Dr. Thomas Wollmann
In recent years, there have been various efforts to product thinking and decentralized data loading using data meshes. However in deep learning, data loading is still challenging to master at scale. In this talk, we present our decentralized data loading solution and show why flexibility and collaboration is key to enable novel ML use cases. We hope to make large-scale model training accessible to a wider community and move towards more sustainable ML.
While most people prefer writing free-form text, it is easier to process structured data. This is a dilemma which many companies face as did our customer felmo (a mobile vet service), when asking users to input appointment reasons for vet visits. We were able to leverage a Sentence Bert architecture to help them convert these to structured data, which they can now use to improve their appointment preparation and scheduling. We will share our learnings from applying Sentence Bert to this task.
Joana Raquel Silva
As a manufacturer, visual inspection is a crucial part of keeping the quality of our products up to high levels. Above that many new applications can be done by making use of deep learning in combination with computer vision. Deep learning models can be industrialized with the Visual Perception Provider (VPP) which is a service developed in-house at Tires. The talk is about the reasoning, why we decided to go that route, and about what we are doing. Also, some use cases done with the Visual Perception Provider will be demonstrated.
Object detection with a monocular camera is extremely important for the automotive industry as obtaining LiDAR data is not only expensive but getting them labelled is extremely difficult. Previous works have tried removing dependencies of LiDAR but only for inference, they still needed LiDAR data during training. In our work, there are no requirements of LiDAR data annotations. Yet the major advancement in our work compared to that of the previous works is that previously 3D detections were initially performed by stacking two different deep learning networks i.e., a 2D object detection network followed by projecting them to Bird’s Eye View (BEV) to get the depth from a depth prediction network. The presented approach instead combines the two different deep learning networks in one single feed-forward pass with a common backbone network separating out at heads. Having two different heads with common backbone helps the backpropagation learn the weights by mutually improving the two different tasks of 2D object detection and depth prediction simultaneously, thus giving better and faster output as the previous works.
Dimas Muñoz Montesinos
Unicode has unified characters from world languages, symbols and emoji into a single standard enabling easy interoperable communications. However, in recent years the availability of similar symbols from diverse languages is being exploited to deceive users for malicious ends. Deep learning has given us the tool to prevent these attacks. You will be shown how this exploit works and how to detect and prevent it by training a Deep learning model to detect visual similarities between characters.
AI algorithms deteriorate and fail silently over time impacting the business’ bottom line. The talk is focused on learning how you should be monitoring machine learning in production. It is a conceptual and informative talk addressed to data scientists & machine learning engineers. We’ll learn about the types of failures, how to detect and address them.
Knowledge is everything!
Sign up for our newsletter to receive:
Yes, I would like to subscribe to the Deep Learning World Newsletter.