The workshop discussed the challenges faced by traditional methods in semiconductor manufacturing, and the potential for innovative AI tools to tackle these complex problems. The discussion emphasized the crucial role of data curation in training AI models. It was highlighted that curating the right datasets is essential for developing AI solutions that can contribute to breakthroughs in semiconductor manufacturing. A structured approach to data collection and curation across academia and industry was recognized as necessary.
Robust technological infrastructure was noted as crucial to support AI initiatives in Singapore. This infrastructure must be capable of handling complex computations and large volumes of data to meet the demands of advanced AI applications in semiconductor manufacturing.
Integrating physics constraints into AI models was proposed as a way to improve semiconductor scanning techniques. By embedding these constraints, AI models can become more efficient and accurate in simulating and predicting semiconductor behaviors. Developing efficient surrogate models was also emphasized to speed up simulation processes without sacrificing accuracy.
The workshop concluded with highlighting the for further collaboration between academia and industry, as well as the need for Singapore-level funding in research and development projects based on the identified challenges and technological needs, with the aim of catalysing innovations and collaborative efforts in the semiconductor industry, especially within the Singapore context.
We use cookies to analyze website traffic and optimize your website experience. By accepting our use of cookies, your data will be aggregated with all other user data.