey includes a formulation of the backpropagation neural network architecture to make it a valid neural network and a proof that the backpropagation mean squared error function exists and is differentiable. Also included in the survey is a theorem showing that any L2 function can be implemented to any desired degree of accuracy with a three-layer backpropagation neural network. An appendix presents a speculative neurophysiological model illustrating the way in which the backpropagation neural network architecture might plausibly be implemented in the mammalian brain for corticocortical learning between nearby regions of cerebral cortex. One of the crucial decisions in the design of the backpropagation architecture is the selection of a sigmoidal activation function.

Theory of the backpropagation neural network

This paper introduces a new method called Dynamic Node Creation (DNC) which automatically grows BP networks until the target problem is solved. DNC sequentially adds nodes one at a time to the hidden layer(s) of the network until the desired approximation accuracy is achieved. Simulation results for parity, symmetry, binary addition, and the encoder problem are presented. The procedure was capable of finding known minimal topologies in many cases, and was always within three nodes of the minimum. Computational expense for finding the solutions was comparable to training normal BP networks with the same final topologies. Starting out with fewer nodes than needed to solve the problem actually seems to help find a solution. The method yielded a solution for every problem tried.

Timur Ash

Papers

Dynamic Node Creation in Backpropagation Networks