P
Padhraic Smyth
Researcher at University of California, Irvine
Publications - 359
Citations - 38795
Padhraic Smyth is an academic researcher from University of California, Irvine. The author has contributed to research in topics: Inference & Topic model. The author has an hindex of 80, co-authored 342 publications receiving 36653 citations. Previous affiliations of Padhraic Smyth include University of California & Jet Propulsion Laboratory.
Papers
More filters
Proceedings ArticleDOI
Objective Functions For Neural Network Classifier Design
TL;DR: In this paper, necessary and sufficient conditions on the required form of an objective function to provide probability estimates are derived, which leads to the definition of a general class of functions which includes MSE and cross entropy (CE) as two of the simplest cases.
Book ChapterDOI
Analyzing text and social network data with probabilistic models
TL;DR: An overview of recent work using probabilistic latent variable models to analyze large text and social network data sets, specifically data in the form of time-stamped events between nodes (such as emails exchanged among individuals over time).
Journal ArticleDOI
Variable-Based Calibration for Machine Learning Classifiers
Mark Kelly,Padhraic Smyth +1 more
TL;DR: It is shown that models with near-perfect ECE can exhibit significant variable-based calibration error as a function of features of the data, and that it can persist after the application of existing recalibration methods.
Proceedings ArticleDOI
Image Retrieval by Content: A Machine Learning Approach
Usama M. Fayyad,Padhraic Smyth +1 more
TL;DR: Two such applications at JPL are presented: the SKICAT system used for the reduction and analysis of a 3 terabyte astronomical data set, and the JARtool system to be used in automatically analyzing the Magellan data set consisting of over 30,000 images of the surface of Venus.
Journal Article
Automating Data Science: Prospects and Challenges
Tijl De Bie,Luc De Raedt,José Hernández-Orallo,Holger H. Hoos,Padhraic Smyth,Christopher Williams +5 more
TL;DR: In this paper, the authors argue that important parts of data science are already being automated, especially in the modeling stages, where techniques such as automated machine learning (AutoML) are gaining traction.