Wafer2Spike: Spiking Neural Network for Wafer Map Pattern Classification

TL;DR

Wafer2Spike introduces a spiking neural network architecture for wafer map pattern classification, achieving high accuracy and efficiency, outperforming traditional deep neural networks especially on underrepresented defect patterns.

Contribution

The paper presents Wafer2Spike, a novel SNN-based approach that improves wafer map classification accuracy and efficiency over existing deep learning methods.

Findings

Achieves 98% accuracy on WM-811k dataset

Outperforms existing methods on underrepresented defect patterns

Offers computational efficiency advantages

Abstract

In integrated circuit design, the analysis of wafer map patterns is critical to improve yield and detect manufacturing issues. We develop Wafer2Spike, an architecture for wafer map pattern classification using a spiking neural network (SNN), and demonstrate that a well-trained SNN achieves superior performance compared to deep neural network-based solutions. Wafer2Spike achieves an average classification accuracy of 98\% on the WM-811k wafer benchmark dataset. It is also superior to existing approaches for classifying defect patterns that are underrepresented in the original dataset. Wafer2Spike achieves this improved precision with great computational efficiency.