Learning spatiotemporal signals using a recurrent spiking network that discretizes time

Abstract

Learning to produce spatiotemporal sequences is a common task that the brain has to solve. The same neural substrate may be used by the brain to produce different sequential behaviours. The way the brain learns and encodes such tasks remains unknown as current computational models do not typically use realistic biologically-plausible learning. Here, we propose a model where a spiking recurrent network of excitatory and inhibitory biophysical neurons drives a read-out layer: the dynamics of the driver recurrent network is trained to encode time which is then mapped through the read-out neurons to encode another dimension, such as space or a phase. Different spatiotemporal patterns can be learned and encoded through the synaptic weights to the read-out neurons that follow common Hebbian learning rules. We demonstrate that the model is able to learn spatiotemporal dynamics on time scales that are behaviourally relevant and we show that the learned sequences are robustly replayed during a regime of spontaneous activity.

To appear in Plos Computational Biology

References in corpus (9)

• Plasmofluidic Single-Molecule Surface Enhanced Raman Scattering from Dynamic Assembly of Plasmonic Nanoparticles
• Complexity without chaos: Plasticity within random recurrent networks generates robust timing and motor control
• Linking connectivity, dynamics and computations in low-rank recurrent neural networks
• Recurrent Network Models Of Sequence Generation And Memory
• Supervised Learning in Spiking Neural Networks with FORCE Training
• Predicting non-linear dynamics by stable local learning in a recurrent spiking neural network
• Emergence of slow-switching assemblies in structured neuronal networks
• Fundamental bounds on learning performance in neural circuits
• Feedforward Architectures Driven by Inhibitory Interactions

Cited by in corpus (7)

• Sequence learning, prediction, and replay in networks of spiking neurons
• Robust trajectory generation for robotic control on the neuromorphic research chip Loihi
• Target spiking patterns enable efficient and biologically plausible learning for complex temporal tasks
• Event-based update of synapses in voltage-based learning rules
• Composing Recurrent Spiking Neural Networks using Locally-Recurrent Motifs and Risk-Mitigating Architectural Optimization
• Coherent noise enables probabilistic sequence replay in spiking neuronal networks
• Constraints on Hebbian and STDP learned weights of a spiking neuron