Predicting non-linear dynamics by stable local learning in a recurrent spiking neural network

Abstract

Brains need to predict how the body reacts to motor commands. It is an open question how networks of spiking neurons can learn to reproduce the non-linear body dynamics caused by motor commands, using local, online and stable learning rules. Here, we present a supervised learning scheme for the feedforward and recurrent connections in a network of heterogeneous spiking neurons. The error in the output is fed back through fixed random connections with a negative gain, causing the network to follow the desired dynamics, while an online and local rule changes the weights. The rule for Feedback-based Online Local Learning Of Weights (FOLLOW) is local in the sense that weight changes depend on the presynaptic activity and the error signal projected onto the postsynaptic neuron. We provide examples of learning linear, non-linear and chaotic dynamics, as well as the dynamics of a two-link arm. Using the Lyapunov method, and under reasonable assumptions and approximations, we show that FOLLOW learning is stable uniformly, with the error going to zero asymptotically.

References in corpus (5)

• Supervised Learning in Spiking Neural Networks with FORCE Training
• Learning universal computations with spikes
• Supervised Learning in Spiking Neural Networks for Precise Temporal Encoding
• Using Firing-Rate Dynamics to Train Recurrent Networks of Spiking Model Neurons
• Learning arbitrary dynamics in efficient, balanced spiking networks using local plasticity rules

Cited by in corpus (11)

• SuperSpike: Supervised learning in multi-layer spiking neural networks
• The Heidelberg spiking datasets for the systematic evaluation of spiking neural networks
• Supervised Learning in Spiking Neural Networks with FORCE Training
• Learning spatiotemporal signals using a recurrent spiking network that discretizes time
• Implicit Regularization and Momentum Algorithms in Nonlinearly Parameterized Adaptive Control and Prediction
• Integration of Leaky-Integrate-and-Fire-Neurons in Deep Learning Architectures
• Embodied Synaptic Plasticity with Online Reinforcement learning
• Learning arbitrary dynamics in efficient, balanced spiking networks using local plasticity rules
• Supervised training of spiking neural networks for robust deployment on mixed-signal neuromorphic processors
• Backpropagation through space, time, and the brain
• A Novel Approximate Hamming Weight Computing for Spiking Neural Networks: an FPGA Friendly Architecture