Implementation of Direct Feedback Alignment Through Time Algorithm in Training of Shallow Fully Memristive Spiking Neural Networks
- 27 September 2025
- journal article
- Published by Wiley in International Journal of Circuit Theory and Applications
- Vol. 54 (5) , 2853-2863
Abstract
In this paper, we present shallow architectures of memristive spiking neural networks (MSNNs) with a single hidden layer and a simple memristive leaky integrate‐and‐fire (LIF) neuron. The SPICE‐based model is used to describe the response of a volatile memristor within LIF, whose intrinsic reset to the initial state eliminates the need for additional electronic components for discharging the membrane capacitance. The direct feedback alignment through time (DFATT) algorithm was implemented for the first time for the training of MSNNs. The deployment of the DFATT learning algorithm on two MSNN architectures resulted in average training times per epoch that were reduced by factors of 2.1 and 2.7 compared to equivalent architectures trained with the backpropagation through time (BPTT) algorithm, with comparable accuracy on MNIST and FMNIST datasets. The reported results indicate the possibility of combining memristive technology with the bioplausible DFATT algorithm toward building energy‐efficient hardware.Keywords
This publication has 63 references indexed in Scilit:
- Advancing Neural Networks: Innovations and Impacts on Energy ConsumptionAdvanced Electronic Materials, 2024
- Memristive Neural Network Circuit of Negative Emotion Inhibition With Self‐Repair and MemoryInternational Journal of Circuit Theory and Applications, 2024
- Efficient private SCO for heavy-tailed data via averaged clippingMachine Learning, 2024
- Design of the non‐associative learning memristive circuit and the application to brightness adaptationInternational Journal of Circuit Theory and Applications, 2024
- A novel memristive neuron model and its energy characteristicsCognitive Neurodynamics, 2024
- Variability in Resistive MemoriesAdvanced Intelligent Systems, 2023
- Combination of Organic‐Based Reservoir Computing and Spiking Neuromorphic Systems for a Robust and Efficient Pattern ClassificationAdvanced Intelligent Systems, 2023
- Noise-assisted persistence and recovery of memory state in a memristive spiking neuromorphic networkChaos, Solitons & Fractals, 2021
- Supervised neural networks with memristor binary synapsesInternational Journal of Circuit Theory and Applications, 2018
- A Review of the Integrate-and-fire Neuron Model: I. Homogeneous Synaptic InputBiological Cybernetics, 2006