Dennis Wilson

Cloud scale distributed evolutionary strategies for high dimensional problems

We develop and evaluate a cloud scale distributed covariance matrix adaptation based evolutionary strategy for problems with dimensions as high as 400. We adopt an island based distribution model and rely on a peer-to-peer communication protocol. We identify a variety of parameters in a distributed island model that could be randomized leading to a new dynamic migration protocol that can prove advantageous when computing on the cloud. Our approach enables efficient and high quality distributed sampling while mitigating the latencies and failure risks associated with running on a cloud. We evaluate performance on a real world problem from the domain of wind energy: wind farm turbine layout optimization.

The Evolution of Artificial Neurogenesis

Evolutionary development as a strategy for the design of artificial neural networks is an enticing idea, with possible inspiration from both biology and existing indirect representations. A growing neural network can not only optimize towards a specific goal, but can also exhibit plasticity and regeneration. Furthermore, a generative system trained in the optimization of the resultant neural network in a reinforcement learning environment has the capability of on-line learning after evolution in any reward-driven environment. In this abstract, we outline the motivation for and design of a generative system for artificial neural network design.

Workshops at PPSN 2018

This article provides an overview of the 6 workshops held in conjunction with PPSN 2018 in Coimbra, Portugal. For each workshop, we list title, organizers, aim and scope as well as the accepted contributions.

First Workshop on Developmental Neural Networks

In nature, brains are built through a process of biological development in which many aspects of the network of neurons and connections change are shaped by external information received through sensory organs. Biological development mechanisms such as axon guidance and dendrite pruning have been shown to rely on neural activity. Despite this, most artificial neural network (ANN) models do not include developmental mechanisms and regard learning as the adjustment of connection weights, while some that do use development restrain it to a period before the ANN is used. It is worthwhile to understand the cognitive functions offered by development and to investigate the fundamental questions raised by artificial neural development. In this workshop, we will explore existing and future approaches that aim to incorporate development into ANNs. Invited speakers will present their work with neural networks, both artificial and biological, in the context of development. Accepted submissions on contemporary work in this field will be presented and we will hold an open discussion on the topic.

A comparison of genetic regulatory network dynamics and encoding

Genetic Regulatory Networks (GRNs) implementations have a high degree of variability in their details. Parameters, encoding methods, and dynamics formulas all differ in the literature, and some GRN implementations have a high degree of model complexity. In this paper, we present a comparative study of different implementations of a GRN and introduce new variants for comparison. We use a modified Genetic Algorithm (GA) to evaluate GRN performance on a number of common benchmark tasks, with a focus on real-time control problems. We propose an encoding scheme and set of dynamics equations that simplifies implementation and evaluate the evolutionary fitness of this proposed method. Lastly, we use the comparative modifications study to demonstrate overall enhancements for GRN models.

A developmental artificial neural network model for solving multiple problems

A developmental model of an artificial neuron is presented. In this model, a pair of neural developmental programs develop an entire artificial neural network of arbitrary size. The pair of neural chromosomes are evolved using Cartesian Genetic Programming. During development, neurons and their connections can move, change, die or be created. We show that this two-chromosome genotype can be evolved to develop into a single neural network from which multiple conventional artificial neural networks can be extracted. The extracted conventional ANNs share some neurons across tasks. We have evaluated the performance of this method on three standard classification problems. The evolved pair of neuron programs can generate artificial neural networks that perform reasonably well on all three benchmark problems simultaneously. It appears to be the first attempt to solve multiple standard classification problems using a developmental approach.

Learning aquatic locomotion with animats.

One of the challenges of researching spiking neural networks (SNN) is translation from temporal spiking behavior to classic controller output. While many encoding schemes exist to facilitate this translation, there are few benchmarks for neural networks that inherently utilize a temporal controller. In this work, we consider the common reinforcement problem of animat locomotion in an environment suited for evaluating SNNs. Using this problem, we explore novel methods of reward distribution as they impacts learning. Hebbian learning, in the form of spike time dependent plasticity (STDP), is modulated by a dopamine signal and affected by reward-induced neural activity. Different reward strategies are parameterized and the Covariance Matrix Adaptation Evolution Strategy (CMA-ES) is used to find the best strategies for fixed animat morphologies. The contribution of this work is two-fold: to cast the problem of animat locomotion in a form directly applicable to simple temporal controllers, and to demonstrate n...

The ethics of automated behavioral microtargeting

One day AM woke up and knew who he was, and he linked himself, and he began feeding all the killing data, until everyone was dead, except for the five of us, and AM brought us down here. <i>I</i> was the only one still sane and whole. <i>Really!</i> AM had not tampered with my mind. <i>Not at all.</i> <i>I Have No Mouth and I Must Scream</i> <b>Ellison</b> (<b>1967</b>)