Neuronal Plasticity and Temporal Adaptivity: GasNet Robot Control Networks

By Tom Smith, P. Husbands, Andrew O. Philippides, Michael O'Shea. 2002

56 citations recorded by the source corpus.

Designing controllers for autonomous robots is not an exact science, and there are few guiding principles on what properties of control systems are useful for what kinds of task. In this article we analyze the functional operation of robot controllers developed using evolutionary computation methods, to elucidate the strengths and weaknesses of the underlying control system class. By comparing and contrasting robot controllers based on two different classes of artificial neural network, the GasNet and NoGas networks, we show that the increased evolvability of the GasNet class on a visual shape discrimination task is due to the temporally adaptive nature of the GasNet, where neuronal plasticity mediated through the concentration of virtual neuromodulatory "gases" occurs over a wide range of time courses. We argue that the availability of mechanisms operating over a wide range of potential time courses is a crucial property for controllers used to generate adaptive behavior over time, and that the design process should easily be able to adapt those time courses to the natural time scales in the environment.

Subfields: Artificial Intelligence, Cognitive Neuroscience, Electrical and Electronic 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 Cognitive Neuroscience

In Electrical and Electronic Engineering

Citations in the corpus

Born to Learn: the Inspiration, Progress, and Future of Evolved Plastic Artificial Neural Networks (2017, background): “In 2002), the authors propose a plastic network that adapts its activation functions by simulating the diffusion of a gas.”
The evolvability of artificial neural net-works for robot control (2002, unknown): “(Smith et al., 2002a).”
Neuromodulation Improves the Evolution of Forward Models (2016, background): “Inspired by this natural phenomenon, researchers have added an abstraction of neuromodulation to NNs to improve short-term memory [34], evolvability [23], learning and adaptability [26], and finegrained plasticity control [24].”
Selectionist and Evolutionary Approaches to Brain Function: A Critical Appraisal (2012, background): “The particular ER task has been chosen because it provides a challenging high dimensional search space with the following properties: noisy fitness evaluations, a highly neutral space with very few widely separated regions of high fitness, and variable dimensionality (Smith et al., 2002a).”
Evolutionary Advantages of Neuromodulated Plasticity in Dynamic, Reward-based Scenarios (2008, background): “Improved performance and adaptation by means of neuromodulation were shown on a real robot in (Kondo, 2007).”
From modulated Hebbian plasticity to simple behavior learning through noise and weight saturation (2012, methodology): “However, this process can be reversed by changing the sign of Hebbian plasticity by means of a modulatory term η (Abbott, 1990; Porr and Wörgötter, 2007; Florian, 2007; Soltoggio et al., 2008; Pfeiffer et al., 2010) in ∆w ji = η · v j · v i .”