Navigating Local Minima in Quantized Spiking Neural Networks

by   Jason K. Eshraghian, et al.

Spiking and Quantized Neural Networks (NNs) are becoming exceedingly important for hyper-efficient implementations of Deep Learning (DL) algorithms. However, these networks face challenges when trained using error backpropagation, due to the absence of gradient signals when applying hard thresholds. The broadly accepted trick to overcoming this is through the use of biased gradient estimators: surrogate gradients which approximate thresholding in Spiking Neural Networks (SNNs), and Straight-Through Estimators (STEs), which completely bypass thresholding in Quantized Neural Networks (QNNs). While noisy gradient feedback has enabled reasonable performance on simple supervised learning tasks, it is thought that such noise increases the difficulty of finding optima in loss landscapes, especially during the later stages of optimization. By periodically boosting the Learning Rate (LR) during training, we expect the network can navigate unexplored solution spaces that would otherwise be difficult to reach due to local minima, barriers, or flat surfaces. This paper presents a systematic evaluation of a cosine-annealed LR schedule coupled with weight-independent adaptive moment estimation as applied to Quantized SNNs (QSNNs). We provide a rigorous empirical evaluation of this technique on high precision and 4-bit quantized SNNs across three datasets, demonstrating (close to) state-of-the-art performance on the more complex datasets. Our source code is available at this link:


Spiking-Diffusion: Vector Quantized Discrete Diffusion Model with Spiking Neural Networks

Spiking neural networks (SNNs) have tremendous potential for energy-effi...

Explicitly Trained Spiking Sparsity in Spiking Neural Networks with Backpropagation

Spiking Neural Networks (SNNs) are being explored for their potential en...

Training Spiking Neural Networks Using Lessons From Deep Learning

The brain is the perfect place to look for inspiration to develop more e...

A Spike in Performance: Training Hybrid-Spiking Neural Networks with Quantized Activation Functions

The machine learning community has become increasingly interested in the...

Low-activity supervised convolutional spiking neural networks applied to speech commands recognition

Deep Neural Networks (DNNs) are the current state-of-the-art models in m...

EXODUS: Stable and Efficient Training of Spiking Neural Networks

Spiking Neural Networks (SNNs) are gaining significant traction in machi...

Fast threshold optimization for multi-label audio tagging using Surrogate gradient learning

Multi-label audio tagging consists of assigning sets of tags to audio re...

Please sign up or login with your details

Forgot password? Click here to reset