Machine Learning and Interpretation in Neuroimaging

This book constitutes the revised selected papers from the 4th International Workshop on Machine Learning and Interpretation in Neuroimaging, MLINI 2014, held in Montreal, QC, Canada, in December 2014 as a satellite event of the 11th annual conference on Neural Information Processing Systems, NIPS 2014.

The 10 MLINI 2014 papers presented in this volume were carefully reviewed and selected from 17 submissions. They were organized in topical sections named: networks and decoding; speech; clinics and cognition; and causality and time-series. In addition, the book contains the 3 best papers presented at MLINI 2013.

Includes supplementary material: sn.pub/extras

Inhalt
Networks and Decoding.- Multi-Task Learning for Interpretation of Brain Decoding Models.- The New Graph Kernels on Connectivity Networks for Identification of MCI.- Mapping Tractography Across Subjects.- Speech.- Automated speech analysis for psychosis evaluation.- Combining different modalities in classifying phonological categories.- Clinics and cognition.- Label-alignment-based Multi-task Feature Selection for Multimodal Classification of Brain Disease.- Leveraging Clinical Data to Enhance Localization of Brain Atrophy.- Estimating Learning Effects: A Short-Time Fourier Transform Regression Model for MEG Source Localization.- Causality and time-series.- Classification-based Causality Detection in Time Series.- Fast and Improved SLEX Analysis of High-dimensional Time Series.- Best paper awards: MLINI 2013.- Predicting Short-Term Cognitive Change from Longitudinal Neuroimaging Analysis.- Hyperalignment of Multi-Subject fMRI Data by Synchronized Projections.- An oblique approach to prediction of conversion to Alzheimer's Disease with multikernel Gaussian Processes.