Search Results - "Utke, Jean"

Timescales and regions of the sensitivity of Atlantic meridional volume and heat transport: Toward observing system design by Heimbach, Patrick, Wunsch, Carl, Ponte, Rui M., Forget, Gael, Hill, Chris, Utke, Jean

“…A dual (adjoint) model is used to explore elements of the oceanic state influencing the meridional volume and heat transports (MVT and MHT) in the sub-tropical…”
Get full text

An optimized treatment for algorithmic differentiation of an important glaciological fixed-point problem by Goldberg, Daniel N, Narayanan, Sri Hari Krishna, Hascoet, Laurent, Utke, Jean

“…We apply an optimized method to the adjoint generation of a time-evolving land ice model through algorithmic differentiation (AD). The optimization involves a…”
Get full text

An approach to computing discrete adjoints for MPI-parallelized models applied to Ice Sheet System Model 4.11 by Larour, Eric, Utke, Jean, Bovin, Anton, Morlighem, Mathieu, Perez, Gilberto

“…Within the framework of sea-level rise projections, there is a strong need for hindcast validation of the evolution of polar ice sheets in a way that tightly…”
Get full text

Corrigendum to “An inverse classification framework with limited budget and maximum number of perturbed samples” [Exp. Syst. Appl. 212 (2023) 118761] by Koo, Jaehoon, Klabjan, Diego, Utke, Jean

Get full text

An inverse classification framework with limited budget and maximum number of perturbed samples by Koo, Jaehoon, Klabjan, Diego, Utke, Jean

“…Most recent machine learning research focuses on developing new classifiers for the sake of improving classification accuracy. With many well-performing…”
Get full text

Combined Convolutional and Recurrent Neural Networks for Hierarchical Classification of Images by Koo, Jaehoon, Klabjan, Diego, Utke, Jean

“…Deep learning models based on CNNs are predominantly used in image classification tasks. Such approaches, assuming independence of object categories, normally…”
Get full text

Evaluating higher derivative tensors by forward propagation of univariate Taylor series by Griewank, Andreas, Utke, Jean, Walther, Andrea

“…This article considers the problem of evaluating all pure and mixed partial derivatives of some vector function defined by an evaluation procedure. The natural…”
Get full text

Nested Multi-view Image Classification by Ebrahimi, Abdolghani, Stec, Alexander, Klabjan, Diego, Utke, Jean

“…There are classification tasks that take as inputs groups of images rather than single images. In order to address such situations, we introduce a nested…”
Get full text

Programming language features, usage patterns, and the efficiency of generated adjoint code by Hascoët, Laurent, Utke, Jean

“…The computation of gradients via the reverse mode of algorithmic differentiation is a valuable technique in modelling many science and engineering…”
Get full text

Randomized heuristics for exploiting Jacobian scarcity by Lyons, Andrew, Safro, Ilya, Utke, Jean

“…In this paper, we describe a code transformation technique that, given a code for a vector function F, produces a code suitable for computing collections of…”
Get full text

Video to Video Generative Adversarial Network for Few-shot Learning Based on Policy Gradient by Ma, Yintai, Klabjan, Diego, Utke, Jean

“…The development of sophisticated models for video-to-video synthesis has been facilitated by recent advances in deep reinforcement learning and generative…”
Get full text

IIFE: Interaction Information Based Automated Feature Engineering by Overman, Tom, Klabjan, Diego, Utke, Jean

“…Automated feature engineering (AutoFE) is the process of automatically building and selecting new features that help improve downstream predictive performance…”
Get full text

Unsupervised Video Summarization by Li, Hanqing, Klabjan, Diego, Utke, Jean

“…This paper introduces a new, unsupervised method for automatic video summarization using ideas from generative adversarial networks but eliminating the…”
Get full text

S-Omninet: Structured Data Enhanced Universal Multimodal Learning Architecture by Xue, Ye, Klabjan, Diego, Utke, Jean

“…Multimodal multitask learning has attracted an increasing interest in recent years. Singlemodal models have been advancing rapidly and have achieved…”
Get full text

Preface by Christianson, Bruce, Naumann, Uwe, Utke, Jean, Walther, Andrea

“…Optimization Methods and Software Preface…”
Get full text

Preface by Christianson, Bruce, Naumann, Uwe, Utke, Jean, Walther, Andrea

Get full text

Preface by Christianson, Bruce, Naumann, Uwe, Utke, Jean, Walther, Andrea

Get full text

Early Classifying Multimodal Sequences by Cao, Alexander, Utke, Jean, Klabjan, Diego

“…Often pieces of information are received sequentially over time. When did one collect enough such pieces to classify? Trading wait time for decision certainty…”
Get full text

A Policy for Early Sequence Classification by Cao, Alexander, Utke, Jean, Klabjan, Diego

“…Sequences are often not received in their entirety at once, but instead, received incrementally over time, element by element. Early predictions yielding a…”
Get full text

Gradient-Boosted Based Structured and Unstructured Learning by Gavito, Andrea Treviño, Klabjan, Diego, Utke, Jean

“…We propose two frameworks to deal with problem settings in which both structured and unstructured data are available. Structured data problems are best solved…”
Get full text