We envision building an optical processing chip that uses light propagation in optical waveguides to perform general mathematical operations such as vector multiplications and matrix-vector multiplications. These computations are the cornerstones for convolutional and deep neural networks.
The growth of machine learning and artificial intelligence has caused significant demand for more powerful computation devices that can process intensive amounts of data. As existing electronic computation chips are already struggling to meet that demand and are rapidly approaching their physical limits, we recognize that a paradigm shift in how we perform computation is needed. We believe that optical computation will be that paradigm shift.
We believe that optical computing can outperform current electronic computation because it solves the main problem therein: increased power cost of moving data in electronic chips. Current electronic chips cope with the computation demand by adding more computational elements which comes with increased energy consumption. Surprisingly, most of this energy consumption doesn’t occur within the computational elements but instead to move the data among the computational units and between these units and memory. This energy loss can be greatly improved via the use of photonic structures to perform computations and perform the transmission of data. Optical components have already dominated the area of data transmission between data centers and are well-positioned to solve the same problem within computing systems and within processing chips.
We address this challenge by having a highly qualified team of engineers and scientists bringing together the required experience in integrated photonics, CMOS electronics and AI computation. We are a portfolio company of TandemLaunch, who provides us with the necessary mentoring and strong experience in venture founding.
Copyright © 2020 Optius - All Rights Reserved.