Can I read Navigating Local Minima in Quantized Spiking Neural Networks on EtoBox?

Navigating Local Minima in Quantized Spiking Neural Networks by Eshraghian, Jason K.; Lammie, Corey; Azghadi, Mostafa Rahimi; Lu, Wei D. is a scholarly article available to read on EtoBox.

What is Navigating Local Minima in Quantized Spiking Neural Networks about?

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 a

Author

Eshraghian, Jason K.; Lammie, Corey; Azghadi, Mostafa Rahimi; Lu, Wei D.

Published

2022

Language

EN