AI in Action - Computer Vision Series #3

Join us on Wednesday 2nd of September at 5pm CET as we bring you the third of our Computer Vision series in the AI in Action Virtual Meetup.

Please register to view the link.

SPEAKERS

1. Justin Shenk, Co-Founder & CTO at VisioLab

Title: "Learning with limited labeled data".

VisioLab brings vision-based food recognition to canteens to enable fast, scalable checkouts. To make usage simple for canteen owners, dishes have to be recognized with only a few labeled images, far less than the thousands typically used for image recognition. This talk will highlight how they address this challenge: from data augmentation strategies and active learning with customer feedback to models trained in the cloud and deployed on the edge.

2. Ganesh Sistu, Computer Vision and Deep Learning Expert at Valeo Vision Systems.

Title: "How Deep Learning is playing a crucial role in advanced autonomous driving applications"

In recent years, Deep Learning, a branch of machine learning,
has revolutionized vehicle’s perception abilities and made the automated cars real. Ganesh will present how Deep Learning is playing
a crucial role in advanced autonomous driving applications like object detection, semantic segmentation, motion estimation and camera lens disturbance detection. He will also give an overview of how they build fisheye camera-based visual perception solutions for
automated parking systems and present a complex life cycle of deep learning projects.

3. Ben Taylor, Chief AI Evangelist at DataRobot

Title: "Teaching CV systems to learn and comprehend like a human"

As AI workloads have expanded beyond experimental notebooks, DataRobot has developed data ingest and MLOps to ensure trust and reliability for the enterprise. In this talk, Ben will explore some of the storytelling methods that work for deep learning and discuss their work in Computer Vision and the latest RL/DL techniques. He will also explore the concept of intelligence and a better Turing test for machines that finally think.