+DS offers 6 In-Person Learning Experiences in January/February
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 IPLEs on the +DS website: https://plus.datascience.duke.edu/learn-ds#iple
Thursday, January 23 | 4:30-6:30 PM
Convolutional Neural Networks for Image Analysis
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. https://training.oit.duke.edu/enroll/common/show/21/174799
Wednesday, February 5 | 4:30-6:30 PM
Introduction to Neural Networks
Qiang Qiu
The basic concepts of neural networks are introduced, with a focus on intuition. The simpler and widely used logistic regression model is introduced first, and from this the neural network is introduced as a generalization. Multilayered neural networks are introduced, yielding deep learning and its applications. From this session, participants will be introduced to what a neural network is, and how it may be used in practice. https://training.oit.duke.edu/enroll/common/show/21/174800
Wednesday, February 12 | 4:30-6:30 PM
Scaling to Big Data
David Carlson
In machine learning, models are developed to represent and make predictions based on data. The model starts with random parameters and must “learn” these parameters by using historical data. In this class, we will discuss how learning is performed in practice, which is one of the key technical areas of machine learning. One of the big challenges in modern data science problems is the ability to perform such learning with massive datasets, so called “big data,” with minimal human intervention. This lecture will include discussion of back-propagation, variants of stochastic gradient descent, and adaptive gradient methods. This lecture assumes background knowledge that would be acquired either from the “Neural Network Basics” IPLE or Weeks 1 and 2 of the Duke Coursera Course “Introduction to Machine Learning.” https://training.oit.duke.edu/enroll/common/show/21/174807
Thursday, February 13 | 4:30-6:30 PM
Biomedical Data Science and Machine Learning Applications in Healthcare
Jessilyn Dunn
Recent technological advancements make it possible to closely and continuously monitor patients on multiple scales, both inside and outside of the clinic. These new technologies provide unprecedented opportunities for understanding and predicting health and disease but have also led to a deluge of biomedical data. In order to derive actionable health insights from these large volumes of data, a combination and biomedical data science and machine learning approaches are needed. In this talk, I will introduce the four major types of biomedical data (multi-omics, electronic health records, mobile sensor data, and imaging) and the opportunities and challenges in working with them. I will discuss applications where machine learning has generated novel uses for these data, including real-time illness detection outside of the clinic and clinical decision support models, and will explore how these new applications are revolutionizing medicine. https://training.oit.duke.edu/enroll/common/show/21/174806
Wednesday, February 19 | 4:30-6:30 PM
Introduction to PyTorch
Kevin Liang
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. Bring a laptop and be ready to code! https://training.oit.duke.edu/enroll/common/show/21/174804
Thursday, February 20 | 4:30-6:30 PM
Introduction to Natural Language Processing with Neural Networks
Lawrence Carin
Natural language processing (NLP) is a field focused on developing automated methods for analyzing text, and also for computer-driven text generation (synthesis, for example in translation). Neural networks have recently become the state-of-the-art method for NLP. In this session several neural NLP models are introduced, from relatively simple models, to advanced models based on the convolutional neural network and on recurrent neural networks. The concept of word embeddings is introduced, and it is also explained that often excellent NLP results may be achieved with simple neural models. https://training.oit.duke.edu/enroll/common/show/21/174801
