Learn

+DS provides training modules and learning experiences grounded in generalizable data science content, while partnering with individual units or groups to develop additional specialized content.

In fall 2019, +DS offers 3 types of learning experiences, open to anyone in the Duke community:

  1. Online +DS Modules introduce the basics of data science

  2. In-Person Learning Experiences offer opportunities to dive deeper into the specific topics

  3. Lunch and Learns share experiences and specific applications

Online Learning

Coursera Online Modules

The online +DS modules introduce the basics of data science, across multiple important application domains. These online modules are used as prerequisites for the in-person learning experiences listed below. Together, the online content supports the in-person "flipped" learning experiences. 

Module 1: Introduction to Machine Learning

Logistic regression, a simple machine learning (ML) method, is introduced and then extended to the multilayered perceptron (MLP), a fundamental neural network. Conceptual understanding is provided to motivate the form of the MLP, and its use.

Module 2: Basics of Model Learning

Concepts in learning model parameters are introduced, as well as model validation and testing. Learning based on stochastic gradient descent is addressed, allowing scaling to large datasets ("big data").

Module 3: Image Analysis and the Convolutional Neural Network

The convolutional neural network (CNN) is developed for image analysis, including details of the model and its underlying components. Model training is covered, as well as transfer learning and fine-tuning.

Module 4: Introduction to Natural Language Processing

Application of neural networks to natural language processing (NLP) is covered, from simple neural models to the more complex. The fundamental concept of word embeddings is discussed, as well as how such methods are employed within model learning and usage for several NLP applications.

Module 5: Introduction to Reinforcement Learning

Reinforcement Learning is introduced, a fundamental concept in machine learning that is concerned with taking suitable actions to maximize rewards in a particular situation. After learning the initial steps of Reinforcement Learning, the module addresses Q Learning as well as Deep Q Learning, and discusses the difference between the concepts of Exploration and Exploitation and why they are important.

Please note that Coursera for Duke is accessible to only Duke students, faculty, and staff. If you are not a member of the Duke community, you can access the public version of this Coursera course: https://www.coursera.org/duke.

Recorded Content from Machine Learning Summer School

In addition to the aforementioned Coursera content, +DS offers recordings of Duke’s Machine Learning Summer School (MLSS), which was help in June of 2018. If you are a Duke student, staff or faculty member, you can review these classroom recordings on Panopto, with accompanying slides and links to github code demos.

In-Person Learning Experience

In addition to the online content, +DS offers in-person opportunities to dive deeper into the information introduced in the online modules. These learning experiences will be developed to target diverse units at Duke: from those that desire a broad understanding of what is possible with data science, and those who wish to use data-science tools (software) without a need for deep understanding of underlying methodology, to those who desire a rigorous technical proficiency of the details and methodology of data science.

See past learning experiences

Upcoming In-Person Learning Experiences

There are no Learning Experiences found.

Lunch and Learns

+DS invites you to learn about how artificial intelligence (AI) is transforming healthcare through a series of lunch and learns this fall. Topics will include deep learning for digital pathology, neural networks and retinal image analysis, machine learning approaches for autism screening, and natural language processing with communications between patients and clinicians.

Both clinical experts and technical experts will lead each session, with content split roughly 50/50 between the clinical setup and technical approach. Participants will learn about both the medical context and the applications of data science for health.

The sessions will be convenient for Duke medical professionals, located at the Trent-Semans Center Learning Hall. The goal for these lunches is a fun, convenient way for the Duke community to learn about data science and engage with Duke’s data science for health community, including clinicians, quantitative experts, faculty, trainees, and students.

Lunch will be provided, and no registration is required.

Tuesday, September 24, 2019 | 12:00 noon – 1:15 p.m. | Trent-Semans Center Learning Hall
Digital Pathology: Identifying Thyroid Malignancy with Deep Learning

Danielle Range, MD, Assistant Professor of Pathology
Yoni Cohen, MD, Medical Instructor, Department of Head and Neck Surgery & Communication Sciences
Ricardo Henao, PhD, Assistant Professor of Biostatistics and Bioinformatics; Principal Data Scientist, Duke Forge

View the video of this session (requires Duke login): https://duke.mediasite.com/Mediasite/Play/a97f106d5dc846468e65fe274730f4bf1d

Tuesday, October 1, 2019 | 12:15 p.m. – 1:30 p.m. | Trent-Semans Center Learning Hall
A Window to the Brain: Analysis of Retinal Images with Deep Neural Networks

Sharon Fekrat, MD, Professor of Ophthalmology; Associate Professor, Department of Surgery
Felipe Medeiros, MD, PhD, Joseph A.C. Wadsworth Professor of Ophthalmology
Dilraj Singh Grewal, MBBS, Associate Professor of Ophthalmology
Lawrence Carin, PhD, James L. Meriam Professor of Electrical and Computer Engineering; Vice President for Research, Duke University

View the video of this session (requires Duke login): https://duke.mediasite.com/Mediasite/Play/044abb60a25d4eea9705aa51343af36b1d

Tuesday, November 5, 2019 | 12:15 p.m. – 1:30 p.m. | Trent-Semans Center Learning Hall
Early Autism Screening with Machine Learning

Geraldine Dawson, PhD, William Cleland Professor of Psychiatry & Behavioral Sciences; Director, Duke Center for Autism and Brain Development; Director, Duke Institute for Brain Sciences
Guillermo Sapiro, PhD, James B. Duke Professor of Electrical and Computer Engineering; Professor of Mathematics

View the video of this session (requires Duke login): https://duke.mediasite.com/Mediasite/Play/588abd8d0e8148aba7b8ea27dd82e9721d

Tuesday, December 3, 2019 | 12:15 p.m. – 1:30 p.m. | Trent-Semans Center Learning Hall
Recommending MyChart Responses with Natural Language Processing

Jedrek Wosik, MD, Cardiology Fellow, Department of Medicine
Ricardo Henao, PhD, Assistant Professor of Biostatistics and Bioinformatics; Principal Data Scientist, Duke Forge

View the video of this session (requires Duke login): https://duke.mediasite.com/Mediasite/Play/5db2130cddd9496cb54c0eb040d758ed1d