Abstract: Most deployed Machine Learning models use Supervised Learning powered by human training data. Selecting the right data for human review is known as Active Learning. This talk will introduce a set of Active Learning methods that help you understand where your model is currently confused (Uncertainty Sampling) and to identify gaps in your model knowledge (Diversity Sampling). We'll cover techniques that are only a few lines of code through to techniques that build on recent advances in transfer learning. We'll use code examples from my open-source PyTorch Active Learning library (https://github.com/rmunro/pytorch_active_learning) that you can implement within your own applications.
Bio: Robert Munro is an expert in combining Human and Machine Intelligence, working with Machine Learning approaches to Text, Speech, Image, and Video Processing. Robert has founded several AI companies, building some of the top teams in Artificial Intelligence. He has worked in many diverse environments, from Sierra Leone, Haiti and the Amazon, to London, Sydney and Silicon Valley, in organizations ranging from startups to the United Nations. He has shipped Machine Learning Products at startups and at/with Amazon, Google, IBM & Microsoft.
Robert has published more than 50 papers on Artificial Intelligence and is a regular speaker about technology in an increasingly connected world. He has a PhD from Stanford University. Robert is the author of Human-in-the-Loop Machine Learning (Manning Publications, 2020)