+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.

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: Simple Introduction to Machine Learning

The focus of this module is to introduce the concepts of machine learning with as little mathematics as possible. We will introduce basic concepts in machine learning, including logistic regression, a simple but widely employed machine learning (ML) method. Also covered is multilayered perceptron (MLP), a fundamental neural network. The concept of deep learning is discussed, and also related to simpler models.

Module 2: Basics of Model Learning

In this module we will be discussing the mathematical basis of learning deep networks. We’ll first work through how we define the issue of learning deep networks as a minimization problem of a mathematical function. After defining our mathematical goal, we will introduce validation methods to estimate real-world performance of the learned deep networks. We will then discuss how gradient descent, a classical technique in optimization, can be used to achieve this mathematical goal. Finally, we will discuss both why and how stochastic gradient descent is used in practice to learn deep networks.

Module 3: Image Analysis with Convolutional Neural Networks (CNNs)

This week will cover model training, as well as transfer learning and fine-tuning. In addition to learning the fundamentals of a CNN and how it is applied, careful discussion is provided on the intuition of the CNN, with the goal of providing a conceptual understanding.

Module 4: Recurrent Neural Networks for Natural Language Processing

This week will cover the application of neural networks to natural language processing (NLP), 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. A wide range of neural NLP models are also discussed, including recurrent neural networks, and specifically long short-term memory (LSTM) models.

Module 5: The Transformer Network for Natural Language Processing

This week we'll cover an Introduction to the Transformer Network, a deep machine learning model designed to be more flexible and robust than Recurrent Neural Network (RNN). We'll start by reviewing several machine learning building blocks of a Transformer Network: the Inner products of word vectors, attention mechanisms, and sequence-to-sequence encoders and decoders. Then, we'll put all of these components together to explore the complete Transformer Network.

Module 6: Introduction to Reinforcement Learning

This week will cover Reinforcement Learning, 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, we'll move to Q Learning, as well as Deep Q Learning. We'll discuss 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 from one of the Duke’s Machine Learning Summer School (MLSS), held 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 and Virtual Learning Experiences

In addition to the online content, +DS offers in-person and virtual 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 Learning Experiences
Tuesday, July 21 - 4:00pm to 5:00pm
Location: Virtual, Classroom
Instructor: Lawrence Carin

A key aspect of analysis of data involves classification and regression; these play a key role in the analysis of many types of data connected to COVID-19. To perform such analyses, one typically must extract features from the data, with which classification/regression is performed.

Wednesday, July 22 - 4:00pm to 5:00pm
Location: Virtual, Classroom
Instructor: Matthew Kenney

PyTorch is an open source framework for building neural networks. In this lesson, we will build a foundational understanding of PyTorch by developing a simple neural network, the Multilayer Perceptron (MLP).

Thursday, July 23 - 4:00pm to 5:00pm
Location: Virtual, Classroom
Instructor: Timothy Dunn

The goal of computer vision is for computers to be able to understand visual content (e.g. images, videos, 3D, stereo), usually for the purpose of making predictions (classification, detection, captioning, generation, etc.).

Tuesday, July 28 - 4:00pm to 5:00pm
Location: Virtual, Classroom
Instructor: Rachel Draelos

Medical image analysis with machine learning holds immense promise for accelerating the radiology workflow and benefiting patient care. Chest computed tomography (CT) is a medical imaging technique that produces a high-resolution volumetric image of the heart and lungs.

Tuesday, August 4 - 4:00pm to 5:00pm
Location: Virtual, Classroom
Instructor: Benjamin Goldstein

As the COVID-19 pandemic hit Durham County, the Duke University Health System (DUHS) responded by postponing most non-urgent (i.e. elective) operations.

Tuesday, August 11 - 4:00pm to 5:00pm
Location: Virtual, Classroom
Instructor: Fan Li

We will overview several important issues in causal inference methods for evaluating the comparative effectiveness and efficacy of potential COVID medications and vaccines. These issues cover both design and analysis of randomized trials, natural experiments, and observational studies.

Tuesday, August 18 - 4:00pm to 5:00pm
Location: Virtual, Classroom
Instructor: Jessilyn Dunn

Recent technological advancements make it possible to closely and continuously monitor patients on multiple scales, both inside and outside of the clinic.

Recorded Content from Lunch and Learns

+DS offers recordings from a series of lunch and learn sessions held in fall 2019 about how artificial intelligence (AI) is transforming healthcare. Both clinical experts and technical experts led each session, with content split roughly 50/50 between the clinical setup and technical approach, and a focus to share both the medical context and the applications of data science for health.

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

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

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

Recommending MyChart Responses with Natural Language Processing