The Center for Intelligent Systems and Machine Learning (CISML) is a collaboration of faculty from four colleges and nine academic departments at the University of Tennessee (UT), and is part of the College of Engineering on the Knoxville campus. Beginning as a simple faculty initiative to create a unified curricula, CISML evolved (in October 2010) into an official UT research center that studies the theory and application of intelligent systems and machine learning. In addition to UT faculty, the Center's research staff is comprised of eight experts from Oak Ridge National Laboratory (ORNL).
CISML's focus is on designing computer-based systems that exhibit intelligent behavior, operate autonomously, and adapt to environmental changes. Examples of the diverse research activities in this area include pattern recognition, robotics, artificial intelligence, biologically-inspired cognitive architectures, bioinformatics, and data mining, to name a few.
New Healthcare Data Analytics Course ~ Fall 2016
HST.953 is a new fall course on secondary analysis of health records at MIT. The course is modeled after the successful datathons that we have organized over the past two falls. These datathons have brought clinicians
and data scientists together, each contributing their expertise to conduct clinical and data science research. Students will learn the basics of research using routinely collected health data, including data extraction, processing and analysis, and acquire skills from a diverse set of field including: epidemiology, databases, statistics, and machine learning. Students will be teamed up with Boston-area clinicians for an end of course group project, whereby participants will use the Medical Information Mart for Intensive Care (MIMIC) database to produce and submit a peer-reviewed article for publication in a scholarly journal. The course will be streamed on YouTube. As we plan the logistics of the course, we would like an estimate of the number of students who will be taking the course. Please complete an expression of interest form here: http://criticaldata.mit.edu/course/eoi/ Email hst953faculty [at] mit.edu for any questions.
FALL 2016 - NEW CLASS OFFERED
Advanced Topics in Data Mining –This course will introduce advanced techniques in data mining and machine learning. Students will be exposed to the state of the art, learn advanced techniques, and build up basic literature review and research skills. Classes Meet T/Th 2:10-3:25 p.m. at SMC 701, Dr. Wenjun Zhou - Office: SMC 247 Email: wzhou4 [at] utk.edu Phone: (865) 974-9198 Office Hours: TBD. Click HERE to view a draft of Syllabus.
Summer intern at NERSC – Berkeley Lab ~ Finding Features in Cosmological Maps
Cosmology is the study of the Universe, and one of the most important ways we study the Universe is using maps of the sky. These can be maps of the locations of galaxies, or of the matter in the Universe (which includes dark matter). The statistics we derive from these maps give us a powerful probe of the structure and evolution of the Universe, but at present we are limited to a small number of simple statistics derived from theoretical models. This project will use machine learning techniques (including Convolutional Neural Nets) to learn new features in these maps that distinguish between different cosmological models, and that can tell us about the nature of Dark Energy, the mysterious force that is driving the accelerated expansion of the universe. Students should have a working knowledge of Linux and some experience writing code. Familiarity with machine-learning packages (such as Neon, Caffe, SciKitLearn or similar) would be useful. Contact: Debbie Bard (djbard [at] lbl.gov) http://www.nersc.gov/
- Evaluating How Level of Detail of Visual History Affects Process Memory by
- Spatiotemporal evolution of market towns in the Jiangnan area during the Ming-Qing dynasties of China by
- Understanding aggregate human mobility patterns using passive mobile phone location data - a home-based approach by
- Making place recommendations: An individual accessibility measure to urban opportunities in space and time by