Upcoming Events

Princeton University is actively monitoring the situation around coronavirus (COVID-19) and the evolving guidance from government and health authorities. The latest guidance for Princeton members and visitors is available on the University’s Emergency Management website

Deep Networks from First Principles

Fri, Jan 15, 2021, 4:30 pm
In this talk, we offer an entirely “white box’’ interpretation of deep (convolutional) networks from the perspective of data compression. In particular, we show how modern deep architectures, linear (convolution) operators and nonlinear activations, and parameters of each layer can be derived from the principle of rate reduction (and invariance).

Research Computing Bootcamp, Jan. 19-29, 2021, Registration Now Open

Intro to Data Analysis Using R w/ Brian Arnold & Andrzej Zuranski (Schmidt DataX), Research Computing Bootcamp

Wed, Jan 20, 2021, 9:00 am
This session in an introduction to data analysis using the R programming language, aimed at people who have ever used R or RStudio before. It will briefly cover different facets of data analysis and their execution using basic R. The style is fairly hands-on, with participants executing the examples on their own laptops alongside the instructors....

Reproducible Research Reports with R Markdown with Daisy Huang, Research Computing Bootcamp

Wed, Jan 20, 2021, 12:30 pm
Do you use LaTeX or Microsoft Word to write your analysis report? Have you ever wished that all your research results (e.g., data analysis, graphs, result discussions) can be included in one place and can be updated effortlessly? Are you tired of all the copying and pasting that you have to do between R and LaTeX/Microsoft Word?

Introduction to NumPy with Vineet Bansal, Research Computing Bootcamp

Wed, Jan 20, 2021, 1:30 pm
This session covers the basics of NumPy, the package that underlies most scientific computing done in Python. It will explain the NumPy array, the principal data type in the NumPy package, and how it differs from similar Python structures like lists. There will be particular emphasis on understanding the two core features of NumPy arrays –...

Data Visualization in R, using ggplot2 with Daisy Huang, Research Computing Bootcamp

Thu, Jan 21, 2021, 9:30 am
This workshop provides an introduction to effective data visualization in R, primarily using the graphics package ggplot2. We will discuss main concepts of the grammar that defines the graphical building blocks of that package, and we will use hands-on examples to explore ggplot2’s layered approach to creating basic and more complex graphs....

GPU HPC Bootcamp (NVIDIA), Research Computing Bootcamp

Thu, Jan 28, 2021, 9:00 am

Full event details and registration link here.

This day-long workshop will teach participants the basics of GPU programming through extensive hands-on collaboration based on real-life codes using the OpenACC programming model.


Fundamentals of Deep Learning (NVIDIA), Research Computing Bootcamp

Fri, Jan 29, 2021, 9:00 am
Deep learning is a powerful AI approach that uses multi-layered artificial neural networks to deliver state-of-the-art accuracy in tasks such as object detection, speech recognition, and language translation. Using deep learning, computers can learn and recognize patterns from data that are considered too complex or subtle for expert-written...

CSML Poster Session Event

Mon, May 3, 2021, 12:00 pm

The annual CSML Poster Session event will be held in person or virtually. Watch this space for further details.

Due date for independent work posters and papers TBA. Please check your email for details.

Events Archive

Breaking the Sample Size Barrier in Statistical Inference and Reinforcement Learning

A proliferation of emerging data science applications require efficient extraction of information from complex data. The unprecedented scale of relevant features, however, often overwhelms the volume of available samples, which dramatically complicates statistical inference and decision making.


HEE Seminar- Taylor Faucett-UCI-Physics Learning from Machines Learning

Machine Learning methods are extremely powerful but often function as black-box problem solvers, providing improved performance at the expense of clarity. Our work describes a new machine learning approach which translates the strategy of a deep neural network into simple functions that are meaningful and intelligible to the physicist, without...

Location: Zoom

Using Code Ocean in the Sciences and Engineering: Bringing computational reproducibility to your research collaborations

Computational analyses are playing an increasingly central role in research. However, many researchers have not received training in best practices and tools for reproducibly managing and sharing their code and data. This is a step-by-step, practical workshop on managing your research code and data for computationally reproducible collaboration...

Conditional Sampling with Monotone GANs: Modifying Generative Models to Solve Inverse Problems

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.

Location: https://www.oneworldml.org/home

Metamaterials Design and Manufacturing: Perspectives From Biology and Artificial Intelligence

After billions of years of evolution, it is no surprise that biological materials are treated as an invaluable source of inspiration in the search for new materials. Additionally, developments in computation spurred the fourth paradigm of materials discovery and design using artificial intelligence. Our research aims to advance design and...

Deep Learning: It’s Not All About Recognizing Cats and Dogs

In 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...

Analysis of Stochastic Gradient Descent in Continuous Time

Stochastic gradient descent is an optimisation method that combines classical gradient descent with random subsampling within the target functional. In this work, we introduce the stochastic gradient process as a continuous-time representation of stochastic gradient descent.

Location: https://www.oneworldml.org/home
Tags: Seminars

Engage 2020

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,...

Introduction to the Machine Learning Libraries

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.


Intro to Data Analysis using Python

This workshop will get students started in data analysis using the pandas Python package. It will briefly cover different components of data analysis and connect them with the goal of extracting meaning from data. We will go over an example to illustrate the data analysis process from beginning to end.