Header

UZH-Logo

Maintenance Infos

Deep counter networks for asynchronous event-based processing


Binas, Jonathan; Indiveri, Giacomo; Pfeiffer, Michael (2016). Deep counter networks for asynchronous event-based processing. arXiv: Computer Science/Neural and Evolutionary Computing 1611.00710, Institute of Neuroinformatics.

Abstract

Despite their advantages in terms of computational resources, latency, and power consumption, event-based implementations of neural networks have not been able to achieve the same performance figures as their equivalent state-of-the-art deep network models. We propose counter neurons as minimal spiking neuron models which only require addition and comparison operations, thus avoiding costly multiplications. We show how inference carried out in deep counter networks converges to the same accuracy levels as are achieved with state-of-the-art conventional networks. As their event-based style of computation leads to reduced latency and sparse updates, counter networks are ideally suited for efficient compact and low-power hardware implementation. We present theory and training methods for counter networks, and demonstrate on the MNIST benchmark that counter networks converge quickly, both in terms of time and number of operations required, to state-of-the-art classification accuracy.

Abstract

Despite their advantages in terms of computational resources, latency, and power consumption, event-based implementations of neural networks have not been able to achieve the same performance figures as their equivalent state-of-the-art deep network models. We propose counter neurons as minimal spiking neuron models which only require addition and comparison operations, thus avoiding costly multiplications. We show how inference carried out in deep counter networks converges to the same accuracy levels as are achieved with state-of-the-art conventional networks. As their event-based style of computation leads to reduced latency and sparse updates, counter networks are ideally suited for efficient compact and low-power hardware implementation. We present theory and training methods for counter networks, and demonstrate on the MNIST benchmark that counter networks converge quickly, both in terms of time and number of operations required, to state-of-the-art classification accuracy.

Statistics

Downloads

7 downloads since deposited on 26 Jan 2017
7 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Working Paper
Communities & Collections:07 Faculty of Science > Institute of Neuroinformatics
Dewey Decimal Classification:570 Life sciences; biology
Language:English
Date:2016
Deposited On:26 Jan 2017 11:48
Last Modified:29 Aug 2017 22:25
Series Name:arXiv: Computer Science/Neural and Evolutionary Computing
Free access at:Official URL. An embargo period may apply.
Official URL:https://arxiv.org/abs/1611.00710

Download

Download PDF  'Deep counter networks for asynchronous event-based processing'.
Preview
Content: Published Version
Filetype: PDF
Size: 802kB