Congatec and Hacarus unveiled what was presented as the first embedded computing kit for Artificial Intelligence (AI) that uses Sparse Modeling technology. Needing little training data to make highly accurate predictions, Sparse Modeling serves applications like vision-based inspection systems, among others.
Sparse Modeling makes it possible to create an inspection model starting with 50 or fewer images, significantly less than the 1,000 or more images required for traditional AI. The Sparse Modeling Kit can be used stand-alone or as an add-on to existing inspection systems, creating inspection systems that can be trained for individual requirements and can therefore function anywhere. There is no longer a need for optimal conditions, such as constant lighting.
Algorithms based on Sparse Modeling make for a much smaller AI footprint, ideal for fanless low-power systems that are in continuous use with only a limited power consumption margin to integrate AI. The starter kit is based on congatec hardware and Hacarus software, and can be deployed and tested in any GigE and USB 3.x environment. Measuring 173 x 88 x 21.7 mm (6.81 x 3.46 x 0.85 in), the system has a DC voltage input from 9V to 32V.