Optimizing Computer Vision with GLAIR - CitC Episode 280

Novan Parmonangan Simanjuntak, Head of Machine Learning and Artificial Intelligence Strategy at GLAIR joins host Jake Smith to discuss how GLAIR worked with Intel to optimize deep learning and inference for their computer vision solution. Novan talks about how the GLAIR crowd detection system is optimized for the Intel OpenVINO toolkit and ONNX Runtime enabling GLAIR to achieve a significant improvement in throughput. He also highlights how their solution runs on CPUs, helping their clients avoid using costly GPUs for their computer vision workloads. Novan discusses how this performance optimization can also be applied to many other different workloads to benefit customer of all kinds. Lastly, he and Jake talk about how AI models in the future will be able to solve any type of problem. Novan feels that as AI is democratized, it will become more ubiquitous throughout our lives and continue to drive transformation throughout the world. For more information, visit: https://glair.ai/ Follow Jake on Twitter at: https://twitter.com/jakesmithintel