no code implementations • 24 Mar 2024 • Anuj Karpatne, Xiaowei Jia, Vipin Kumar
We discuss different facets of KGML research in terms of the type of scientific knowledge used, the form of knowledge-ML integration explored, and the method for incorporating scientific knowledge in ML.
1 code implementation • 7 Nov 2023 • Dipanjyoti Paul, Arpita Chowdhury, Xinqi Xiong, Feng-Ju Chang, David Carlyn, Samuel Stevens, Kaiya Provost, Anuj Karpatne, Bryan Carstens, Daniel Rubenstein, Charles Stewart, Tanya Berger-Wolf, Yu Su, Wei-Lun Chao
Unlike mainstream classifiers that wait until the last fully-connected layer to incorporate class information to make predictions, we investigate a proactive approach, asking each class to search for itself in an image.
1 code implementation • 13 Oct 2023 • Medha Sawhney, Bhas Karmarkar, Eric J. Leaman, Arka Daw, Anuj Karpatne, Bahareh Behkam
Herein, we report Motion Enhanced Multi-level Tracker (MEMTrack), a robust pipeline for detecting and tracking microrobots using synthetic motion features, deep learning-based object detection, and a modified Simple Online and Real-time Tracking (SORT) algorithm with interpolation for tracking.
no code implementations • 26 Sep 2023 • Mohannad Elhamod, Anuj Karpatne
In recent years, there has been a growing interest in visualizing the loss landscape of neural networks.
no code implementations • 21 Aug 2023 • M. Maruf, Arka Daw, Amartya Dutta, Jie Bu, Anuj Karpatne
Furthermore, we propose random cropping as a stochastic aggregation technique that improves the performance of saliency, making it a strong alternative to CAM for WS3.
1 code implementation • 5 Jun 2023 • Mohannad Elhamod, Mridul Khurana, Harish Babu Manogaran, Josef C. Uyeda, Meghan A. Balk, Wasila Dahdul, Yasin Bakış, Henry L. Bart Jr., Paula M. Mabee, Hilmar Lapp, James P. Balhoff, Caleb Charpentier, David Carlyn, Wei-Lun Chao, Charles V. Stewart, Daniel I. Rubenstein, Tanya Berger-Wolf, Anuj Karpatne
Discovering evolutionary traits that are heritable across species on the tree of life (also referred to as a phylogenetic tree) is of great interest to biologists to understand how organisms diversify and evolve.
1 code implementation • 24 May 2023 • Jie Bu, Kazi Sajeed Mehrab, Anuj Karpatne
Conditional graph generation tasks involve training a model to generate a graph given a set of input conditions.
no code implementations • 2 Nov 2022 • Arka Daw, Kyongmin Yeo, Anuj Karpatne, Levente Klein
Inferring the source information of greenhouse gases, such as methane, from spatially sparse sensor observations is an essential element in mitigating climate change.
1 code implementation • 5 Jul 2022 • Arka Daw, Jie Bu, Sifan Wang, Paris Perdikaris, Anuj Karpatne
In this paper, we provide a novel perspective of failure modes of PINNs by hypothesizing that training PINNs relies on successful "propagation" of solution from initial and/or boundary condition points to interior points.
no code implementations • 12 Feb 2022 • Sangeeta Srivastava, Samuel Olin, Viktor Podolskiy, Anuj Karpatne, Wei-Cheng Lee, Anish Arora
Unfortunately, for the learned models in these scientific applications to achieve generalization, a large, diverse, and preferably annotated dataset is typically needed and is computationally expensive to obtain.
no code implementations • 16 Nov 2021 • Austin Chennault, Andrey A. Popov, Amit N. Subrahmanya, Rachel Cooper, Ali Haisam Muhammad Rafid, Anuj Karpatne, Adrian Sandu
Surrogates constructed using adjoint information demonstrate superior performance on the 4D-Var data assimilation problem compared to a standard neural network surrogate that uses only forward dynamics information.
1 code implementation • NeurIPS 2021 • Jie Bu, Arka Daw, M. Maruf, Anuj Karpatne
We also theoretically show that the learning objective of DAM is directly related to minimizing the L0 norm of the masking layer.
