A novel generative encoding for exploiting neural network sensor and output geometry

By David B. D'Ambrosio, Kenneth O. Stanley. 2007

98 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Electrical and Electronic Engineering, Mechanical Engineering

How researchers see this paper

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

In Artificial Intelligence

In Electrical and Electronic Engineering

In Mechanical Engineering

Citations in the corpus

Deep learning in neural networks: An overview (2014, neutral): “Instead of evolving large NNs directly (Section 6.6), one can sometimes greatly reduce the search space by evolving compact encodings of NNs, e.g., through Lindenmeyer Systems (Jacob, Lindenmayer, & Rozenberg, 1994; Lindenmayer, 1968), graph rewriting (Kitano, 1990), Cellular Encoding (Gruau, Whitle”
A unified approach to evolving plasticity and neural geometry (2012, methodology): “neural topology) [12, 30, 35], the Hypercube-based NeuroEvolution of Augmenting Topologies (HyperNEAT) method [8, 13, 32] provided a new perspective on evolving ANNs by showing that the pattern of weights across the connectivity of an ANN can be generated as a function of its geometry.”
Guided self-organization in indirectly encoded and evolving topographic maps (2014, unknown): “Copyright 2014 ACM 978-1-4503-2662-9/14/07 ...$15.00. http://dx.doi.org/10.1145/2576768.2598369.”
Ieee Transactions on Evolutionary Computation on the Performance of Indirect Encoding across the Continuum of Regularity (unknown): “Many prior studies have shown that indirect encodings often outperform direct encodings [2], [7]–[14].”
Evolving deep unsupervised convolutional networks for vision-based reinforcement learning (2014, background): “Most approaches to scaling neuroevolution to tasks that require large networks, such as those processing video input, have focused on indirect encodings where relatively small neural network descriptions are transformed via a complex mapping into networks of arbitrary size [4, 7, 10, 12, 14, 21].”
Evolving large-scale neural networks for vision-based reinforcement learning (2013, background): “Further experiments are needed to compare the approach with other indirect or generative encodings such as HyperNEAT [2]; not only to evaluate the relative efficiency of each algorithm, but also to understand how the methods differ in the type of solutions they produce.”
Policy Optimization by Genetic Distillation (2017, methodology): “HyperNEAT (D’Ambrosio & Stanley, 2007), which extends on NEAT and uses CPPN-based indirect encoding, has been used to learn to play Atari games from raw game pixels (Hausknecht et al., 2014).”
Online Evolution of Deep Convolutional Network for Vision-Based Reinforcement Learning (2014, background): “Most approaches to scaling neuroevolution to tasks that require large networks, such as those processing video input, have focused on indirect encodings where relatively small neural network descriptions are transformed via a complex mapping into networks of arbitrary size [4, 7, 10,13,15,23].”
Evolving large-scale neural networks for vision-based TORCS (2013, methodology): “Therefore, recent efforts have focused on indirect encodings [1, 4, 5, 13] where relatively small genomes are transformed into networks of arbitrary size using a more complex mapping.”