Ensemble sampling serves as a practical approximation to Thompson sampling when maintaining an exact posterior distribution over model parameters is computationally intractable. In this paper, we establish a regret bound that ensures desirable behavior when ensemble sampling is applied to the linear bandit problem. This represents the first rigorous regret analysis of ensemble sampling and is made possible by leveraging information-theoretic concepts and novel analytic techniques that may prove useful beyond the scope of this paper.

In the following report we propose pipelines for Goodness of Pronunciation (GoP) computation solving OOV problem at testing time using Vocab/Lexicon expansion techniques. The pipeline uses different components of ASR system to quantify accent and automatically evaluate them as scores. We use the posteriors of an ASR model trained on native English speech, along with the phone level boundaries to obtain phone level pronunciation scores. We used this as a baseline pipeline and implemented methods to remove UNK and SPN phonemes in the GoP output by building three pipelines. The Online, Offline and Hybrid pipeline which returns the scores but also can prevent unknown words in the final output. The Online method is based per utterance, Offline method pre-incorporates a set of OOV words for a given data set and the Hybrid method combines the above two ideas to expand the lexicon as well work per utterance. We further provide utilities such as the Phoneme to posterior mappings, GoP scores of each utterance as a vector, and Word boundaries used in the GoP pipeline for use in future research.

Kettering University will host two FIRST Robotics district competitions in March at the Connie and Jim John Recreation Center. Forty FIRST Robotics Competition (FRC) high school teams will compete in each of the FRC Kettering Districts 1 and 2, presented by Ford, March 2-4 and March 9-11. Opening ceremonies kick off the competitions at 10:30 a.m. Award ceremonies will take place at 5 p.m. March 4 and March 11. "It is an absolute honor to partner with Ford, yet again, to make a positive impact on these talented students," said Kim Shumaker, Robotics Center and Robotics Outreach Director.

As technology constantly advances and focuses on the use of artificial intelligence (AI) and virtual assistance, the future of education also goes through numerous changes. It is not only in how we acquire information these days but also in how the tools we use transform the way we study per se. One of the prominent examples is ChatGPT, which has instantly taken things to another level by allowing smart students and educators to use it as a solution for writing and even analytical purposes. As the system bases itself on the information that is being shared, ChatGPT also provides intelligent feedback that helps to remain inspired and have fun with this new generation chatbot! If you have never used intelligent chatbots in the past for educational purposes, the best way to start is ChatGPT.

Last fall, I published a book about strollers and what they reveal about our attitudes toward children and their caretakers. Although I pitched Stroller as, in part, a critique of the consumer culture of contemporary American parenthood, I came to love my (many) strollers. In the years when I routinely ran while pushing my kids ahead of me in our jogging stroller, I recorded race times faster than I had as the captain of my college track team. In the long, claustrophobic early days of the pandemic, my son and I meandered slowly up and down the sidewalks of our neighborhood watching that late, cold spring come to New England. Often, at the end of a long stroller walk or run, my kids fell asleep, and on warm days, I'd park them in the shade and myself in the sun to work while they slept, feeling a proud mix of self-sufficiency and frugality (no childcare needed to run or meet a deadline).

The rapid rise of ChatGPT has spawned equal proportions of hype, horror, and hope about the potential of artificial intelligence. Here's a sample of the surging headlines about AI from just one day, most triggered by the ChatGPT phenomenon (emphasis added): How Artificial Intelligence Can Boost Diversity & Inclusion (Forbes.com) Can Artificial Intelligence Help Detect Lung Cancer? And my favorite: "Can pigeons match wits with artificial intelligence?" ChatGPT, an AI application that allows machines to write and respond in uncannily humanlike ways, reached 100 million users in about two months. This makes it the fastest-growing app in history, according to a report from UBS cited by Reuters.

Although nothing really changes but the date, a new year fills everyone with the hope of starting things afresh. If you add in a bit of planning, some well-envisioned goals, and a learning roadmap, you'll have a great recipe for a year full of growth. This post intends to strengthen your plan by providing you with a learning framework, resources, and project ideas to help you build a solid portfolio of work showcasing expertise in data science. Just a note: I've prepared this roadmap based on my personal experience in data science. This is not the be-all and end-all learning plan.

Pre-training representations (a.k.a. foundation models) has recently become a prevalent learning paradigm, where one first pre-trains a representation using large-scale unlabeled data, and then learns simple predictors on top of the representation using small labeled data from the downstream tasks. There are two key desiderata for the representation: label efficiency (the ability to learn an accurate classifier on top of the representation with a small amount of labeled data) and universality (usefulness across a wide range of downstream tasks). In this paper, we focus on one of the most popular instantiations of this paradigm: contrastive learning with linear probing, i.e., learning a linear predictor on the representation pre-trained by contrastive learning. We show that there exists a trade-off between the two desiderata so that one may not be able to achieve both simultaneously. Specifically, we provide analysis using a theoretical data model and show that, while more diverse pre-training data result in more diverse features for different tasks (improving universality), it puts less emphasis on task-specific features, giving rise to larger sample complexity for down-stream supervised tasks, and thus worse prediction performance. Guided by this analysis, we propose a contrastive regularization method to improve the trade-off. We validate our analysis and method empirically with systematic experiments using real-world datasets and foundation models.

Machine learning (ML) recourse techniques are increasingly used in high-stakes domains, providing end users with actions to alter ML predictions, but they assume ML developers understand what input variables can be changed. However, a recourse plan's actionability is subjective and unlikely to match developers' expectations completely. We present GAM Coach, a novel open-source system that adapts integer linear programming to generate customizable counterfactual explanations for Generalized Additive Models (GAMs), and leverages interactive visualizations to enable end users to iteratively generate recourse plans meeting their needs. A quantitative user study with 41 participants shows our tool is usable and useful, and users prefer personalized recourse plans over generic plans. Through a log analysis, we explore how users discover satisfactory recourse plans, and provide empirical evidence that transparency can lead to more opportunities for everyday users to discover counterintuitive patterns in ML models. GAM Coach is available at: https://poloclub.github.io/gam-coach/.

AI-based design tools are proliferating in professional software to assist engineering and industrial designers in complex manufacturing and design tasks. These tools take on more agentic roles than traditional computer-aided design tools and are often portrayed as "co-creators." Yet, working effectively with such systems requires different skills than working with complex CAD tools alone. To date, we know little about how engineering designers learn to work with AI-based design tools. In this study, we observed trained designers as they learned to work with two AI-based tools on a realistic design task. We find that designers face many challenges in learning to effectively co-create with current systems, including challenges in understanding and adjusting AI outputs and in communicating their design goals. Based on our findings, we highlight several design opportunities to better support designer-AI co-creation.