PRNI (Pattern Recognition in NeuroImaging) is a great little conference, focused on machine learning neuroimaging applications (lots of fMRI, but also EEG, MEG, etc.). It has aspects of both engineering conferences, with proceedings (you can submit a short paper - and there's still time; the deadline isn't until
PR4NI tutorial on Sunday, "A new MVPA-er’s guide to fMRI datasets". Here's the abstract: "fMRI datasets have properties which make the application of machine learning (pattern recognition) techniques challenging – and exciting! This talk will introduce some of the properties most relevant for MVPA, particularly the strong temporal and spatial dependencies inherent in BOLD imaging. These dependencies mean that some fMRI experimental designs are more suitable for MVPA than others, due, for example, to how the tasks are distributed within scanner runs. I will also introduce some of the necessary analysis choices, such as how to summarize the response in time (e.g., convolving with an HRF), which brain areas to include, and feature selection techniques."
I also organized a symposium, which will be Tuesday morning, "High resolution fMRI via multiband (SMS) acquisition: opportunities and limitations". This symposium isn't about MVPA, but rather the practicalities of high-resolution fMRI: working with fMRI datasets with small voxels (say, 2 mm or so isotropic) and multiband acquisitions is different than single-shot fMRI datasets with 3 mm voxels. I will put up a separate post with talk and speaker details soon - I think it'll be a great session. Finally, I'll be presenting a poster sometime, about MVPA-ish twin similarity analyses using parts of the HCP dataset.