Behavioral plasticity through the modulation of switch neurons
Christodoulou, Chris C.
Google Scholar check
MetadataShow full item record
A central question in artificial intelligence is how to design agents capable of switching between different behaviors in response to environmental changes. Taking inspiration from neuroscience, we address this problem by utilizing artificial neural networks (NNs) as agent controllers, and mechanisms such as neuromodulation and synaptic gating. The novel aspect of this work is the introduction of a type of artificial neuron we call "switch neuron". A switch neuron regulates the flow of information in NNs by selectively gating all but one of its incoming synaptic connections, effectively allowing only one signal to propagate forward. The allowed connection is determined by the switch neuron's level of modulatory activation which is affected by modulatory signals, such as signals that encode some information about the reward received by the agent. An important aspect of the switch neuron is that it can be used in appropriate "switch modules" in order to modulate other switch neurons. As we show, the introduction of the switch modules enables the creation of sequences of gating events. This is achieved through the design of a modulatory pathway capable of exploring in a principled manner all permutations of the connections arriving on the switch neurons. We test the model by presenting appropriate architectures in nonstationary binary association problems and T-maze tasks. The results show that for all tasks, the switch neuron architectures generate optimal adaptive behaviors, providing evidence that the switch neuron model could be a valuable tool in simulations where behavioral plasticity is required. © 2015 Elsevier Ltd.
Showing items related by title, author, creator and subject.
Christodoulou, Chris C.; Bugmann, G.; Clarkson, T. G.; Taylor, J. G. (1993)The Temporal Noisy-Leaky Integrator (TNU) neuron model with additional inhibitory inputs is presented together with its theoretical mathematical basis. The TNU is a biologically inspired hardware neuron which models ...
Multiagent reinforcement learning: Spiking and nonspiking agents in the Iterated Prisoner's Dilemma Vassiliades, Vassilis; Cleanthous, A.; Christodoulou, Chris C. (2011)This paper investigates multiagent reinforcement learning (MARL) in a general-sum game where the payoffs' structure is such that the agents are required to exploit each other in a way that benefits all agents. The contradictory ...
Neokleous, Kleanthis C.; Avraamides, Marios N.; Neocleous, Costas K.; Schizas, Christos N. (2009)One challenging application for Artificial Neural Networks (ANN) would be to try and actually mimic the behaviour of the system that has inspired their creation as computational algorithms. That is to use ANN in order to ...