Mega Trends Lecture: The Nexus of Energy and Data Science

The Nexus of Energy and Data Science: How Recent Advances in Data Analysis are Transforming the Energy Industry

Join Duke students at this Mega Trends lecture by Kyle Bradbury, Lecturing Fellow and Managing Director, Energy Data Analytics Lab.

"Emerging sources of energy data are enabling new ways of generating, transmitting, and consuming energy more efficiently through the use of machine learning techniques. From renewable electricity systems to oil and gas production, we’ll discuss innovations in data science that are transforming the way we interact and understand energy systems."

CEE Symposium - Engineering for the Planet

PRESENTER

NCDOT Secretary James H. Trogdon III, NCDEQ Assistant Secretary Shelia Holman, Duke CEE Faculty

The Department of Civil and Environmental Engineering at Duke University is hosting a symposium (“Engineering for the Planet”) on Monday, October 29th. This is an opportunity to hear from the featured speakers: NCDOT Secretary James H. Trogdon, III and NCDEQ Assistant Secretary Shelia Holman, as well as internationally recognized professors speaking on a variety of topics of interest to the broader community. Additionally, because the symposium is located adjacent to the rare manuscript archive, the curators have agreed to display some of John Snow's original documents.

Members of the Duke community are invited to attend all (or part) of the event, but if you would like to have lunch on that day, we respectfully request you RSVP with Ruby Nell Carpenter (ruby.carpenter@duke.edu).

More information here.

Machine Learning Seminar: Principled Deep Neural Network Training through Linear Programming


Speaker(s): 
Daniel Bienstock (Columbia University)

Deep Learning has received significant attention due to its impressive performance in many state-of-the-art learning tasks. Unfortunately, while very powerful, Deep Learning is not well understood theoretically and in particular only recently results for the complexity of training deep neural networks have been obtained. In this work we show that large classes of deep neural networks with various architectures (e.g., DNNs, CNNs, Binary Neural Networks, and ResNets), activation functions (e.g., ReLUs and leaky ReLUs), and loss functions (e.g., Hinge loss, Euclidean loss, etc) can be trained to near optimality with desired target accuracy using linear programming in time that is exponential in the size of the architecture and polynomial in the size of the data set; this is the best one can hope for due to the NP-Hardness of the problem and in line with previous work. In particular, we obtain polynomial time algorithms for training for a given fixed network architecture. Our work applies more broadly to empirical risk minimization problems which allows us to generalize various previous results and obtain new complexity results for previously unstudied architectures in the proper learning setting. Joint work with G. Munoz (Montreal) and S. Pokutta (G. Tech.) Daniel Bienstock 

RTCC Cleantech Innovators’ Networking

Join the Research Triangle Cleantech Cluster to learn about the technologies and companies changing the world and making the Triangle region a global cleantech leader. Mingle with the region's cleantech innovators and meet influencers from industry, government, and academia. Use code trianglestudent for 50% student discount. Please register here.

Energy Mix

Come one, come all to the Energy Mix, where students, faculty, and energy professionals from Duke (and far beyond!) will share food, drink, and electrifying conversation. We'll set aside a few minutes to toast the winners of the 2018 Energy in Emerging Markets Case Competition. Be sure to stop by The Generator to check out a digital exhibit curated by the Global Energy Access Network (GLEAN), a Duke student group. 

Energy Alumni Breakfast (Energy Week at Duke 2018)

Start the day off right by joining other Duke alumni in energy for a networking breakfast sponsored by the Duke University Energy Initiative! Catch up with peers from the past—and make new connections—as you fuel up for the Duke University Energy Conference.

To attend the breakfast only, RSVP here. Otherwise, you can indicate your interest as you register for the Conference

Pratt MEMP Energy Club hosting workshop on ArcGIS (Session 2)

The Pratt MEMP Energy Club will be hosting a workshop on ArcGIS, in two sessions, with the 1st session on Oct 26th and 2ndsession on Nov 2nd. The first that was originally planned for Oct 12th has been postponed to Oct 26th. The workshop is designed to give students an overview of the ArcGIS software and no prior experience in ArcGIS is needed. RSVP here by Oct. 25th.

Pratt MEMP Energy Club hosting workshop on ArcGIS (Session 1)

The Pratt MEMP Energy Club will be hosting a workshop on ArcGIS, in two sessions, with the 1st session on October 26th and 2nd session on November 2nd. The first that was originally planned for Oct 12th has been postponed to Oct 26th. The workshop is designed to give students an overview of the ArcGIS software and no prior experience in ArcGIS is needed. RSVP here by Oct. 25th.

Pages

Subscribe to RSS - Fall 18