Event-driven contrastive divergence for spiking neuromorphic systems

By Emre O. Neftci, Srinjoy Das, Bruno U. Pedroni, Kenneth Kreutz-Delgado, Gert Cauwenberghs. 2013

211 citations recorded by the source corpus.

Restricted Boltzmann Machines (RBMs) and Deep Belief Networks have been demonstrated to perform efficiently in a variety of applications, such as dimensionality reduction, feature learning, and classification. Their implementation on neuromorphic hardware platforms emulating large-scale networks of spiking neurons can have significant advantages from the perspectives of scalability, power dissipation and real-time interfacing with the environment. However, the traditional RBM architecture and the commonly used training algorithm known as Contrastive Divergence (CD) are based on discrete updates and exact arithmetics which do not directly map onto a dynamical neural substrate. Here, we present an event-driven variation of CD to train a RBM constructed with Integrate & Fire (I&F) neurons, that is constrained by the limitations of existing and near future neuromorphic hardware platforms. Our strategy is based on neural sampling, which allows us to synthesize a spiking neural network that samples from a target Boltzmann distribution. The recurrent activity of the network replaces the discrete steps of the CD algorithm, while Spike Time Dependent Plasticity (STDP) carries out the weight updates in an online, asynchronous fashion. We demonstrate our approach by training an RBM composed of leaky I&F neurons with STDP synapses to learn a generative model of the MNIST hand-written digit dataset, and by testing it in recognition, generation and cue integration tasks. Our results contribute to a machine learning-driven approach for synthesizing networks of spiking neurons capable of carrying out practical, high-level functionality.

Subfields: Cognitive Neuroscience, Electrical and Electronic Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cognitive Neuroscience

In Electrical and Electronic Engineering

Citations in the corpus

Unsupervised learning of digit recognition using spike-timing-dependent plasticity (2015, methodology): “6% Spiking RBM [29] Thresholding Spike-based Supervised Contrastive divergence 1,324/412,000 91.”
Neuromorphic Electronic Circuits for Building Autonomous Cognitive Systems (2014, background): “interfacing circuits and networks of the type described in this paper with neuromorphic event-based sensors [164]; new promising neural-based approaches have been proposed that link neuromorphic systems to machine learning [165]–[169]; substantial progress has been made in the field of neuromorphic ”
Deep Learning With Spiking Neurons: Opportunities and Challenges (2018, unknown): “If spiking neurons are connected according to the structure of restricted Boltzmann machines, contrastive divergence can be approximated in an event-based fashion (Neftci et al., 2014, 2016).”
Spiking Deep Networks with LIF Neurons (2015, background): “…(30 seconds of Source MNIST error Brader et al. [8] 3.5% (1.3% misclassiﬁed, 2.2% not classiﬁed) (IF) Eliasmith et al. [9] 6% (LIF) Neftci et al. [10] 8.1% (LIF) O’Connor et al. [11] 2.52% (sigmoid-binary), 5.91% (LIF) Garbin et al. [20] 1.7% (IF) Diehl et al. [13] 1.36% a (IF) Our network 1.63%…”
Training Deep Spiking Neural Networks Using Backpropagation (2016, methodology): “ devise learning rules operating directly on spike trains, but so far it has only been possible to train single layers, and use unsupervised learning rules, which leads to a deterioration of accuracy [3, 18, 20]. An alternative approach has recently been introduced by [23], in which a SNN learns fro”
Conversion of Continuous-Valued Deep Networks to Efficient Event-Driven Networks for Image Classification (2017, background): “Alternatively, one could present the bias with an external spike input of constant rate proportional to the ANN bias, as proposed in Neftci et al. (2014), though then one may have to invert the sign of spikes to account for negative biases.”
Spatio-Temporal Backpropagation for Training High-Performance Spiking Neural Networks (2017, background): “…controls the DVS to move in the direction of three sides of the isosceles triangle in turn (ﬁgure5.b) and collects the generated spike train which [31] 784-500-40 None 93.16% Spiking RBM(pre-training*) [20] 784-500-500-10 None 97.48% Spiking MLP(pre-training*) [19] 784-1200-1200-10 Weight…”