Bio-inspired digit recognition using reward-modulated spike-timing-dependent plasticity in deep convolutional networks

2018-03-31 · Milad Mozafari, Mohammad Ganjtabesh, Abbas Nowzari-Dalini, Simon J. Thorpe, Timothée Masquelier

The primate visual system has inspired the development of deep artificial neural networks, which have revolutionized the computer vision domain. Yet these networks are much less energy-efficient than their biological counterparts, and they are typically trained with backpropagation, which is extremely data-hungry. To address these limitations, we used a deep convolutional spiking neural network (DCSNN) and a latency-coding scheme. We trained it using a combination of spike-timing-dependent plasticity (STDP) for the lower layers and reward-modulated STDP (R-STDP) for the higher ones. In short, with R-STDP a correct (resp. incorrect) decision leads to STDP (resp. anti-STDP). This approach led to an accuracy of $97.2\%$ on MNIST, without requiring an external classifier. In addition, we demonstrated that R-STDP extracts features that are diagnostic for the task at hand, and discards the other ones, whereas STDP extracts any feature that repeats. Finally, our approach is biologically plausible, hardware friendly, and energy-efficient.

📄 PDF Abstract BibTeX arXiv:1804.00227

Code (1)

miladmozafari/SpykeTorch 공식 구현 pytorch

Tasks

Diagnostic

Custom DNN using Reward Modulated Inverted STDP Learning for Temporal Pattern Recognition

2023-07-15 · Vijay Shankaran Vivekanand, Rajkumar Kubendran

Temporal spike recognition plays a crucial role in various domains, including anomaly detection, keyword spotting and neuroscience. This paper presents a novel algorithm for efficient temporal spike pattern recognition o…

Anomaly Detection Keyword Spotting Time Series

Reward-Modulated Local Learning in Spiking Encoders: Controlled Benchmarks with STDP and Hybrid Rate Readouts

2026-02-28 · Debjyoti Chakraborty arxiv

This paper presents a controlled empirical study of biologically motivated local learning for handwritten digit recognition. We evaluate an STDP-inspired competitive proxy and a practical hybrid benchmark built on the sa…

Handwritten Digit Recognition

BioLCNet: Reward-modulated Locally Connected Spiking Neural Networks

2021-09-12 · Hafez Ghaemi, Erfan Mirzaei, Mahbod Nouri, Saeed Reza Kheradpisheh

Brain-inspired computation and information processing alongside compatibility with neuromorphic hardware have made spiking neural networks (SNN) a promising method for solving learning tasks in machine learning (ML). Spi…

Decoder image-classification Image Classification

First-spike based visual categorization using reward-modulated STDP

2017-05-25 · Milad Mozafari, Saeed Reza Kheradpisheh, Timothée Masquelier, Abbas Nowzari-Dalini 외

Reinforcement learning (RL) has recently regained popularity, with major achievements such as beating the European game of Go champion. Here, for the first time, we show that RL can be used efficiently to train a spiking…

Game of Go Object Recognition Reinforcement Learning Reinforcement Learning (RL)

Ultra Low-Power and Real-time ECG Classification Based on STDP and R-STDP Neural Networks for Wearable Devices

2019-05-08 · arXiv:1905.02954 2019 5 · Alireza Amirshahi, Matin Hashemi

This paper presents a novel ECG classification algorithm for real-time cardiac monitoring on ultra low-power wearable devices. The proposed solution is based on spiking neural networks which are the third generation of n…

ECG Classification