Deep Learning and Curvilinear Masks ... a conversation with Aki Fujimura of D2S

     Aki Fujimura     eBeam Initiative
      484      Nov 18, 2019
    Deep Learning and Curvilinear Masks are some of the most disruptive technologies coming to the semiconductor mask making industry. In the interview, Aki Fujimura of D2S has a conversation about this with Dan Hutcheson. We cover current trends in Deep Learning in Semiconductor Manufacturing, where Growing recognition of DL’s importance to semiconductor manufacturing caused the organizers of the SPIE Photomask Technology Conference to dedicate an entire session to DL Popular uses of DL today include: Improving the accuracy of Automatic Defect Categorization of inspection data and accelerating runtime of OPC.

    We also talk about some of the new things that D2S has come out with, such as where they fit in at the Center for Deep Learning in Electronics Manufacturing (CDLe) where a lack of training data makes it hard to generate good results -- especially true with anomalous data and now also with curvilinear data.  In the mask and wafer lithography space, D2S has developed a tool kit (TrueMask® DLK) to help both mask shops and non-mask shop/fab customers generate the training data needed to accelerate their DL efforts.

    Also, D2S launched it’s TrueMask® ILT solution at SPIE Photomask Conference, which enables stitchless full-chip ILT in a single day and is built specifically for the revolutionary multi-beam-based mask world. It addresses the weeks-long runtime challenge that until now had held curvilinear ILT back from use as a full-chip solution.

    About weVISION: weVISION is a series of video interviews of visionaries by G Dan Hutcheson, his career spans more than thirty years, in which he became a well-known as a visionary for helping companies make businesses out of technology. This includes hundreds of successful programs involving product development, positioning, and launch in Semiconductor, Technology, Medicine, Energy, Business, High Tech, Environment, Electronics, healthcare and Business divisions.