论文信息 - Machine Learning and Brain Imaging: Opportunities and Challenges

Machine Learning and Brain Imaging: Opportunities and Challenges

Machine learning approaches may provide ways to link brain activation patterns to behavior at an individual-subject level. Using a comparative performance analysis, Jollans and colleagues (Neuroimage, 2019) highlight in a recent paper key considerations when applying machine learning algorithms to neuroimaging data.

Rayus Kuplicki | Martin P Paulus | Hung-Wen Yeh

[1] Daniel Durstewitz,et al. Deep neural networks in psychiatry , 2019, Molecular Psychiatry.

[2] Alexander Allen,et al. Benchmarking Automatic Machine Learning Frameworks , 2018, ArXiv.

[3] Rich Caruana,et al. Ensemble selection from libraries of models , 2004, ICML.

[4] Robert Tibshirani,et al. The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd Edition , 2001, Springer Series in Statistics.

[5] M. Paulus,et al. The Challenges and Opportunities of Small Effects: The New Normal in Academic Psychiatry. , 2019, JAMA psychiatry.

[6] Antoine Grigis,et al. Quantifying performance of machine learning methods for neuroimaging data , 2019, NeuroImage.

[7] Eric J Topol,et al. High-performance medicine: the convergence of human and artificial intelligence , 2019, Nature Medicine.

[8] Toniann Pitassi,et al. The reusable holdout: Preserving validity in adaptive data analysis , 2015, Science.

[9] Scott Fortmann-Roe,et al. Understanding the bias-variance tradeoff , 2012 .