Towards a Neural Statistician

7 Jun 2016  ·  Harrison Edwards, Amos Storkey ·

An efficient learner is one who reuses what they already know to tackle a new problem. For a machine learner, this means understanding the similarities amongst datasets. In order to do this, one must take seriously the idea of working with datasets, rather than datapoints, as the key objects to model. Towards this goal, we demonstrate an extension of a variational autoencoder that can learn a method for computing representations, or statistics, of datasets in an unsupervised fashion. The network is trained to produce statistics that encapsulate a generative model for each dataset. Hence the network enables efficient learning from new datasets for both unsupervised and supervised tasks. We show that we are able to learn statistics that can be used for: clustering datasets, transferring generative models to new datasets, selecting representative samples of datasets and classifying previously unseen classes. We refer to our model as a neural statistician, and by this we mean a neural network that can learn to compute summary statistics of datasets without supervision.

PDF Abstract


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Few-Shot Image Classification OMNIGLOT - 1-Shot, 20-way Neural Statistician Accuracy 93.2% # 16
Few-Shot Image Classification OMNIGLOT - 1-Shot, 5-way Neural Statistician Accuracy 98.1 # 14
Few-Shot Image Classification OMNIGLOT - 5-Shot, 20-way Neural Statistician Accuracy 98.1% # 16
Few-Shot Image Classification OMNIGLOT - 5-Shot, 5-way Neural Statistician Accuracy 99.5 # 12


No methods listed for this paper. Add relevant methods here