Skip to main content

Much like neuroinformatics, data science uses techniques from computational science to derive meaningful results from large complex datasets. In this session, we will explore the relationship between neuroinformatics and data science, by emphasizing a range of data science approaches and activities, ranging from the development and application of statistical methods, through the establishment of communities and platforms, and through the implementation of open-source software tools. Rather than rigid distinctions, in the data science of neuroinformatics, these activities and approaches intersect and interact in dynamic ways. Together with a panel of cutting-edge neuro-data-scientist speakers, we will explore these dynamics

 

This lecture covers self-supervision as it relates to neural data tasks and the Mine Your Own vieW (MYOW) approach.

Difficulty level: Beginner
Duration: 25:50
Speaker: : Eva Dyer

Estefany Suárez provides a conceptual overview of the rudiments of machine learning, including its bases in traditional statistics and the types of questions it might be applied to.

 

The lesson was presented in the context of the BrainHack School 2020.

Difficulty level: Beginner
Duration: 01:22:18
Speaker: :

Jake Vogel gives a hands-on, Jupyter-notebook-based tutorial to apply machine learning in Python to brain-imaging data.

 

The lesson was presented in the context of the BrainHack School 2020.

Difficulty level: Beginner
Duration: 02:13:53
Speaker: :

Gael Varoquaux presents some advanced machine learning algorithms for neuroimaging, while addressing some real-world considerations related to data size and type.

 

The lesson was presented in the context of the BrainHack School 2020.

Difficulty level: Beginner
Duration: 01:17:14
Speaker: :

This lesson from freeCodeCamp introduces Scikit-learn, the most widely used machine learning Python library.

Difficulty level: Beginner
Duration: 02:09:22
Speaker: :

Dr. Guangyu Robert Yang describes how Recurrent Neural Networks (RNNs) trained with machine learning techniques on cognitive tasks have become a widely accepted tool for neuroscientists. In comparison to traditional computational models in neuroscience, RNNs can offer substantial advantages at explaining complex behavior and neural activity patterns. Their use allows rapid generation of mechanistic hypotheses for cognitive computations. RNNs further provide a natural way to flexibly combine bottom-up biological knowledge with top-down computational goals into network models. However, early works of this approach are faced with fundamental challenges. In this talk, Dr. Guangyu Robert Yang discusses some of these challenges, and several recent steps that we took to partly address them and to build next-generation RNN models for cognitive neuroscience.​

Difficulty level: Beginner
Duration: 00:51:12
Speaker: :

As models in neuroscience have become increasingly complex, it has become more difficult to share all aspects of models and model analysis, hindering model accessibility and reproducibility. In this session, we will discuss existing resources for promoting FAIR data and models in computational neuroscience, their impact on the field, and the remaining barriers. This lecture covers how FAIR practices affect personalized data models, including workflows, challenges, and how to improve these practices.

Difficulty level: Beginner
Duration: 13:16
Speaker: : Kelly Shen

Much like neuroinformatics, data science uses techniques from computational science to derive meaningful results from large complex datasets. In this session, we will explore the relationship between neuroinformatics and data science, by emphasizing a range of data science approaches and activities, ranging from the development and application of statistical methods, through the establishment of communities and platforms, and through the implementation of open-source software tools. Rather than rigid distinctions, in the data science of neuroinformatics, these activities and approaches intersect and interact in dynamic ways. Together with a panel of cutting-edge neuro-data-scientist speakers, we will explore these dynamics

 

This lecture covers how brainlife.io works, and how it can be applied to neuroscience data.

Difficulty level: Beginner
Duration: 10:14
Speaker: : Franco Pestilli

As a part of NeuroHackademy 2020, Tara Madhyastha (University of Washington), Andrew Crabb (AWS), and Ariel Rokem (University of Washington) give a lecture on Cloud Computing, focusing on Amazon Web Services

 

This video is provided by the University of Washington eScience Institute.

 

Difficulty level: Beginner
Duration: 01:43:59
Speaker: :

Shawn Brown presents an overview of CBRAIN, a web-based platform that allows neuroscientists to perform computationally intensive data analyses by connecting them to high-performance-computing facilities across Canada and around the world.

