Proven Path to Deep Learning Success

Electronics manufacturing companies doing Deep Learning (DL) have found that it’s easy to get to a DL prototype, but it’s harder to get from “good prototype” results to “production-quality” results.

DL for electronics manufacturing is inherently more difficult because the level of accuracy required is orders of magnitude higher than typical DL applications. Reaching this high level of accuracy requires masses of training data, including serious anomalous conditions that (thankfully) rarely occur in production.

This lack of data – particularly anomalous data – creates a data gap between prototype- and production-quality DL applications. CDLe has successfully completed over 30 production DL projects for electronic manufacturing by using digital twin technology to bridge this data gap.

Example of mask SEM image generated by the SEM digital twin and the real SEM image.

Example of mask SEM image generated by the SEM digital twin and the real SEM image.

Digital Twins Bridge the Data Gap

Digital twins – virtual representations of actual processes, systems, and devices – are a key tool for creating the right amount of the right kind of data to train DL networks successfully. For many error conditions, digital twins are the only way to create enough anomalous data to properly train the networks to recognize these conditions. 

For more details on the use of SEM digital twins, watch this video by Ajay Barawal, director of CDLe, or read an article covering this topic for Semiconductor Digest. 

“GPU computing has achieved great success in semiconductor design, simulation, and manufacturing. But as process technology shrinks, the physics is becoming increasingly difficult to simulate. At the same time, the sensor data is growing exponentially. This creates an opportunity for data-driven approaches like deep learning to complement physical models. We look forward to supporting CDLe and their efforts to achieve breakthrough results.”

Jerry Chen

Business Development Lead for Industrial Applications

Videos

A Deep Learning Mask Analysis Toolset Using Mask SEM Digital Twins

Thomas Kurian of Mycronic describes work at CDLe to identify “Mura” on flat panel display (FPD) masks

Ajay Baranwal, Director of CDLe, describes five deep learning recipes for the semiconductor mask making industry

CDLe Celebrates One-year Anniversary

About Deep Learning in Electronics Manufacturing

Meet Ajay Baranwal, the new CDLe Director

Aki Fujimura and Steve Teig talk about Deep Learning

Publications

Article from Ajay Baranwal of the CDLe, Noriaki Nakayamada of NuFlare, Mikael Wahlsten of Micronic, and Aki Fujimura of D2S
Ajay Baranwal, Director of CDLe, Presented at 2020 Photomask Technology Conference
Aki Fujimura explains the critical role of digital twins in deep learning
Experts at the Table, Part 2: ML is playing a bigger role in metrology and lithography, but it can’t replace physics-based models.
Experts at the Table: It’s not as accurate as simulation, but it’s a lot faster.
Presented at SPIE eBeam Initiative lunch by Thomas Kurian from Mycronic
Presented at SEMICON Europa 2019 by Javier Cabello from Mycronic
Ajay Baranwal, Director of CDLe, Presented at 2019 Photomask Technology Conference
Leo Pang of D2S explains why GPU-accelerated simulation is so important to deep learning
Mikael Wahlsten, Director and Product Area Manager for Photomask Generators at Mycronic, gives his insights into the idea behind the new collaboration and what it can mean for Mycronic customers in the near future.
Experts at the Table, part 3: Where can this technology be applied and what’s ahead.
Experts at the Table, part 2: Where can this technology be applied, why it is taking so long, and what challenges lie ahead.
NVIDIA, NuFlare, Mycronic and D2S executives give their perspective
Aki Fujimura pens an editorial on Deep Learning for the BACUS Newsletter

Deep Learning Primer: Data is the New Source Code

publication • September 19, 2018

Presentation at 2018 Photomask Technology Conference
NuFlare, Mycronic, and D2S Partnership tops the manufacturing news for the week
Alliance of NuFlare Technology, Mycronic and D2S using NVIDIA Technology