- Thu, Nov 12, 2020, 12:30 pmIn this seminar, we will examine the underinvested deep learning personalization and recommendation systems in the overall research community. The training of state-of-the-art industry-scale personalized and recommendation models consumes the highest number of compute cycles among all deep learning use cases. For AI inference, personalization and recommendation consumes even higher compute cycles of 80%. What does state-of-the-art industry-scale neural personalization and recommendation models look like?
- Wed, Nov 18, 2020, 12:00 pm
The One World Seminar Series on the Mathematics of Machine Learning is an online platform for research seminars, workshops and seasonal schools in theoretical machine learning.
- Wed, Nov 4, 2020 (All day) to Fri, Nov 6, 2020 (All day)This multi-day, virtual conference will help create new connections among Princeton innovators and leaders in entrepreneurship, industry, nonprofit organizations, and government in the state, regional and global innovation ecosystems. Engage 2020 brings together a roster of accomplished academics, inventors, and entrepreneurs from science, medicine, engineering, technology, social sciences and the arts, and external partners from government, businesses, finance, and organizations.
- Wed, Oct 14, 2020, 8:00 pmNowadays, all sorts of sensors, from ground to space, collect a huge volume of data about the Earth. Recent advances in artificial intelligence (AI) provide unprecedented opportunities for data-driven hydrological modeling using such “Big Earth Data”. However, many critical issues remain to be addressed. For example, there lacks efficient frameworks for data-driven modeling under the big data condition. Moreover, with the amazing predicting power of deep learning (DL) demonstrated in the field of hydrology, whether and how hydrology theory can still play an important role in hydrological modeling is under debate. This presentation introduces two recent studies conducted by Prof. Yi Zheng’s group which attempt to address the above issues. A novel approach to data-driven hydrological modeling was first developed.
- Wed, Oct 28, 2020, 4:30 pm
The Princeton HPC clusters offer several machine learning (ML) software libraries. Some are straightforward to use while others need to be installed and are highly configurable. Additional complications arise when job scheduler scripts need to be written to take advantage of multi-threading and/or GPUs. This workshop will show participants how to get started with various ML libraries and use these libraries optimally on the HPC clusters. We will cover PyTorch, TensorFlow, Spark, NVIDIA Rapids, R, Julia and more.
- Tue, Oct 20, 2020, 12:00 pmThis workshop is an introduction to working with data in the cloud on Azure. You will walk through the different data structures and how they can be managed, consumed, and accessed in Azure. This workshop also explores solutions and integrations with common tools used for extract, transform, and load (ETL) processes. You will leave with an improved understanding of Azure’s data ecosystem and where your existing data fits within it.
- Tue, Oct 13, 2020, 12:00 pmIn this workshop, you will learn the most important concepts of the machine learning workflow that data scientists follow to build an end-to-end data science solution on Azure. You will learn how to find, import, and prepare data, select a machine learning algorithm, train, and test the model, and deploy a complete model to an API. You will get tips, best practices, and resources you and your team need to continue your machine learning journey, build your first model, and more.
- Tue, Oct 6, 2020, 12:00 pmParticipants will learn the basics of cloud computing, getting started on Azure, and then move on to Azure’s Data and ML tool. Class participants should watch the four prerequisite videos prior to the live workshop.
- Tue, Sep 22, 2020, 12:30 pmMultiple organizations often wish to aggregate their sensitive data and learn from it, but they cannot do so because they cannot share their data. For example, banks wish to run joint anti-money laundering algorithms over their aggregate transaction data because criminals hide their traces across different banks. Bio: Raluca Ada Popa is an assistant professor of computer science at University of California, Berkeley working in computer security, systems, and applied cryptography. She is a co-founder and co-director of the RISELab at UC Berkeley, as well as a co-founder and CTO of a cybersecurity startup called PreVeil. Raluca received her doctoral degree in computer science as well as her master’s and two bachelors’ degrees from Massachusetts Institute of Technology. She is the recipient of a Sloan Foundation Fellowship award, NSF Career, Technology Review 35 Innovators under 35, Microsoft Faculty Fellowship, and a George M. Sprowls Award for best MIT computer science doctoral thesis. To request accommodations for a disability please contact Jean Butcher, firstname.lastname@example.org, at least one week prior to the event.
- Wed, Oct 21, 2020, 12:00 pm
Clustering unlabeled point clouds is a fundamental problem in machine learning. One classical method for constructing clusters on graph-based data is to solve for Cheeger cuts, which balance between finding clusters that require cutting few graph edges and finding clusters which are similar in size. Although solving for Cheeger cuts on general graphs is very challenging, when the graph is constructed by sampling from a continuum domain one suspects that the problem may be more tractable.