In this talk I introduce the neural statistician as an approach for meta learning. The neural statistician learns to appropriately summarise datasets through a learnt statistic vector. This can be used for few shot learning, by computing the statistic vectors for the presented data, and using these statistics as context variables for one-shot classification and generation. I will show how we can generalise the neural statistician to a context aware learner that learns to characterise and combine independently learnt contexts. I will also demonstrate an approach for meta-learning data augmentation strategies.
Acknowledgments: This work is joint work with Harri Edwards, Antreas Antoniou, and Conor Durkan.
Biography: Amos is a reader in Informatics, with wide-ranging interests all over machine learning. He has worked on advanced Monte Carlo methods, time series, computational neuroscience, Gaussian processes and other Bayesian models, and, more recently, on deep learning. His group tends to go for real applications, and has built applied systems for areas from computer vision through astronomy to board games.