This module provides an introduction to the problem of speech recognition using neural models, emphasizing the CTC loss for training and inference when input and output sequences are of different lengths. It also covers beam search for use during inference, and how that procedure may be modeled at training time using a Graph Transformer Network.

Neuromatch Academy aims to introduce traditional and emerging tools of computational neuroscience to trainees.

This short course covers Hypothes.is, an annotation tool that enables users to collaboratively annotate course readings and other internet resources.

Features of Hypothes.is:

This course provides several visual walkthroughs documenting how to execute various processes in brainlife.io, an open-source, free and secure reproducible neuroscience analysis platform. The platform allows to analyze Magnetic Resonance Imaging (MRI), electroencephalography (EEG) and magnetoencephalography (MEG) data. Data can either be uploaded from local computers or imported from public archives such as OpenNeuro.org.

As technological improvements continue to facilitate innovations in the mental health space, researchers and clinicians are faced with novel opportunities and challenges regarding study design, diagnoses, treatments, and follow-up care. This course includes a lecture outlining these new developments, as well as a workshop which introduces users to Synapse, an open-source platform for collaborative data analysis. 

This course consists of one lesson and one tutorial, focusing on the neural connectivity measures derived from neuroimaging, specifically from methods like functional magnetic resonance imaging (fMRI) and diffusion-weighted imaging (DWI). Additional tools such as tractography and parcellation are discussed in the context of brain connectivity and mental health. The tutorial leads participants through the computation of brain connectomes from fMRI data. 

The goal of this module is to work with action potential data taken from a publicly available database. You will learn about spike counts, orientation tuning, and spatial maps. The MATLAB code introduces data types, for-loops and vectorizations, indexing, and data visualization.

As technological improvements continue to facilitate innovations in the mental health space, researchers and clinicians are faced with novel opportunities and challenges regarding study design, diagnoses, treatments, and follow-up care. This course includes a lecture outlining these new developments, as well as a workshop which introduces users to Synapse, an open-source platform for collaborative data analysis. 

This workshop provides basic knowledge on personalized brain network modeling using the open-source simulation platform The Virtual Brain (TVB). Participants will gain theoretical knowledge and apply this knowledge to construct brain models, process multimodal neuroimaging data for reconstructing individual brains, run simulations, and use supporting neuroinformatics tools such as collaboratories, pipelines, workflows, and data repositories.

The Neurodata Without Borders: Neurophysiology project (NWB, https://www.nwb.org/) is an effort to standardize the description and storage of neurophysiology data and metadata. NWB enables data sharing and reuse and reduces the energy-barrier to applying data analytics both within and across labs. Several laboratories, including the Allen Institute for Brain Science, have wholeheartedly adopted NWB.

This course consists of a three-part session from the second day of INCF's Neuroinformatics Assembly 2023. The lessons describe various on-going efforts within the fields of neuroinformatics and clinical neuroscience to adjust to the increasingly vast volumes of brain data being collected and stored.

Neurohackademy is a two-week hands-on summer institute in neuroimaging and data science held at the University of Washington eScience Institute. Participants learn about technologies used to analyze human neuroscience data, and to make analyses and results shareable and reproducible.

This course contains sessions from the first day of INCF's Neuroinformatics Assembly 2022.

The importance of Research Data Management in the conduct of open and reproducible science is better understood and technically supported than ever, and many of the underlying principles apply as much to everyday activities of a single researcher as to large-scale, multi-center open data sharing.

This course offers lectures on the origin and functional significance of certain electrophysiological signals in the brain, as well as a hands-on tutorial on how to simulate, statistically evaluate, and visualize such signals. Participants will learn the simulation of signals at different spatial scales, including single-cell (neuronal spiking) and global (EEG), and how these may serve as biomarkers in the evaluation of mental health data.

This course corresponds to the second session of INCF's Neuroinformatics Assembly 2023. This series of talks continues a discussion of FAIR principles from the first session, with a greater emphasis on brain data (humans and animals) atlases for data analysis and integation. 

This course, consisting of one lecture and two workshops, is presented by the Computational Genomics Lab at the Centre for Addiction and Mental Health and University of Toronto. The lecture deals with single-cell and bulk level transciptomics, while the two hands-on workshops introduce users to transcriptomic data types (e.g., RNAseq) and how to perform analyses in specific use cases (e.g., cellular changes in major depression). 

This course consists of several lightning talks from the second day of INCF's Neuroinformatics Assembly 2023. Covering a wide range of topics, these brief talks provide snapshots of various neuroinformatic efforts such as brain-computer interface standards, dealing with multimodal animal MRI datasets, distributed data management, and several more. 

This course consists of brief tutorials on OpenNeuro.org, a free and open platform for analyzing and sharing neuroimaging data. During this course, you will learn how to deal with your neuroscientific datasets using OpenNeuro.org for operations such as uploading and version control, as well as how to analyze and share your data. 

This course provides several visual walkthroughs documenting how to execute various processes in brainlife.io, an open-source, free and secure reproducible neuroscience analysis platform. The platform allows to analyze Magnetic Resonance Imaging (MRI), electroencephalography (EEG) and magnetoencephalography (MEG) data. Data can either be uploaded from local computers or imported from public archives such as OpenNeuro.org.