In this paper abstractions of neurodevelopmental mechanisms of biological nervous systems are interpreted as changes in the structure, learning parameters and input data of artificial neural networks. A review of neurodevelopmental mechanisms reveals that structural changes follow a typical timeline. We propose it as part of an algorithmic model of neurodevelopment and early learning. We further discuss the concept of incremental learning in artificial neural networks. We conclude that incremental learning can currently only model a small part of neurodevelopment in biology. Neurodevelopment should be modeled in the context of evolution.
|
4962
|
The Nature of Statistical Learning Theory
– Vapnik
- 1998
|
|
1473
|
Introduction to the theory of neural computation
– Hertz, Krogh, et al.
- 1991
|
|
582
|
The cascade-correlation learning architecture
– Fahlman, Lebiere
- 1990
|
|
526
|
Neural networks and the bias/variance dilemma
– Geman, Bienenstock, et al.
- 1992
|
|
402
|
A direct adaptive method for faster backpropagation learning: The RPROP algorithm
– Riedmiller, Braun
- 1993
|
|
242
|
Learning and development in neural networks: The importance of starting small
– Elman
- 1993
|
|
234
|
Evolving artificial neural networks
– Yao
- 1999
|
|
209
|
Growing cell structures - a self-organizing network for unsupervised and supervised learning
– Fritzke
- 1994
|
|
159
|
Pruning algorithms - a survey
– Reed
- 1993
|
|
156
|
The Organization of Behaviour
– Hebb
- 1949
|
|
135
|
A resource-allocating network for function interpolation
– Platt
- 1991
|
|
124
|
The Handbook of Brain Theory and Neural Networks
– Arbib
- 1995
|
|
87
|
The neural basis of cognitive development: A constructivist manifesto
– Quartz, Sejnowski
- 1997
|
|
83
|
Maturational constraints on language learning
– Newport
- 1990
|
|
74
|
Perceptron-Based Learning Algorithms
– Gallant
- 1990
|
|
64
|
Advanced supervised learning in multi-layer perceptrons - from backpropagation to adaptive learning algorithms
– Riedmiller
- 1994
|
|
51
|
The Cognitive Neurosciences
– Gazzaniga
- 1995
|
|
51
|
Competitive Hebbian Learning Rule Forms Perfectly Topology Preserving Maps
– Martinetz
- 1993
|
|
47
|
Language acquisition in the absence of explicit negative evidence: How important is starting small
– Rohde, Plaut
- 1999
|
|
36
|
The Vapnik-Chervonenkis dimension: information versus complexity in learning
– Abu-Mostafa
- 1989
|
|
33
|
Fast Learning with Incremental RBF Networks
– Fritzke
- 1994
|
|
26
|
Notes on the Simulation of Evolution
– Atmar
- 1994
|
|
20
|
Discrete Recurrent Neural Networks for Grammatical Inference
– Zeng, Goodman, et al.
- 1994
|
|
15
|
The replacement of general-purpose learning models with adaptively specialized learning modules
– Gallistel
- 2000
|
|
14
|
Investigation of the CasCor Family of Learning Algorithms
– Prechelt
- 1997
|
|
13
|
The evolution of incremental learning: language, development and critical periods
– Hurford, Kirby
- 1997
|
|
11
|
Concurrent overproduction of synapses in diverse regions of the primate cerebral cortex
– Rakic, Bourgeois, et al.
- 1986
|
|
7
|
An empirical study of learning speed in back-propagation networks
– Fahlmann
- 1988
|
|
6
|
An incremental learning algorithm that optimizes network size and sample size in one trial
– Zhang
- 1994
|
|
5
|
Courten. The development of synapses in striate cortex of man
– Huttenlocher, De
- 1987
|
|
4
|
New algorithms for feedforward networks
– Nadal
- 1989
|
|
4
|
Limits of Neurogenesis in Primates
– Rakic
- 1985
|
|
4
|
Corticogenesis in human and nonhuman primates
– Rakic
- 1995
|
|
3
|
Structural change and development in real and artificial neural networks
– Quinlan
- 1998
|
|
2
|
Rule extraction from artificial neural networks trained on elementary number classification tasks
– Chalup, Hayward, et al.
- 1998
|
|
2
|
First order recurrent neural networks learn to predict a mildly context-sensitive lan
– Chalup, Blair
- 2000
|
|
2
|
Axon overproduction and elimination in the corpus callosum of the developing rhesus monkey
– LaMantia, Rakic
- 1990
|
|
1
|
Ontogenie des Nervensystems und der Sinnesorgane
– Campos-Ortega
- 1996
|
|
1
|
Analytic and Inductive Learning in an Efficient Connectionist Rule-based Reasoning System
– Hayward
- 2000
|
|
1
|
Axon overproduction and elimination in the anterior commissure of the developing rhesus monkey
– LaMantia, Rakic
- 1994
|
|
1
|
Scheduling of monoamineric neurotransmitter receptor expression in the primate neocortex during postnatal development
– Lidow, Rakic
- 1992
|
|
1
|
Setting the Stage for Cognition: Genesis of the Primate
– Rakic
|
|
1
|
comp.ai.neural-nets faq: Learning. posted in: comp.ai.neural-nets
– Sarle
- 1999
|
