Selected 2017-2018 Yale University Courses
CPSC663/AMTH663 Deep Learning: Theory and Applications (Taught By: Smita Krishnaswamy)
Deep neural networks have gained immense popularity within the last decade due to their success in many important machine learning tasks such as image recognition, speech recognition, and natural language processing. This course will provide a principled and hands-on approach to deep learning with neural networks. By the end of the course, students will have mastered the principles and practices underlying neural networks including modern methods of deep learning, and will have applied deep learning methods to real-world problems including image recognition, natural language processing, and biomedical applications. The course will be based on homework, a final exam, and a final project (either group or individual, depending on the total number enrolled). The project will include both a written and oral (i.e. presentation) component. Students’ grades will be based on their homework scores and the quality of the written and oral component of their projects. The course assumes basic prior knowledge in linear algebra and probability.
CPSC745/AMTH745/CB&B745 Advanced Topics in Machine Learning and Data Mining (Taught By: Smita Krishnaswamy & Guy Wolf)
An overview of advances in the past decade in machine learning and automatic data-mining approaches for dealing with the broad scope of modern data-analysis challenges, including deep learning, kernel methods, dictionary learning, and bag of words/features. This year, the focus is on a broad scope of biomedical data-analysis tasks, such as single-cell RNA sequencing, single-cell signaling and proteomic analysis, health care assessment, and medical diagnosis and treatment recommendations. The seminar is based on student presentations and discussions of recent prominent publications from leading journals and conferences in the field.
See class website: http://cpsc745.guywolf.org/
CPSC553/CPSC453/GENE555/CB&B555 Machine Learning for Biology (Taught By: Smita Krishnaswamy)
This course introduces biology as a systems and data science through open computational problems in biology, the types of high-throughput data that are being produced by modern biological technologies, and computational approaches that may be used to tackle such problems. We cover applications of machine-learning methods in the analysis of high-throughput biological data, especially focusing on genomic and proteomic data, including denoising data; nonlinear dimensionality reduction for visualization and progression analysis; unsupervised clustering; and information theoretic analysis of gene regulatory and signaling networks. Students' grades are based on programming assignments, a midterm, a paper presentation, and a final project.
Selected Talks by Lab Members
Manifold-Learning Frameworks for Extracting Structure
from High-throughput Single-Cell Datasets
Monday, November 27, 2017
Smita Krishnaswamy, Yale University
Models, Inference, and Algorithms (MIA):
Manifold learning of cellular state space
October 17, 2018
David van Dijk and Smita Krishnaswamy
Geometry Based Data Generation
NeurIPS Montreal, 2018
Jay Stanley, Yale University