WEDNESDAY July 22, 2:00pm - 3:00pm
TOPIC AREA: MACHINE LEARNING/AI, EDA
KEYWORD: ANY
EVENT TYPE: PANEL
Artificial Intelligence Comes to CAD: Where’s the Data?
Moderator:
Marilyn Wolf - Univ. of Nebraska, Lincoln, NE
Organizer:
Marilyn Wolf - Univ. of Nebraska, Lincoln, NE
Machine learning has received widespread attention in many fields including CAD. This panel will discuss and debate two main questions that must be solved before machine learning can be successfully applied to computer-aided design of electronic systems. First, at what levels of abstraction is machine learning applicable? Potential applications include device optimization, circuit synthesis, and optimization, logic synthesis, ESL, verification, and validation. The machine learning methods required at these different levels of abstraction will vary widely. The impact of machine learning at these levels of abstraction is up for debate. Given the large investments required to introduce machine learning-based approaches, targets of opportunity must be carefully evaluated and identified. Second, how do we manage the huge amounts of data required to apply machine learning? Does data need to be labeled; if so, who will provide labels? Can models be used to augment labeling? What intellectual property rights must be negotiated to obtain training data? Who will own the results of machine learning methods driven by outside data?

Panelists:
Thomas Andersen - Synopsys, Inc., Mountain View, CA
Paul Franzon - North Carolina State Univ., Raleigh, NC
Elias Fallon - Cadence Design Systems, Inc., Pittsburgh, PA
Raviv Gal - IBM Research - Haifa, Israel
Sachin Sapatnekar - Univ. of Minnesota, Minneapolis, MN