Abigail Drummond advanced a novel machine-learning driven technique to map the outbreak risk for dengue, as a case study example. She started by collecting climate and anthropogenic data from 2000 to 2019. She used this data to model current dengue outbreak risk using various machine-learning based species distribution models. She then compared the outbreak risk to the distribution of the mosquito species, Aedes aegypti, the main vector for dengue.
A two-day DataX workshop that covered a wide range of scientific topics, from Bayesian inference techniques to looking at machine learning in the context of the larger world, was held from May 13th to the 14th at Princeton University’s Friends Center. According to its organizers, the event, “Tutorial Workshop on Machine Learning for Experimental Science,” was meant to disseminate current topics and techniques in the field so that scholars may advance their research.
The detailed lecture notes that Ramadge distributes every week are legendary. They have proved to be indispensable to the many students who have taken his courses over the years since Ramadge, whose scholarship focuses on signal processing and machine learning, joined the faculty in 1984.
The Center for Statistics and Machine Learning held its annual undergraduate poster session earlier this month. Hosted virtually, 124 students participated in the event and hailed from 13 departments and centers, including African American Studies, chemical and biological engineering, and ecology, just to name a few. CSML feted the poster session participants with a celebratory in-person event on May 12th.
Data scientists Brain Arnold and Jose Garrido Torres, supported by the Schmidt DataX Initiative, are featured in a new series of videos talking about their role and impact in research with Princeton University scholars.
Olga Russakovsky's project is “Toward complete interpretability of computer vision models." Chi Jin's project is “Demystifying partial observability in reinforcement learning" and Bartolomeo Stellato's project is “Learning task-specific optimizers for real-time autonomous systems.” All three are CSML-affiliated faculty. Peter Ramadge, the director of CSML, received funds for his project “Using machine learning to model and analyze human language and communication." More details in the article.
On the CSML undergraduate certificate, Eugene Tang said the curriculum gave him a solid foundation to learn more complex topics. “The field of machine learning has been changing so rapidly. What was the state-of-the-art when I was in college is no longer the case. And with the certificate curriculum laying an excellent foundation, that's helped me quickly pick up the new stuff,” he said.
The US Research Software Engineer Association (US-RSE) is set to hold its first face-to-face workshop on April 26th and 27th. Held at Princeton University and sponsored by the Alfred P. Sloan Foundation, the US-RSE Community Building Workshop will bring together research software engineers from universities, industry, and research laboratories across the country, plus a few more from abroad, to chart a path forward for the swiftly expanding group.
After he graduated from Princeton, Stefan Keselj joined Google as a software engineer for the company’s Video Understanding in Google Search team. He worked at the search engine giant for two and a half years. “The goal of that team was to leverage video understanding technology to make better video features and to make video ranking better on Google Search,” said Keselj.
Naomi Ehrich Leonard, the Edwin S. Wilsey Professor of Mechanical and Aerospace Engineering, has an article in the latest EQuad magazine that features her research on helping robots move safely and gracefully around humans while achieving desired goals.