Design and evolution of modular neural network architectures

By Bart L. M. Happel, J. Murre. 1994

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Deep learning in neural networks: An overview (2014, background): “Here several policies are represented by a population of NNs improved throughmutations and/or repeated recombinations of the population’s fittest individuals (e.g., Fogel, Fogel, & Porto, 1990; Happel & Murre, 1994;Maniezzo, 1994;Montana &Davis, 1989; Nolfi, Parisi, & Elman, 1994).”
Born to Learn: the Inspiration, Progress, and Future of Evolved Plastic Artificial Neural Networks (2017, background): “One seminal early study by Happel and Murre (1994) proposed the evolutionary design of modular neural networks in which modules could perform unsupervised learning, and the intermodule connectivity was shaped by Hebbian rules.”
Practical options for selecting data-driven or physics-based prognostics algorithms with reviews (2015, methodology): “In addition to the FFNN and RNN, there are other neural networks, such as fuzzy-neural [41], wavelet [42], associative-memory [43], modular [44] and hybrid [45,46] neural networks.”
Evolutionary and Computational Advantages of Neuromodulated Plasticity (2008, background): “The idea that different neural functions can have a common computation led to the concept of modularity (Happel and Murre, 1994; Gruau, 1994).”
Evolutionary Algorithms for Neural Network Design and Training (1995, background): “Happel and Murre [27] focus on modularity as a basic design principle.”
A phylogenetic, ontogenetic, and epigenetic view of bio-inspired hardware systems (1997, background): “Learning (epigenesis) in biological neural systems can be considered to serve as a mechanism for fine-tuning these broadly laid out neural circuits [ 95 ].”
Phylogeny, Ontogeny, and Epigenesis: Three Sources of Biological Inspiration for Softening Hardware (1996, background): “Learning (epigenesis) in biological neural systems can be considered to serve as a mechanism for fine-tuning these broadly laid out neural circuits [24].”
TOWARDS BIOMIMETIC CONCEPT GENERATION (2001, methodology): “Specifically using neural networks, more powerful computers and computer architectures have been created by studying the structure of neurons in the brain (Happel and Murre 1994).”
SVM and SVM Ensembles in Breast Cancer Prediction (2017, background): “That is, individual functions can be subdivided into functionally different sub-process or subtasks without mutual interference [30].”
Modular Neural Networks and Self-Decomposition (1997, background): “20 Happel, B. and J.M.J Murre (1994).”