Task relevant autoencoding enhances machine learning for human neuroscience.

In human neuroscience, machine learning can help reveal lower-dimensional neural representations relevant to subjects' behavior. However, state-of-the-art models typically require large datasets to train, and so are prone to overfitting on human neuroimaging data that often possess few samples but many input dimensions. Here, we capitalized on the fact that the features we seek in human neuroscience are precisely those relevant to subjects' behavior rather than noise or other irrelevant factors.

Strategic use of reminders in an 'intention offloading' task: Do individuals with autism spectrum conditions compensate for memory difficulties?

Previous studies have found that individuals with autism spectrum conditions (ASC) can have difficulty remembering to execute delayed intentions. However, in these studies participants were prevented from setting external reminders, whereas the use of such reminders in everyday life is commonplace (e.g.