Multitask computation through dynamics in recurrent spiking neural networks
Mechislav M. Pugavko, Oleg V. Maslennikov, Vladimir I. Nekorkin
Abstract
In this work, inspired by cognitive neuroscience experiments, we propose recurrent spiking neural networks trained to perform multiple target tasks. These models are designed by considering neurocognitive activity as computational processes through dynamics. Trained by input-output examples, these spiking neural networks are reverse engineered to find the dynamic mechanisms that are fundamental to their performance. We show that considering multitasking and spiking within one system provides insightful ideas on the principles of neural computation.
Topics & Concepts
Human multitaskingComputer scienceSpiking neural networkNeurocognitiveModels of neural computationComputationArtificial intelligenceArtificial neural networkDynamics (music)Recurrent neural networkMachine learningCognitionNeuroscienceAlgorithmPsychologyPedagogyAdvanced Memory and Neural ComputingNeural Networks and Reservoir ComputingNeural dynamics and brain function