Learning universal computations with spikes

Abstract

Providing the neurobiological basis of information processing in higher animals, spiking neural networks must be able to learn a variety of complicated computations, including the generation of appropriate, possibly delayed reactions to inputs and the self-sustained generation of complex activity patterns, e.g.~for locomotion. Many such computations require previous building of intrinsic world models. Here we show how spiking neural networks may solve these different tasks. Firstly, we derive constraints under which classes of spiking neural networks lend themselves to substrates of powerful general purpose computing. The networks contain dendritic or synaptic nonlinearities and have a constrained connectivity. We then combine such networks with learning rules for outputs or recurrent connections. We show that this allows to learn even difficult benchmark tasks such as the self-sustained generation of desired low-dimensional chaotic dynamics or memory-dependent computations. Furthermore, we show how spiking networks can build models of external world systems and use the acquired knowledge to control them.

References in corpus (2)

• Transition to chaos in random neuronal networks
• Using Firing-Rate Dynamics to Train Recurrent Networks of Spiking Model Neurons

Cited by in corpus (16)

• SuperSpike: Supervised learning in multi-layer spiking neural networks
• Linking connectivity, dynamics and computations in low-rank recurrent neural networks
• The Heidelberg spiking datasets for the systematic evaluation of spiking neural networks
• Supervised Learning in Spiking Neural Networks with FORCE Training
• Predicting non-linear dynamics by stable local learning in a recurrent spiking neural network
• Dynamical learning of dynamics
• Gridbot: An autonomous robot controlled by a Spiking Neural Network mimicking the brain's navigational system
• Using Firing-Rate Dynamics to Train Recurrent Networks of Spiking Model Neurons
• Passive nonlinear dendritic interactions as a general computational resource in functional spiking neural networks
• Evolution and Analysis of Embodied Spiking Neural Networks Reveals Task-Specific Clusters of Effective Networks
• Dynamics and computation in mixed networks containing neurons that accelerate towards spiking
• Spiking mode-based neural networks
• Nonlinear computations in spiking neural networks through multiplicative synapses
• The brain as an efficient and robust adaptive learner
• Learning recurrent dynamics in spiking networks
• A geometrical analysis of global stability in trained feedback networks