This lecture covers advanced concept of energy based models. The lecture is a part of the Advanced energy based models modules of the the Deep Learning Course at NYU's Center for Data Science. Prerequisites for this course include: Energy-Based Models I, Energy-Based Models II, Energy-Based Models III, and an Introduction to Data Science or a Graduate Level Machine Learning course.

This lesson gives an introduction to deep learning, with a perspective via inductive biases and emphasis on correctly matching deep learning to the right research questions.

As a part of NeuroHackademy 2021, Noah Benson gives an introduction to Pytorch, one of the two most common software packages for deep learning applications to the neurosciences.

Learn how to use TensorFlow 2.0 in this full tutorial for beginners. This course is designed for Python programmers looking to enhance their knowledge and skills in machine learning and artificial intelligence.

Throughout the 8 modules in this course you will learn about fundamental concepts and methods in ML & AI like core learning algorithms, deep learning with neural networks, computer vision with convolutional neural networks, natural language processing with recurrent neural networks, and reinforcement learning.

In this hands-on tutorial, Dr. Robert Guangyu Yang works through a number of coding exercises to see how RNNs can be easily used to study cognitive neuroscience questions, with a quick demonstration of how we can train and analyze RNNs on various cognitive neuroscience tasks. Familiarity of Python and basic knowledge of Pytorch are assumed.

This lesson contains the first part of the lecture Data Science and Reproducibility. You will learn about the development of data science and what the term currently encompasses, as well as how neuroscience and data science intersect. 

In this second part of the lecture Data Science and Reproducibility, you will learn how to apply the awareness of the intersection between neuroscience and data science (discussed in part one) to an understanding of the current reproducibility crisis in biomedical science and neuroscience. 

In this lesson, you will learn about the current challenges facing the integration of machine learning and neuroscience. 

JupyterHub is a simple, highly extensible, multi-user system for managing per-user Jupyter Notebook servers, designed for research groups or classes. This lecture covers deploying JupyterHub on a single server, as well as deploying with Docker using GitHub for authentication.

This demonstration walks through how to import your data into MATLAB.

This lesson provides instruction regarding the various factors one must consider when preprocessing data, preparing it for statistical exploration and analyses. 

This tutorial outlines, step by step, how to perform analysis by group and how to do change-point detection.

This tutorial walks through several common methods for visualizing your data in different ways depending on your data type.

This tutorial illustrates several ways to approach predictive modeling and machine learning with MATLAB.

This brief tutorial goes over how you can easily work with big data as you would with any size of data.

In this tutorial, you will learn how to deploy your models outside of your local MATLAB environment, enabling wider sharing and collaboration.

This lesson provides a brief overview of the Python programming language, with an emphasis on tools relevant to data scientists.

This lecture gives an introduction to the FAIR (findability, accessibility, interoperability, and reusability) science principles and examples of their application in neuroscience research. 

The lecture provides an overview of the core skills and practical solutions required to practice reproducible research.

This lecture covers the description and brief history of data science and its use in neuroinformatics.