Technical Insights

In most AI research today, deep neural networks (DNNs) are designed solely to improve prediction accuracy, often ignoring real-world constraints such as compute and memory requirements. Embedded vision developers typically prefer to use these state-of-the-art (SOTA) DNNs from the research […]

AI models that produce accurate results on test data are a necessary component of successful applications, but by themselves they are insufficient. In this talk, we delve into often-overlooked, but critical, elements required to create and sustain a robust application […]

Optix is a computer vision-based AI system that measures advertising and media exposures on mobile devices for real-time marketing optimization. Optix was initially developed as a cloud-based solution, but costs and limitations associated with relying entirely on the cloud drove […]

In this session we show how techniques of sequential optimization are applied to enable continual learning during run-time, as new observations flow in. The lightweight nature of these techniques, using only the new batches of observations for processing, allows for […]

Developers of machine-learning based computer vision applications often face difficulties obtaining sufficient data for training and evaluating models. In this talk, we explore the use of synthetic data techniques to overcome these challenges. We explain the “simulation-to-reality” gap and the […]

A cloud-to-edge deep learning pipeline is a fully automated conduit for training and deploying models to the edge. This enables quick model retraining and makes the solution more robust toward data shifts. Cloud-to-edge pipelines are pivotal for many applications, from […]