The aim of this page is to point to various useful materials to assist in training in the fields of machine learning and deep learning.
Digital Pathology group training materials:
Introduction to Python, Machine Learning, and using the CANDLE Benchmarks
Documentation by Madeleine Birdsell and Catherine Warnement as interns with the High Performance Computing Team (Frederick National Lab) in summer 2018.
Contact: George Zaki
Data Science Learning Exchange
Source code and detailed documentation for various workflows in machine and deep learning can be found at GitHub. This is a new collection that will be growing in the coming weeks.
Higher-level walk-throughs of the scripts and their utility will be uploaded to NIH.AI as well.
Contact: Andrew Weisman
Courses
Deep Learning at the NIH FAES (BIOF 399)
Abstract:
In this course, students will learn how to apply Convolutional Neural Networks (CNNs) to medical images to perform a variety of medical tasks and calculations. Upon completion of this course, students will be able to apply CNNs to medical images to conduct a variety of medical tasks.
Learning objectives:
- Understand how to use popular image classification neural networks for classification, object detection, and semantic segmentation
- Create a powerful GPU accelerated convolution neural network (CNN) solution for quantitative medical image analysis
- Use deep learning techniques to predict genomic biomarkers from medical image analysis
- Explore other areas of innovation and research
- Get hands-on to try many different deep learning frameworks
- Class material: https://github.com/akinhwan/NIH-FAES-BIOF-399-Spring-2019
Contact: Hoo Chang Shin