Gerard David Howard

Evolution of Plastic Learning in Spiking Networks via Memristive Connections

This paper presents a spiking neuroevolutionary system which implements memristors as plastic connections, i.e., whose weights can vary during a trial. The evolutionary design process exploits parameter self-adaptation and variable topologies, allowing the number of neurons, connection weights, and interneural connectivity pattern to emerge. By comparing two phenomenological real-world memristor implementations with networks comprised of: 1) linear resistors, and 2) constant-valued connections, we demonstrate that this approach allows the evolution of networks of appropriate complexity to emerge whilst exploiting the memristive properties of the connections to reduce learning time. We extend this approach to allow for heterogeneous mixtures of memristors within the networks; our approach provides an in-depth analysis of network structure. Our networks are evaluated on simulated robotic navigation tasks; results demonstrate that memristive plasticity enables higher performance than constant-weighted connections in both static and dynamic reward scenarios, and that mixtures of memristive elements provide performance advantages when compared to homogeneous memristive networks.

ORGANIC MEMRISTOR DEVICES FOR LOGIC ELEMENTS WITH MEMORY

Memristors are promising next-generation memory candidates that are nonvolatile, possess low power requirements and are capable of nanoscale fabrication. In this article we physically realise and describe the use of organic memristors in designing statefull boolean logic gates for the AND OR and NOT operations. The output of these gates is analog and dependent on the length of time that suitable charge is applied to the inputs, displaying a learning property. Results may be also interpreted in a traditional binary manner through use of a suitable thresholding function at the output. The memristive property of the gate allows the for the production of analog outputs that vary based on the charge-dependent nonvolatile state of the memristor. We provide experimental results of physical fabrication of three types of logic gate. A simulation of a one-bit full adder comprised of memristive logic gates is also included, displaying varying response to two distinct input patterns.

Towards evolving spiking networks with memristive synapses

This paper presents a spiking neuro-evolutionary system which implements memristors as neuromodulatory connections, i.e. whose weights can vary during a trial. The evolutionary design process exploits parameter self-adaptation and a constructionist approach, allowing the number of neurons, connection weights, and inter-neural connectivity pattern to be evolved for each network. We demonstrate that this approach allows the evolution of networks of appropriate complexity to emerge whilst exploiting the memristive properties of the connections to reduce learning time. We evaluate two phenomenological real-world memristive implementations against a theoretical “linear memristor”, and a system containing standard connections only. Our networks are evaluated on a simulated robotic navigation task.

Self-adaptive constructivism in Neural XCS and XCSF

For artificial entities to achieve high degrees of autonomy they will need to display appropriate adaptability. In this sense adaptability includes representational flexibility guided by the environment at any given time. This paper presents the use of constructivism-inspired mechanisms within a neural learning classifier system which exploits parameter self-adaptation as an approach to realize such behaviour. The system uses a rule structure in which each is represented by an artificial neural network. It is shown that appropriate internal rule complexity emerges during learning at a rate controlled by the system. Further, the use of computed predictions is shown possible.

A spiking neural representation for XCSF

This paper presents a Learning Classifier System (LCS) where each traditional rule is represented by a spiking neural network, a type of network with dynamic internal state. The evolutionary design process exploits parameter self-adaptation and a constructionist approach, providing the system with a flexible knowledge representation. It is shown how this approach allows for the evolution of networks of appropriate complexity to emerge whilst solving a continuous maze environment. Additionally, we extend the system to allow for temporal state decomposition. We evaluate our spiking neural LCS against one that uses Multi Layer Perceptron rules.

Towards continuous actions in continuous space and time using self-adaptive constructivism in neural XCSF

This paper presents a Learning Classifier System (LCS) where each classifier condition is represented by a feed-forward multi-layered perceptron (MLP) network. Adaptive behavior is realized through the use of self-adaptive parameters and neural constructivism, providing the system with a flexible knowledge representation. The approach allows for the evolution of networks of appropriate complexity to solve a continuous maze environment, here using either discrete-valued actions, continuous-valued actions, or continuous-valued actions of continuous duration. In each case, it is shown that the neural LCS employed is capable of developing optimal solutions to the reinforcement learning task presented in this paper.

Evolving spiking networks with variable resistive memories

Neuromorphic computing is a brainlike information processing paradigm that requires adaptive learning mechanisms. A spiking neuro-evolutionary system is used for this purpose; plastic resistive memories are implemented as synapses in spiking neural networks. The evolutionary design process exploits parameter self-adaptation and allows the topology and synaptic weights to be evolved for each network in an autonomous manner. Variable resistive memories are the focus of this research; each synapse has its own conductance profile which modifies the plastic behaviour of the device and may be altered during evolution. These variable resistive networks are evaluated on a noisy robotic dynamic-reward scenario against two static resistive memories and a system containing standard connections only. The results indicate that the extra behavioural degrees of freedom available to the networks incorporating variable resistive memories enable them to outperform the comparative synapse types.

On the effects of node duplication and connection-oriented constructivism in neural XCSF

For artificial entities to achieve high degrees of autonomy they will need to display appropriate adaptability. In this sense adaptability includes representational flexibility guided by the environment at any given time. This paper presents the use of constructivism-inspired mechanisms within a neural learning classifier system which exploits parameter self-adaptation as an approach to realize such behavior. Various network growth/regression mechanisms are implemented and their performances compared. The system uses a rule structure in which each is represented by an artificial neural network. It is shown that appropriate internal rule complexity emerges during learning at a rate controlled by the system.

A SPICE MODEL OF THE PEO-PANI MEMRISTOR

The memristor is a novel circuit element which is capable of maintaining an activity-dependent nonvolatile resistance and is therefore a candidate for use in next-generation storage and logic circuits. In this article, we present a model of the PEO-PANI memristor for use in the SPICE circuit simulation program which is especially suited to analog logic applications. Two variants are presented herein; accompanying each is a short description that explains any design decisions made, as well as elucidating on preferred simulation settings. It is shown that the model accurately replicates corresponding experimental results found in the literature. Simple simulations are used to show the suitability of each variant to specific experimental usage. Appendices contain verbatim implementations of the SPICE models.

Cartesian genetic programming for memristive logic circuits

In this paper memristive logic circuits are evolved using Cartesian Genetic Programming. Graphs comprised of implication logic (IMP) nodes are compared to more ubiquitous NAND circuitry on a number of logic circuit problems and a robotic control task. Self-adaptive search parameters are used to provide each graph with autonomy with respect to its relative mutation rates. Results demonstrate that, although NAND-logic graphs are easier to evolve, IMP graphs carry benefits in terms of (i) numbers of memristors required (ii) the time required to process the graphs.