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 and AI. We aim to bring together practitioners from industry and academia to listen to each other's work. Previous speakers include Juergen Schmidhuber, Yoshua Bengio and Andrej Karpathy.

https://www.youtube.com/channel/UCpwC9QC0lWaEJ85MoMRFvrA/videos

Please subscribe to our Youtube channel to be notified when talks are uploaded.

Twitter: #MLLondon

Upcoming events (1)

Machine Learning in Computational Biology & Logic Tensor Networks

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. * Title: Machine learning in computational biology - exploiting symmetry (Gerton Lunter - University of Oxford) Abstract: Machine learning has made remarkable progress in modeling large and complex data sets. In parallel, since the sequencing of the human genome in 2001, biology has become an increasingly data-rich science. Biology therefore seems an obvious hunting ground for machine learning applications. I will argue that despite appearances, biology is still a relatively data-poor discipline, and perhaps fundamentally so, compared to familiar application areas such as image & speech analysis. This relative data poverty throws up some interesting challenges & I will discuss one solution, exploiting symmetries, that may have applications in other relatively data-poor applications. I will show some successful applications of machine learning to problems in biology ranging from improved understanding basic biology to personalized medicine. Bio: Gerton Lunter studied Maths in the Netherlands & worked in video signal processing at Philips Labs before in 2002 moving to Oxford & into computational biology, where he worked ever since. He is one of 4 co-founders of Genomics plc, a company that analyzes genetic data to find new drug targets. He divides his time between the company & the Centre for Computational Biology at the MRC Weatherall Institute of Molecular Medicine in Oxford, where he is Group Leader in Computational Biology & Artificial Intelligence. * Title: Logic Tensor Networks (Artur d'Avila Garcez - City, University of London) * Abstract: Deep learning has achieved great success at image & audio recognition, language modelling & multimodal learning. Recent results indicate that deep networks may not be robust or capable of extrapolation. To address the problem, much of the AI research has turned to neural networks capable of harnessing knowledge, including relational reasoning & use of external memory by recurrent networks. Neural-symbolic AI has sought to benefit from the integration of symbolic AI & neural computation for many years. In a neural-symbolic system, neural networks offer the machinery for efficient learning and computation, while symbolic knowledge representation & reasoning enables the use of prior knowledge, transfer learning & extrapolation, as well as producing explainable AI models. Neural-symbolic computing has found application in many areas including software systems specification, training & assessment in simulators, & the prediction of harm in gambling for consumer protection. I will introduce the principles of neural-symbolic computing as used in Logic Tensor Networks. I will identify applications where the neural-symbolic approach has been successful & will conclude by discussing the main challenges of the R&D of neural-symbolic AI for the next decade. * Bio: Prof Artur d’Avila Garcez, FBCS, is the Director of the Research Centre for Machine Learning at City, University of London & the Chair of The City Data Science Institute. He holds a Ph.D. in Computer Science (2000) from Imperial College London. He co-authored 2 books: Neural-Symbolic Cognitive Reasoning (Springer, 2009) and Neural-Symbolic Learning Systems (Springer, 2002), & has more than 150 peer-reviewed publications in Artificial Intelligence, Machine Learning, Neural Computing & Neural-Symbolic AI. In 2013, he designed & became the first course director of the MSc in Data Science at City University, London's leading Data Science masters

Photos (24)