Machine learning and deep learning
Workshops and Videos
General
- Deep learning with Keras part 1 by Ariel Rokem [Video, ca. 2 hrs]
- Deep learning with Keras part 2 by Ariel Rokem [Video, ca. 2 hrs]
- Machine learning with scikit-learn 1 by Jake Vanderplas within Neurohackweek [Jupyter Notebook]
- Machine learning with scikit-learn 2 by Jake Vanderplas within Neurohackweek 2017 [Video, ca. 80 mins]
- Machine learning with scikit-learn 3 by Jake Vanderplas within Neurohackademy [Video, ca. 140 mins]
- Deep learning and machine learing tutorials from the Montreal Artificial Intelligence and Neuroscience conference, Montreal 2018 by many authors. [Jupyter notebook, 2 days]
- TensorFlow 2.0 Complete Course - Python Neural Networks for Beginners by Tim Ruscica (Tech with Tim) [Video, 7 hrs]
Neuroimaging-related
Machine learning in general
- Machine learning for neuroimaging by Chris Holdgraf within Neurohackweek 2017 [Video, ca. 1 hr]
- Machine learning in neuroimaging by Gael Varoquaux within Neurohackademy 2018 [Video, ca. 2hrs 40 mins]
- Synthesizing fMRI using generative adversarial networks: cognitive neuroscience applications, promises and pitfalls by Sanmi Koyejo within Neurohackademy 2018 [Video, ca. 1 hr]
Deep learning
- OHBM DL Educational Course 2018-2020 (https://brainhack101.github.io/IntroDL/) [Video and Jupyter Notebook, 3 days]
- Introduction to Keras & Interpretability Methods by Andrew Doyle within MAIN 2018 Hands-on DL course [Jupyter notebook]
- Brain Segmentation in Keras by Thomas Funck within MAIN 2018 Hands-on DL course [Jupyter notebook]
Software
They are divided in sub-sections depending on the language they use.
pyMVPA
??? example "pyMVPA - Intended to ease statistical learning analyses of large datasets." - code repository - website - documentation - programming language: [python] - tags: - [paper] - RRID:SCR_006099 - tutorial: - URL - level: [beginner] - type: [notebook]
nilearn
Nilearn is a Python module for fast and easy statistical learning on NeuroImaging data.
neuropredict
neuropredict is an easy to use Python tool for comprehensive evaluation of predictive power of popular ML techniques for features-to-target prediction (such as biomarkers to disease and similar variations)
brainIAK
BrainIAK applies advanced machine learning methods and high-performance computing to analyzing neuroimaging data. We also have tutorials that cover topics from basics to advanced techniques.
The Decoding Toolbox (TDT)
TDT is an easy to use, fast and versatile Matlab toolbox for the multivariate analysis of functional and structural MRI data. It contains searchlight, region-of-interest, and whole-brain analyses, as well as many feature selection and parameter selection methods including recursive feature elimination.
ProNTo
PRoNTo is the Pattern Recognition for Neuroimaging Toolbox developed at UCL (UK). The toolbox is based on pattern recognition techniques for the analysis of neuroimaging data.
RSA toolbox
A Matlab toolbox for representational similarity analysis
Pattern components modelling (PCM) toolbox
Pattern component modeling (PCM) is a practical Bayesian approach for evaluating representational models - models that specify how complex patterns of neural activity relate to visual stimuli, motor actions, or abstract thoughts.
cvMANOVA
MVPA by cross-validated MANOVA, which is proposed as a replacement of classification.