Training dynamically balanced excitatory-inhibitory networks

Ingrosso, Alessandro; Abbott, L. F.

doi:10.1371/journal.pone.0220547

Cited by 47 publications

(72 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Instead, some of them were relying on control theory to train a chaotic reservoir of spiking neurons [32][33][34] . Others used the FORCE algorithm 35,36 or variants of it 35,[37][38][39] . However, the FORCE algorithm was not argued to be biologically realistic, as the plasticity rule for each synaptic weight requires knowledge of the current values of all other synaptic weights.…”

Section: Discussionmentioning

confidence: 99%

A solution to the learning dilemma for recurrent networks of spiking neurons

et al. 2020

View full text Add to dashboard Cite

Recurrently connected networks of spiking neurons underlie the astounding information processing capabilities of the brain. Yet in spite of extensive research, how they can learn through synaptic plasticity to carry out complex network computations remains unclear. We argue that two pieces of this puzzle were provided by experimental data from neuroscience. A mathematical result tells us how these pieces need to be combined to enable biologically plausible online network learning through gradient descent, in particular deep reinforcement learning. This learning method-called e-prop-approaches the performance of backpropagation through time (BPTT), the best-known method for training recurrent neural networks in machine learning. In addition, it suggests a method for powerful on-chip learning in energy-efficient spike-based hardware for artificial intelligence.

show abstract

Section: Discussionmentioning

confidence: 99%

A solution to the learning dilemma for recurrent networks of spiking neurons

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Despite some fundamental limitations common to most computational models of brain activity, our approach was designed with several key features of living neuronal networks, including spiking neurons, Dale's principle, balanced excitation/inhibition, a heterogeneity of neuronal and synaptic parameters, propagation delays, and conductance-based synapses (van Vreeswijk and Sompolinsky, 1996 ; Sussillo and Abbott, 2009 ; Ingrosso and Abbott, 2019 ). We used a learning algorithm that isn't biologically plausible to train the readout unit (recursive least-square).…”

Section: Discussionmentioning

confidence: 99%

“…We used the recursive least square algorithm (Haykin, 2002) to train the readout units to produce the target functions. The W out weight matrix was updated based on the following equations:…”

Section: Learning Algorithm For the Readout Unitmentioning

confidence: 99%

“…During the training phase, the network was training when receiving a combination of two oscillatory inputs at 4 and 5 Hz. Synaptic weights from the SRNN to the read-out were adjusted using the recursive leastsquares learning algorithm (Haykin, 2002) adapted to spiking units (Nicola and Clopath, 2017). During the testing phase, synaptic weights were frozen and the network's performance was assessed by computing the Pearson correlation between the target function and the network's output.…”

Section: A Cortical Network Driven By Oscillationsmentioning

confidence: 99%

See 1 more Smart Citation

Learning Long Temporal Sequences in Spiking Networks by Multiplexing Neural Oscillations

Vincent-Lamarre

Calderini

Thivierge

2020

Front. Comput. Neurosci.

View full text Add to dashboard Cite

Many cognitive and behavioral tasks-such as interval timing, spatial navigation, motor control, and speech-require the execution of precisely-timed sequences of neural activation that cannot be fully explained by a succession of external stimuli. We show how repeatable and reliable patterns of spatiotemporal activity can be generated in chaotic and noisy spiking recurrent neural networks. We propose a general solution for networks to autonomously produce rich patterns of activity by providing a multi-periodic oscillatory signal as input. We show that the model accurately learns a variety of tasks, including speech generation, motor control, and spatial navigation. Further, the model performs temporal rescaling of natural spoken words and exhibits sequential neural activity commonly found in experimental data involving temporal processing. In the context of spatial navigation, the model learns and replays compressed sequences of place cells and captures features of neural activity such as the emergence of ripples and theta phase precession. Together, our findings suggest that combining oscillatory neuronal inputs with different frequencies provides a key mechanism to generate precisely timed sequences of activity in recurrent circuits of the brain.

show abstract

Section: Discussionmentioning

confidence: 99%

Learning long temporal sequences in spiking networks by multiplexing neural oscillations

Vincent-Lamarre

Calderini

Thivierge

2019

Preprint

View full text Add to dashboard Cite

Many cognitive and behavioral tasks -such as interval timing, spatial navigation, motor control and speech -require the execution of preciselytimed sequences of neural activation that cannot be fully explained by a succession of external stimuli. We use a reservoir computing framework to explain how such neural sequences can be generated and employed in temporal tasks. We propose a general solution for recurrent neural networks to autonomously produce rich patterns of activity by providing a multi-periodic oscillatory signal as input. We show that the model accurately learns a variety of tasks, including speech generation, motor control and spatial navigation. Further, the model performs temporal rescaling of natural spoken words and exhibits sequential neural activity commonly found in experimental data involving temporal processing. In the context of spatial navigation, the model learns and replays compressed sequences of place cells and captures features of neural activity such as the emergence of ripples and theta phase precession. Together, our findings suggest that combining oscillatory neuronal inputs with different frequencies provides a key mechanism to generate precisely timed sequences of activity in recurrent circuits of the brain. 1 2 3 4 5 6 7 8 9 10 Reservoir computing | Neural oscillations | Temporal processing | Balanced networks 1. Introduction 1 Virtually every aspect of sensory, cognitive and motor processing in biological organisms involves operations unfolding in time 2(1). In the brain, neuronal circuits must represent time on a variety of scales, from milliseconds to minutes and longer circadian 3 rhythms (2). Despite increasingly sophisticated models of brain activity, time representation remains a challenging problem in 4 computational modelling (3, 4). 5 Recurrent neural networks offer a promising avenue to detect and produce precisely timed sequences of activity (5). However, 6 it is challenging to train these networks due to their complexity (6), particularly when operating in a chaotic regime associated 7 with biological neural networks (7, 8). 8 One avenue to address this issue is with the use of reservoir computing (RC) (9, 10). Under this framework, a recurrent 9 network (the reservoir) projects onto a read-out layer whose synaptic weights are adjusted to produce a desired response. 10 However, while RC can capture some behavioral and cognitive processes (11)(12)(13), it often relies on biologically implausible 11 mechanisms (14). Further, current RC implementations offer little insight to understand how the brain generates activity that 12 does not follow a strict rhythmic pattern (1, 5). That is because RC models are either restricted to learning periodic functions, 13 or require an aperiodic input to generate an aperiodic output, thus leaving the neural origins of aperiodic activity unresolved 14 (5). A solution to this problem is to train the recurrent connections of the reservoir to stabilize innate patterns of activity (12), 15 but this approach is more com...

show abstract

Training dynamically balanced excitatory-inhibitory networks

Cited by 47 publications

References 37 publications

A solution to the learning dilemma for recurrent networks of spiking neurons

A solution to the learning dilemma for recurrent networks of spiking neurons

Learning Long Temporal Sequences in Spiking Networks by Multiplexing Neural Oscillations

Learning long temporal sequences in spiking networks by multiplexing neural oscillations

Contact Info

Product

Resources

About