Supervised Learning in Spiking Neural Networks with FORCE Training

Abstract

Populations of neurons display an extraordinary diversity in the behaviors they affect and display. Machine learning techniques have recently emerged that allow us to create networks of model neurons that display behaviours of similar complexity. Here, we demonstrate the direct applicability of one such technique, the FORCE method, to spiking neural networks. We train these networks to mimic dynamical systems, classify inputs, and store discrete sequences that correspond to the notes of a song. Finally, we use FORCE training to create two biologically motivated model circuits. One is inspired by the zebra-finch and successfully reproduces songbird singing. The second network is motivated by the hippocampus and is trained to store and replay a movie scene. FORCE trained networks reproduce behaviors comparable in complexity to their inspired circuits and yield information not easily obtainable with other techniques such as behavioral responses to pharmacological manipulations and spike timing statistics.

References in corpus (7)

• Recurrent Network Models Of Sequence Generation And Memory
• Supervised Learning in Spiking Neural Networks with FORCE Training
• Learning universal computations with spikes
• Predicting non-linear dynamics by stable local learning in a recurrent spiking neural network
• Local Dynamics in Trained Recurrent Neural Networks
• 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 (35)

• Artificial neural networks for neuroscientists: A primer
• The Heidelberg spiking datasets for the systematic evaluation of spiking neural networks
• Supervised Learning in Spiking Neural Networks with FORCE Training
• Surrogate Gradient Learning in Spiking Neural Networks
• Real-time ultra-low power ECG anomaly detection using an event-driven neuromorphic processor
• Predicting non-linear dynamics by stable local learning in a recurrent spiking neural network
• Biologically inspired alternatives to backpropagation through time for learning in recurrent neural nets
• Learning spatiotemporal signals using a recurrent spiking network that discretizes time
• A Survey on Reservoir Computing and its Interdisciplinary Applications Beyond Traditional Machine Learning
• Connectivity Concepts in Neuronal Network Modeling
• How single neuron properties shape chaotic dynamics and signal transmission in random neural networks
• Training dynamically balanced excitatory-inhibitory networks
• Contrasting the effects of adaptation and synaptic filtering on the timescales of dynamics in recurrent networks
• Sleep-like slow oscillations improve visual classification through synaptic homeostasis and memory association in a thalamo-cortical model
• Reservoir Computing Benchmarks: a tutorial review and critique
• Beyond spiking networks: the computational advantages of dendritic amplification and input segregation
• Firing rate homeostasis counteracts changes in stability of recurrent neural networks caused by synapse loss in Alzheimer's disease
• Passive nonlinear dendritic interactions as a general computational resource in functional spiking neural networks
• Online Training of Spiking Recurrent Neural Networks with Phase-Change Memory Synapses
• Target spiking patterns enable efficient and biologically plausible learning for complex temporal tasks
• Populations of Spiking Neurons for Reservoir Computing: Closed Loop Control of a Compliant Quadruped
• Emergent Computations in Trained Artificial Neural Networks and Real Brains
• Composite FORCE learning of chaotic echo state networks for time-series prediction
• Error-based or target-based? A unifying framework for learning in recurrent spiking networks
• A Unifying Framework for Information Processing in Stochastically Driven Dynamical Systems
• Supervised training of spiking neural networks for robust deployment on mixed-signal neuromorphic processors
• Optimal Learning with Excitatory and Inhibitory synapses
• Dynamics and computation in mixed networks containing neurons that accelerate towards spiking
• Spiking mode-based neural networks
• Training Spiking Neural Networks for Cognitive Tasks: A Versatile Framework Compatible to Various Temporal Codes
• Harnessing Slow Dynamics in Neuromorphic Computation
• The Roles of Supervised Machine Learning in Systems Neuroscience
• Learning recurrent dynamics in spiking networks
• Reliable counting of weakly labeled concepts by a single spiking neuron model
• A Novel Approximate Hamming Weight Computing for Spiking Neural Networks: an FPGA Friendly Architecture