Towards Explainable AI & Point Cloud Based Deep Learning Methods

Please note that Photo ID will be required. Please can attendees ensure their meetup profile name includes their full name to ensure entry.

Agenda:
- 18:30: Doors open, pizza, beer, networking
- 19:00: First talk
- 19:45: Break & networking
- 20:00: Second talk
- 20:45: Close

*Sponsors*
Man AHL: At Man AHL, we mix machine learning, computer science and engineering with terabytes of data to invest billions of dollars every day.

Evolution AI: Machines that Read - get answers from your text data.

* Towards Explainable AI (Dr Anita Faul)

Abstract: The talk will address: building models simple enough to be explainable, but complex enough to explain the data; adaptable to new data arriving; estimating the confidence in predictions; generating the model space.

A technique is introduced which builds the one-dimensional model space consisting of one basis function. More basis functions are added, if informed so by the data. Basis functions can be deleted if a more suitable one is found. The possible choices are provided from a dictionary. A geometric explanation is given, how the goodness of basis functions for the model is assessed. This technique can update the model, if new data arrives, which is suitable when a sparse model is needed for example due to limited up-link and/or down-link bandwidth. It can also assess the confidence in predictions using the expected change in likelihood. The talk concludes outlining work in progress on the generation of basis functions.

Bio: Anita Faul came to Cambridge after studying two years in Germany. She studied Part II & Part III Maths at Churchill College, Cambridge. This was followed by a PhD on the Faul-Powell Algorithm for Radial Basis Function Interpolation under the supervision of Prof Mike Powell. This collaboration resulted in an Erdős number of 4 (Powell - Beatson - Chui - Erdős). Current projects are on ML techniques. In teaching she enjoys to bring out the underlying, connecting principles of algorithms which is the emphasis of her book on Numerical Analysis.

* The use of point cloud based deep learning methods to learn 3D printing manufacturing intuition in the Oqton FactoryOS (Benjamin Schrauwen)

Abstract: Manufacturing is being profoundly disrupted: all product categories are being reimagined with the further digitalization of goods, times to market are decreasing with an ever acceleration of innovation, new disruptive production methods are coming of age, and the global workforce is shifting. There is one important scarce resource that is the major bottleneck in the current approach: manufacturing engineering expertise. This expertise is what is required to design the machine (ie. factory) that will build your product. The goal of the Oqton FactoryOS is to create an integrated system, connecting machines, people and AI agents to create a closed loop learning and reason system, with the goal to discover and capture manufacturing intuition, using it to assist and automate engineering workflows. We will give an overview of the FactoryOS, and detail how we use point cloud based deep learning methods to capture 3D printing manufacturing intuition on 3D geometry. Oqton is a global startup with R&D offices in Belgium, Copenhagen, Denmark, China and USA.

Bio: Benjamin Schrauwen is CTO and co-founder of Oqton Inc, a global startup solving today’s manufacturing industry challenges with an AI-powered factory operating system. Schrauwen was a professor in ML & robotics at Ghent University where he co-authored more than 200 peer reviewed publications & was leading or part of several large international research programs. Many of his PhD students are now running successful AI companies world-wide. Schrauwen holds a doctorate in engineering from Ghent University with an emphasis on hardware implementations of ML methods, and two Master’s degrees in computer science and computer engineering from Antwerp University & Ghent University. He was a visiting scientist at Harvard.