55 citations · 197 across the 20 of their papers we have counts for
20 papers
Explanations of Black-Box Models based on Directional Feature Interactions
Aria Masoomi, Davin Hill, Zhonghui Xu +5
As machine learning algorithms are deployed ubiquitously to a variety of domains, it is imperative to make these often black-box models transparent. Several recent works explain bl…
Explainable deep learning for insights in El Niño and river flows
Yumin Liu, Kate Duffy, Jennifer G. Dy +1
The El Niño Southern Oscillation (ENSO) is a semi-periodic fluctuation in sea surface temperature (SST) over the tropical central and eastern Pacific Ocean that influences interann…
Kernel Dependence Network
Chieh Wu, Aria Masoomi, Arthur Gretton +1
We propose a greedy strategy to spectrally train a deep network for multi-class classification. Each layer is defined as a composition of linear weights with the feature map of a G…
Deep Markov Spatio-Temporal Factorization
Amirreza Farnoosh, Behnaz Rezaei, Eli Zachary Sennesh +6
We introduce deep Markov spatio-temporal factorization (DMSTF), a generative model for dynamical analysis of spatio-temporal data. Like other factor analysis methods, DMSTF approxi…
Weighting Is Worth the Wait: Bayesian Optimization with Importance Sampling
Setareh Ariafar, Zelda Mariet, Ehsan Elhamifar +3
Many contemporary machine learning models require extensive tuning of hyperparameters to perform well. A variety of methods, such as Bayesian optimization, have been developed to a…
Rate-Regularization and Generalization in VAEs
Alican Bozkurt, Babak Esmaeili, Jean-Baptiste Tristan +3
Variational autoencoders optimize an objective that combines a reconstruction loss (the distortion) and a KL term (the rate). The rate is an upper bound on the mutual information,…
Solving Interpretable Kernel Dimension Reduction
Chieh Wu, Jared Miller, Yale Chang +2
Kernel dimensionality reduction (KDR) algorithms find a low dimensional representation of the original data by optimizing kernel dependency measures that are capable of capturing n…
Iterative Spectral Method for Alternative Clustering
Chieh Wu, Stratis Ioannidis, Mario Sznaier +3
Given a dataset and an existing clustering as input, alternative clustering aims to find an alternative partition. One of the state-of-the-art approaches is Kernel Dimension Altern…
Streaming Adaptive Nonparametric Variational Autoencoder
Tingting Zhao, Zifeng Wang, Aria Masoomi +1
We develop a data driven approach to perform clustering and end-to-end feature learning simultaneously for streaming data that can adaptively detect novel clusters in emerging data…
Accelerated Experimental Design for Pairwise Comparisons
Yuan Guo, Jennifer Dy, Deniz Erdogmus +5
Pairwise comparison labels are more informative and less variable than class labels, but generating them poses a challenge: their number grows quadratically in the dataset size. We…
Can VAEs Generate Novel Examples?
Alican Bozkurt, Babak Esmaeili, Dana H. Brooks +2
An implicit goal in works on deep generative models is that such models should be able to generate novel examples that were not previously seen in the training data. In this paper,…
Deep feature transfer between localization and segmentation tasks
Szu-Yeu Hu, Andrew Beers, Ken Chang +8
In this paper, we propose a new pre-training scheme for U-net based image segmentation. We first train the encoding arm as a localization network to predict the center of the targe…
Quantifying Uncertainty in Discrete-Continuous and Skewed Data with Bayesian Deep Learning
Thomas Vandal, Evan Kodra, Jennifer Dy +3
Deep Learning (DL) methods have been transforming computer vision with innovative adaptations to other domains including climate change. For DL to pervade Science and Engineering (…
A Multiresolution Convolutional Neural Network with Partial Label Training for Annotating Reflectance Confocal Microscopy Images of Skin
Alican Bozkurt, Kivanc Kose, Christi Alessi-Fox +4
We describe a new multiresolution "nested encoder-decoder" convolutional network architecture and use it to annotate morphological patterns in reflectance confocal microscopy (RCM)…
Delineation of Skin Strata in Reflectance Confocal Microscopy Images using Recurrent Convolutional Networks with Toeplitz Attention
Alican Bozkurt, Kivanc Kose, Jaume Coll-Font +4
Reflectance confocal microscopy (RCM) is an effective, non-invasive pre-screening tool for skin cancer diagnosis, but it requires extensive training and experience to assess accura…
Subject-Specific Abnormal Region Detection in Traumatic Brain Injury Using Sparse Model Selection on High Dimensional Diffusion Data
Matineh Shaker, Deniz Erdogmus, Jennifer Dy +1
We present a method to estimate a multivariate Gaussian distribution of diffusion tensor features in a set of brain regions based on a small sample of healthy individuals, and use…
Multi-task Learning with Weak Class Labels: Leveraging iEEG to Detect Cortical Lesions in Cryptogenic Epilepsy
Bilal Ahmed, Thomas Thesen, Karen E. Blackmon +4
Multi-task learning (MTL) is useful for domains in which data originates from multiple sources that are individually under-sampled. MTL methods are able to learn classification mod…
Evaluating Crowdsourcing Participants in the Absence of Ground-Truth
Ramanathan Subramanian, Romer Rosales, Glenn Fung +1
Given a supervised/semi-supervised learning scenario where multiple annotators are available, we consider the problem of identification of adversarial or unreliable annotators.
Asymptotic Analysis of Objectives based on Fisher Information in Active Learning
Jamshid Sourati, Murat Akcakaya, Todd K. Leen +2
Obtaining labels can be costly and time-consuming. Active learning allows a learning algorithm to intelligently query samples to be labeled for efficient learning. Fisher informati…
Modeling Multiple Annotator Expertise in the Semi-Supervised Learning Scenario
Yan Yan, Romer Rosales, Glenn Fung +1
Learning algorithms normally assume that there is at most one annotation or label per data point. However, in some scenarios, such as medical diagnosis and on-line collaboration,mu…