Next Meetup

Beyond pattern recognition for human-in-the-Loop & Meta-Learning
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: Build a state-of-the-art NLP pipeline in seconds. * Beyond pattern recognition for human-in-the-Loop: the AI clinician (Aldo Faisal) Abstract: The quick wins of deep learning methods have demonstrated the power of machine learning for supervised learning problems. While our attention is still on perceptual abilities that support human decision makers, the challenge of how to have AI mimic human cognitive abilities and integrate them with human decision makers remains unclear. Our application domain is healthcare as it illustrates all the aspects that make AI and human-in-the-Loop AI a hard problem. We will present recent work from our lab, including the AI clinician (Komorowski et Faisal, 2018, Nature Medicine). Bio: Dr Faisal is Reader in Neurotechnology (US equivalent: Associate Professor, tenured) jointly at the Dept. of Bioengineering and the Dept. of Computing at Imperial College London, where he leads the Brain & Behaviour Lab. Aldo is also Director of the Behaviour Analytics Lab at the Data Science Institute. He is also Associate Investigator at the MRC London Institute of Medical Sciences and is affiliated faculty at the Gatsby Computational Neuroscience Unit (University College London). * Meta-Learning to Make Smart Inferences from Small Data (Sam Ritter) Abstract: Deep learning methods have enabled enormous gains in predictive accuracy when large labeled datasets are available; however, they are not applicable in settings where only a few relevant data points can be obtained. In this talk, I will discuss meta-learning: the process whereby a learning system acquires background knowledge that enables it to later make powerful inferences from only a few examples. This old idea from psychology and computer science has recently resurfaced in the context of modern deep learning, producing stunning advances in the low-shot learning capabilities of neural networks, in both supervised and reinforcement learning settings. The talk will cover foundational concepts of meta-learning, key seminal results on meta-learning and meta-reinforcement learning with deep networks, interpretability of meta-learning systems, and -as time permits- the current frontier of meta-learning research. Bio: Sam is a research scientist at DeepMind and PhD candidate at the Princeton Neuroscience Institute. His work at the intersection of neuroscience and deep learning has the twin objectives of understanding human cognition and building useful intelligent systems. His recent work focuses on meta-reinforcement learning, deep learning interpretability, and episodic memory in deep reinforcement learning agents. Sam is a former Graduate Fellow of the US National Science Foundation and his work has been covered in the Economist, the Wall Street Journal, and other venues.

1 Angel Ln

1 Angel Ln · London

2 comments

What we're about

The London Machine Learning Meetup is the largest machine learning community in Europe. We're a group of scientists and engineers interested in Machine Learning, AI and Natural Language Processing. We aim to bring together practitioners from industry and academia to listen to each other's work. Our focus is purely technical.

Previous speakers have included researchers such as Juergen Schmidhuber, Yoshua Bengio and Andrej Karpathy.

Youtube: https://www.youtube.com/channel/UCpwC9QC0lW... (https://www.youtube.com/channel/UCpwC9QC0lWaEJ85MoMRFvrA/videos)

Twitter: #MLLondon

Members (7,425)

Photos (21)