Navigating Local Minima in Quantized Spiking Neural Networks Article Swipe

MAKE IMPACT

Jason K. Eshraghian , Corey Lammie , Mostafa Rahimi Azghadi , Wei Lü · YOU? · · 2022 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2202.07221

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: https://github.com/jeshraghian/QSNNs.

Type

preprint

Language

en

Landing Page

http://arxiv.org/abs/2202.07221

PDF

https://arxiv.org/pdf/2202.07221

OA Status

green

Cited By

1

Related Works

10

OpenAlex ID

https://openalex.org/W4221155749

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W4221155749

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2202.07221

Digital Object Identifier

Title

Navigating Local Minima in Quantized Spiking Neural Networks

Work title

Type

preprint

OpenAlex work type

Language

en

Primary language

Publication year

2022

Year of publication

Publication date

2022-02-15

Full publication date if available

Authors

Jason K. Eshraghian, Corey Lammie, Mostafa Rahimi Azghadi, Wei Lü

List of authors in order

Landing page

https://arxiv.org/abs/2202.07221

Publisher landing page

PDF URL

https://arxiv.org/pdf/2202.07221

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2202.07221

Direct OA link when available

Concepts

Maxima and minima, Computer science, Artificial neural network, Artificial intelligence, Thresholding, Estimator, Spiking neural network, Backpropagation, Machine learning, Gradient descent, Code (set theory), Noise (video), Algorithm, Pattern recognition (psychology), Mathematics, Statistics, Mathematical analysis, Set (abstract data type), Programming language, Image (mathematics)

Top concepts (fields/topics) attached by OpenAlex

Cited by

1

Total citation count in OpenAlex

Citations by year (recent)

2023: 1

Per-year citation counts (last 5 years)

Related works (count)

10

Other works algorithmically related by OpenAlex

Full payload