Learning A Wafer Feature With One Training Sample
| Autor: | Nik Sumikawa, Yueling Jenny Zeng, Li-C. Wang, Chuanhe Jay Shan |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Computer science
business.industry 05 social sciences Construct (python library) 010501 environmental sciences Machine learning computer.software_genre 01 natural sciences Autoencoder Sample (graphics) Plot (graphics) 0502 economics and business Line (geometry) Feature (machine learning) Wafer testing Artificial intelligence 050207 economics business computer 0105 earth and related environmental sciences Test data |
| Zdroj: | ITC |
| Popis: | In this work, we consider learning a wafer plot recognizer where only one training sample is available. We introduce an approach called Manifestation Learning to enable the learning. The underlying technology utilizes the Variational AutoEncoder (VAE) approach to construct a so-called Manifestation Space. The training sample is projected into this space and the recognition is achieved through a pre-trained model in the space. Using wafer probe test data from an automotive product line, this paper explains the learning approach, its feasibility and limitation. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|