+Data Science (+DS) is a Duke-wide program, operating in partnership with departments, schools, and institutes to enable faculty, students, and staff to employ data science at a level tailored to their needs, level of expertise, and interests. For more information, please visit our website at https://plus.datascience.duke.edu
Upcoming Virtual Learning Experiences (vLEs)
Seven +DS learning experiences will be held in September. These sessions offer the opportunity to dive deeper into topics and 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. Anyone in the Duke community is welcome to join, there is no fee to attend, and no prior experience is necessary. Learn more about learning experiences on the +DS website: https://plus.datascience.duke.edu/learn-ds
Introduction to PyTorch for Deep Learning
Thursday, September 3 | 4:30-6:00 PM
Serge Assaad
PyTorch is an open source machine learning framework popular for building neural networks. In this hands-on session, we’ll walk through building and training a neural network, introducing the basic mechanics of PyTorch. Register at https://training.oit.duke.edu/enroll/common/show/21/175201
Introduction to Basic Concepts in Machine Learning
Tuesday, September 8 | 4:30-6:00 PM
Ricardo Henao
The basic concepts of machine learning are introduced with a focus on intuition and examples. The simpler and widely used logistic regression model is introduced first, and from this, multilayered neural network are introduced as a generalization. Concepts of parameter learning (optimization), generalization (and overfitting), validation and performance evaluation are also introduced. Register at https://training.oit.duke.edu/enroll/common/show/21/175200
The Transformer Network for Natural Language Processing
Thursday, September 10 | 4:30-6:00 PM
Lawrence Carin
Neural-network-based methods for natural language processing (NLP) constitute an area of significant recent technical progress, with many interesting real-world applications. The Transformer Network is one of the newest and most powerful approaches of this type. This algorithm is based on repeated application of attention networks, in an encoder-decoder framework. In this presentation the basics of all-attention models (the Transformer) for NLP will be described, with application in areas like text synthesis (e.g., suggesting email text) and language translation. Register at https://training.oit.duke.edu/enroll/common/show/21/175199
Deep Learning with PyTorch for Natural Language Processing
Tuesday, September 15 | 4:30-6:00 PM
Liqun Chen
Deep natural language (NLP) processing models have achieved great success to improve language understanding for real-world applications, i.e., question and answering, translation, etc. The Transformer is the most powerful approach among those tools. The fundamental idea behind the Transformer is the self-attention mechanism. In this session, how to implement such self-attention mechanisms and how to use the transformer for NLP tasks via PyTorch will be discussed. This hands-on session is a complement to the earlier session on September 10, “The Transformer Network for Natural Language Processing.” Register at https://training.oit.duke.edu/enroll/common/show/21/175202
Convolutional Neural Networks for Image Analysis
Tuesday, September 22 | 4:30-6:00 PM
Timothy Dunn
The convolutional neural network (CNN) represents the current state-of-the-art for image and video analysis, and is increasingly used for analyzing time series and other data with spatial or sequential structure. This session will provide an intuitive introduction to the fundamentals of CNNs, with an emphasis on hierarchical feature extraction and the convolution operation itself. Model training and transfer learning will also be discussed. Register at https://training.oit.duke.edu/enroll/common/show/21/175205
Deep Learning with PyTorch for Image Analysis
Wednesday, September 23 | 4:30-6:00 PM
Rachel Draelos
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.). Modern computer vision models are almost universally based on convolutional neural networks (CNNs), whose recent developments have lead to increasing adoption and deployment of deep learning models in a wide number of fields. In this hands-on session, we’ll introduce how to build CNNs in PyTorch, as well as how to load datasets and pre-trained models using PyTorch’s vision library, Torchvision. These tools form the foundation for the session on “Convolutional Neural Networks for Image Analysis,” offered on September 22. Register at https://training.oit.duke.edu/enroll/common/show/21/175206
bespokeDS: Effective Data Visualization
Monday, September 28 | 2:00-3:00 PM
Matthew Hirschey and Cédric Scherer
Data visualization is part art and part science. A data visualization has to accurately convey the data, but also should be aesthetically pleasing. Great visual presentations of data will enhance the message and lead to deeper understanding of the underlying data. In this session, Matthew Hirschey will be speaking with Data Visualization expert Cédric Scherer about his journey into data visualization, discuss important principles in making figures, and review a recent example of converting a poor visual into a great one. We will use R, ggplot2, and principles of graphic design to dive into beautiful and truthful visualizations of data. This session is co-hosted by bespokeDS and Duke+DataScience. Register at https://training.oit.duke.edu/enroll/common/show/21/175222
Center for Computational Thinking
The +DS program is part of a broader Duke strategy directed toward delivering targeted training in computational sciences to a wide audience. We invite you to visit the new Duke Center for Computational Thinking (CCT) website to learn more: https://computationalthinking.duke.edu/
+DS vLEs are a component of the full CCT event listing, which also features a number of September sessions available to the Duke community from Duke’s Co-Lab Roots series, Science and Society, and other programs.