 

This talk was given in the context of a Ludmer Centre event in 2019.

 

 

Difficulty level: Beginner
Duration: 56:07
Speaker: :
Course:

Longitudinal Online Research and Imaging System (LORIS) is a web-based data and project management software for neuroimaging research studies. It is an open source framework for storing and processing behavioural, clinical, neuroimaging and genetic data. LORIS also makes it easy to manage large datasets acquired over time in a longitudinal study, or at different locations in a large multi-site study.

Difficulty level: Beginner
Duration: 0:35
Speaker: : Samir Das

This talk highlights a set of platform technologies, software, and data collections that close and shorten the feedback cycle in research. 

Difficulty level: Beginner
Duration: 57:52
Speaker: : Satrajit Ghosh

An agent for reproducible neuroimaging

Difficulty level: Beginner
Duration: 1:00:10
Speaker: : David Kennedy

Lecture on functional brain parcellations and a set of tutorials on bootstrap agregation of stable clusters (BASC) for fMRI brain parcellation which were part of the 2019 Neurohackademy, a 2-week hands-on summer institute in neuroimaging and data science held at the University of Washington eScience Institute.

Difficulty level: Advanced
Duration: 50:28
Speaker: : Pierre Bellec

This lecture was part of the 2019 Neurohackademy, a 2-week hands-on summer institute in neuroimaging and data science held at the University of Washington eScience Institute.

Difficulty level: Beginner
Duration: 1:03:07
Speaker: : Russell Poldrack

This lecture was part of the 2019 Neurohackademy, a 2-week hands-on summer institute in neuroimaging and data science held at the University of Washington eScience Institute.

Difficulty level: Beginner
Duration: 55:39
Speaker: : Angela Laird
Course:

BioImage Suite is an integrated image analysis software suite developed at Yale University. BioImage Suite has been extensively used at different labs at Yale since about 2001.

Difficulty level: Beginner
Duration: 01:47
Speaker: : BioImage Suite
Course:

Fibr is an app for quality control of diffusion MRI images from the Healthy Brain Network, a landmark mental health study that is collecting MRI images and other assessment data from 10,000 New York City area children. The purpose of the app is to train a computer algorithm to analyze the Healthy Brain Network dataset. By playing fibr, you are helping to teach the computer which images have sufficiently good quality and which images do not. 

Difficulty level: Beginner
Duration: 02:26
Speaker: : Ariel Rokem

Since their introduction in 2016, the FAIR data principles have gained increasing recognition and adoption in global neuroscience.  FAIR defines a set of high-level principles and practices for making digital objects, including data, software, and workflows, Findable, Accessible,  Interoperable, and Reusable.  But FAIR is not a specification;  it leaves many of the specifics up to individual scientific disciplines to define.  INCF has been leading the way in promoting, defining, and implementing FAIR data practices for neuroscience.  We have been bringing together researchers, infrastructure providers, industry, and publishers through our programs and networks.  In this session, we will hear some perspectives on FAIR neuroscience from some of these stakeholders who have been working to develop and use FAIR tools for neuroscience.  We will engage in a discussion on questions such as:  how is neuroscience doing with respect to FAIR?  What have been the successes?  What is currently very difficult? Where does neuroscience need to go? This lecture covers the needs and challenges involved in creating a FAIR ecosystem for neuroimaging research.

Difficulty level: Beginner
Duration: 12:26
Speaker: : Camille Maumet

Over the last three decades, neuroimaging research has seen large strides in the scale, diversity, and complexity of studies, the open availability of data and methodological resources, the quality of instrumentation and multimodal studies, and the number of researchers and consortia. The awareness of rigor and reproducibility has increased with the advent of funding mandates, and with the work done by national and international brain initiatives. This session will focus on the question of FAIRness in neuroimaging research touching on each of the FAIR elements through brief vignettes of ongoing research and challenges faced by the community to enact these principles. This lecture covers the NIDM data format within BIDS to make your datasets more searchable, and how to optimize your dataset searches.

Difficulty level: Beginner
Duration: 12:33
Speaker: : David Keator