Voltage-dependent synaptic plasticity: Unsupervised probabilistic Hebbian plasticity rule based on neurons membrane potential

Abstract

This study proposes voltage-dependent-synaptic plasticity (VDSP), a novel brain-inspired unsupervised local learning rule for the online implementation of Hebb’s plasticity mechanism on neuromorphic hardware. The proposed VDSP learning rule updates the synaptic conductance on the spike of the postsynaptic neuron only, which reduces by a factor of two the number of updates with respect to standard spike timing dependent plasticity (STDP). This update is dependent on the membrane potential of the presynaptic neuron, which is readily available as part of neuron implementation and hence does not require additional memory for storage. Moreover, the update is also regularized on synaptic weight and prevents explosion or vanishing of weights on repeated stimulation. Rigorous mathematical analysis is performed to draw an equivalence between VDSP and STDP. To validate the system-level performance of VDSP, we train a single-layer spiking neural network (SNN) for the recognition of handwritten digits. We report 85.01 ± 0.76% (Mean ± SD) accuracy for a network of 100 output neurons on the MNIST dataset. The performance improves when scaling the network size (89.93 ± 0.41% for 400 output neurons, 90.56 ± 0.27 for 500 neurons), which validates the applicability of the proposed learning rule for spatial pattern recognition tasks. Future work will consider more complicated tasks. Interestingly, the learning rule better adapts than STDP to the frequency of input signal and does not require hand-tuning of hyperparameters.

Unsupervised and efficient learning in sparsely activated convolutional spiking neural networks enabled by voltage-dependent synaptic plasticity

“…around 0.9% activations. The proposed CSNN with a linear SVM also outperforms by 8% the accuracy reported in the original VDSP paper [23], where a one-layer fully connected network is used. However, it is important to note that the author used an unsupervised readout based on spike counts, which is much less complex.…”

“…However, STDP has some limitations that makes its hardware implementation difficult. Hence, a novel plasticity rule, called voltage-dependent synaptic plasticity (VDSP) [23], has been developed for the implementation of STDP on memristive-based neuromorphic hardware. This rule is also unsupervised and local, as it uses the membrane potential of the presynaptic neuron (instead of its spike timing in STDP) to evaluate pre/post neurons correlation.…”

“…Learning in the CSNN is performed online, in an unsupervised and local fashion, with a winner-take-all based adaptation of VDSP [23] for SSIF neurons. VDSP is a novel, hardware-friendly, alternative approach to STDP, developed for the implementation of Hebb's plasticity mechanism on memristive-based neuromorphic hardware.…”

“…Consequently, a novel unsupervised and local plasticity rule, called voltage-dependent synaptic plasticity (VDSP) [23], has recently been developed to address STDP issues. VDSP is a hardware-friendly alternative approach to STDP (and other Hebbian-based rules) developed for the implementation of Hebb's plasticity mechanism on memristive-based neuromorphic hardware.…”

“…The membrane potential is, hence, readily and locally available to the synapses. VDSP is new and has been implemented only on a one-layer fully connected network for now [23]. Further research has to be done to evaluate the scalability and the performance of VDSP in other network architectures.…”