![]() |
COOKIES: By using this website you agree that we can place Google Analytics Cookies on your device for performance monitoring. | ![]() |
University of Cambridge > Talks.cam > Isaac Newton Institute Seminar Series > Log Signatures and Neural Controlled Differential Equations
![]() Log Signatures and Neural Controlled Differential EquationsAdd to your list(s) Download to your calendar using vCal
If you have a question about this talk, please contact info@newton.ac.uk. TGMW89 - Unlocking Data Streams Neural Ordinary Differential Equations are the continuous time extension of residual networks. They combine two dominant modelling paradigms in Neural Networks and Differential Equations and result in a host of benefits over a standard neural net. However, being ODEs, their solution trajectory is uniquely defined by the initial state of the system. In the case of sequential data (e.g. a time series), it is imperative that the solution trajectory can be updated based on incoming data. In this talk we describe the Neural Controlled Differential Equation – which can be thought as ODE extension to an RNN - and depends continuously on the incoming data. We give experiments that demonstrate state-of-the-art performance across a range of modelling tasks, and go on to describe the application areas the model is expected to be of most utility. This talk is part of the Isaac Newton Institute Seminar Series series. This talk is included in these lists:
Note that ex-directory lists are not shown. |
Other listsDobson Group - General Interest CUSPE Forum Neuropsychiatry discussion groupOther talksProbabilistic machine learning as an algorithmic interface to weather model and environmental data Larmor Lecture - title to be confirmed Machine Learning for Weather Prediction The Millimetre Sky from the Atacama Cosmology Telescope How atomic-level understanding of biology helps us to design more effective drugs Designing brighter dyes for advanced fluorescence microscopy |