Maties Machine Learning (MML) is a seminar series and discussion forum with the goal of bringing together people working on machine learning at Stellenbosch University. We meet roughly every second week for short talks on people’s current work, some ML-related topic, or open discussions. The idea is to get to know what others are working on and to strengthen machine learning research at Stellenbosch.
11 October 2019, 13:00-13:50 in K303 (Knowledge Centre, Engineering)
Jacomine Grobler - Supply chain data science: unleashing AI in the business domain
Effective supply chain management is one of the most important enablers for operational success of a company. Customers expect to receive the right product, at the right time, at the right place, in perfect condition. This goal is, however, challenging to achieve in an ever changing business and technology environment. Fortunately, more and more data is being created every day that can be used to improve decision making in a supply chain. This talk will touch on various case studies from the logistics, manufacturing and agricultural industries, that will be used to show the value that data science can add in the process of converting raw data to effective business decision making.
Matthew Baas - Style transfer: Visual art with deep learning
Most methods for making visual art using deep learning involve style transfer, where usually a random input image is trained to minimize a style loss and a content loss in order for the image to eventually have the style of one image and the content of another. For a competition of the AI Expo Africa 2019, I tried to swap this usual order around and see if, given as input a stylistic painting (like a Van Gogh) as a content image, can we remove the artist’s unique style and leave the fundamental content of the painting behind. This resulted in the winning artwork for the AI art competition hosted by Zindi for the AI Expo Africa, where the artwork was auctioned off. This talk will give an brief description of style transfer and the competition, as well explore the method I used to generate the artworks.
25 October 2019, 13:00-13:50 in K303 (Knowledge Centre, Engineering)
We will have supervisor spotlights by:
- Steve Kroon
- Willie Brink
- Hanno Coetzer
- David Hofmeyr