no code implementations • 2 Oct 2023 • Jacob Whitehill, Jennifer LoCasale-Crouch
With the aim to provide teachers with more specific, frequent, and actionable feedback about their teaching, we explore how Large Language Models (LLMs) can be used to estimate ``Instructional Support'' domain scores of the CLassroom Assessment Scoring System (CLASS), a widely used observation protocol.
1 code implementation • 9 Sep 2021 • Zeqian Li, Xinlu He, Jacob Whitehill
We consider a novel clustering task in which clusters can have compositional relationships, e. g., one cluster contains images of rectangles, one contains images of circles, and a third (compositional) cluster contains images with both objects.
no code implementations • 5 Mar 2021 • Anand Ramakrishnan, Minh Pham, Jacob Whitehill
For the task of face verification, we explore the utility of harnessing auxiliary facial emotion labels to impose explicit geometric constraints on the embedding space when training deep embedding models.
1 code implementation • 22 Oct 2020 • Zeqian Li, Jacob Whitehill
We propose a new method for speaker diarization that can handle overlapping speech with 2+ people.
no code implementations • 19 May 2020 • Anand Ramakrishnan, Brian Zylich, Erin Ottmar, Jennifer LoCasale-Crouch, Jacob Whitehill
In this work we present a multi-modal machine learning-based system, which we call ACORN, to analyze videos of school classrooms for the Positive Climate (PC) and Negative Climate (NC) dimensions of the CLASS observation protocol that is widely used in educational research.
no code implementations • 11 Feb 2020 • Zeqian Li, Michael C. Mozer, Jacob Whitehill
We present a compositional embedding framework that infers not just a single class per input image, but a set of classes, in the setting of one-shot learning.
no code implementations • 25 Sep 2019 • Zeqian Li, Jacob Whitehill
We explore the idea of compositional set embeddings that can be used to infer not just a single class, but the set of classes associated with the input data (e. g., image, video, audio signal).
no code implementations • 19 Dec 2018 • Jacob Whitehill, Anand Ramakrishnan
In particular: (1) We show that if the true correlation between $U$ and $V$ is $r$, then the expected sample correlation, over all vectors $\mathcal{T}^n$ whose correlation with $U$ is $q$, is $qr$.
no code implementations • 7 Sep 2017 • Jacob Whitehill
Recent work on privacy-preserving machine learning has considered how data-mining competitions such as Kaggle could potentially be "hacked", either intentionally or inadvertently, by using information from an oracle that reports a classifier's accuracy on the test set.
no code implementations • 6 Jul 2017 • Jacob Whitehill
In the context of data-mining competitions (e. g., Kaggle, KDDCup, ILSVRC Challenge), we show how access to an oracle that reports a contestant's log-loss score on the test set can be exploited to deduce the ground-truth of some of the test examples.
no code implementations • 21 Feb 2017 • Jacob Whitehill, Kiran Mohan, Daniel Seaton, Yigal Rosen, Dustin Tingley
In order to obtain reliable accuracy estimates for automatic MOOC dropout predictors, it is important to train and test them in a manner consistent with how they will be used in practice.
no code implementations • 3 Jun 2015 • Jacob Whitehill
In this paper we provide proofs-of-concept of how knowledge of the AUC of a set of guesses can be used, in two different kinds of attacks, to improve the accuracy of those guesses.
no code implementations • 1 Jun 2013 • Jacob Whitehill
The ACT-R theory of cognition developed by John Anderson and colleagues endeavors to explain how humans recall chunks of information and how they solve problems.
no code implementations • NeurIPS 2009 • Jacob Whitehill, Ting-Fan Wu, Jacob Bergsma, Javier R. Movellan, Paul L. Ruvolo
However, using these services to label large databases brings with it new theoretical and practical challenges: (1) The labelers may have wide ranging levels of expertise which are unknown a priori, and in some cases may be adversarial; (2) images may vary in their level of difficulty; and (3) multiple labels for the same image must be combined to provide an estimate of the actual label of the image.