We refer to Table S2 for example questions from each a subset of clusters. Each participant first read the task instructions (see Figure S2), and completed a short comprehension test. The comprehension check was designed to test the participants' knowledge and understanding of key aspectsoftheexperiment. Once all players had joined, the group started the main experiment. In practice, data was collected in batches of around 20 groups (100 participants) in parallel.

We showthatourproposedmethod,MetaAuXiliaryLearning(MAXL),outperforms single-task learning on 7 image datasets, without requiring any additional data. We also show that MAXL outperforms several other baselines for generating auxiliary labels, and is even competitive when compared with human-defined auxiliary labels. The self-supervised nature of our method leads to a promising new direction towards automated generalisation. Source code can be found at https://github.com/lorenmt/maxl.

Then,itsamplesafixednumber of nodes by the calculated probability,and recursively conducts such procedure per layer toconstruct the whole computation graph.

First, we show the negativeresult that no strongly sublinear sized coresets existforlogisticregression.

Withaback-offstrategyin the SGD step and an elitist strategy in the evolution step, it guarantees that the best fitness in the population will never degrade.

Neural Information Processing Systems http://nips.cc/