1 code implementation • 6 Jun 2021 • Arka Daw, M. Maruf, Anuj Karpatne
In scientific applications, it is also important to inform the learning of DL models with knowledge of physics of the problem to produce physically consistent and generalized solutions.
no code implementations • 9 Apr 2021 • Reza Sepasdar, Anuj Karpatne, Maryam Shakiba
The proposed deep learning framework predicts the post-failure full-field stress distribution and crack pattern in two-dimensional representations of the composites based on the geometry of microstructures.
1 code implementation • 20 Jan 2021 • Jie Bu, Anuj Karpatne
We propose quadratic residual networks (QRes) as a new type of parameter-efficient neural network architecture, by adding a quadratic residual term to the weighted sum of inputs before applying activation functions.
2 code implementations • 30 Sep 2020 • Ioannis Papakis, Abhijit Sarkar, Anuj Karpatne
This new paradigm enables the network to leverage the "context" information of the geometry of objects and allows us to model the interactions among the features of multiple objects.
1 code implementation • 2 Jul 2020 • Mohannad Elhamod, Jie Bu, Christopher Singh, Matthew Redell, Abantika Ghosh, Viktor Podolskiy, Wei-Cheng Lee, Anuj Karpatne
Physics-guided Neural Networks (PGNNs) represent an emerging class of neural networks that are trained using physics-guided (PG) loss functions (capturing violations in network outputs with known physics), along with the supervision contained in data.
1 code implementation • 2 Jul 2020 • M. Maruf, Anuj Karpatne
Existing algorithms for this task rely on negative sampling objectives that maximize the similarity in node embeddings at nearby nodes (referred to as "cohesion") by maintaining positive and negative corpus of node pairs.
no code implementations • 28 Jan 2020 • Xiaowei Jia, Jared Willard, Anuj Karpatne, Jordan S. Read, Jacob A Zwart, Michael Steinbach, Vipin Kumar
Specifically, we show that a PGRNN can improve prediction accuracy over that of physics-based models, while generating outputs consistent with physical laws.
1 code implementation • 6 Nov 2019 • Nikhil Muralidhar, Jie Bu, Ze Cao, Long He, Naren Ramakrishnan, Danesh Tafti, Anuj Karpatne
In such situations, it is often useful to rely on machine learning methods to fill in the gap by learning a model of the complex physical process directly from simulation data.
1 code implementation • 6 Nov 2019 • Arka Daw, R. Quinn Thomas, Cayelan C. Carey, Jordan S. Read, Alison P. Appling, Anuj Karpatne
To simultaneously address the rising need of expressing uncertainties in deep learning models along with producing model outputs which are consistent with the known scientific knowledge, we propose a novel physics-guided architecture (PGA) of neural networks in the context of lake temperature modeling where the physical constraints are hard coded in the neural network architecture.
no code implementations • 3 Jun 2019 • Saurabh Agrawal, Saurabh Verma, Anuj Karpatne, Stefan Liess, Snigdhansu Chatterjee, Vipin Kumar
Traditional approaches focus on finding relationships between two entire time series, however, many interesting relationships exist in small sub-intervals of time and remain feeble during other sub-intervals.
no code implementations • 31 Oct 2018 • Xiaowei Jia, Jared Willard, Anuj Karpatne, Jordan Read, Jacob Zwart, Michael Steinbach, Vipin Kumar
This paper proposes a physics-guided recurrent neural network model (PGRNN) that combines RNNs and physics-based models to leverage their complementary strengths and improve the modeling of physical processes.
no code implementations • 5 Oct 2018 • Xiaowei Jia, Anuj Karpatne, Jared Willard, Michael Steinbach, Jordan Read, Paul C Hanson, Hilary A Dugan, Vipin Kumar
In this paper, we introduce a novel framework for combining scientific knowledge within physics-based models and recurrent neural networks to advance scientific discovery in many dynamical systems.
no code implementations • 16 Feb 2018 • Saurabh Agrawal, Saurabh Verma, Gowtham Atluri, Anuj Karpatne, Stefan Liess, Angus Macdonald III, Snigdhansu Chatterjee, Vipin Kumar
In this paper, we define the notion of a sub-interval relationship (SIR) to capture inter- actions between two time series that are prominent only in certain sub-intervals of time.
no code implementations • 19 Dec 2017 • Xiaowei Jia, Ankush Khandelwal, Anuj Karpatne, Vipin Kumar
The experiments demonstrate the superiority of our proposed method in sequence classification performance and in detecting discriminative shifting patterns.
no code implementations • 15 Nov 2017 • Ankush Khandelwal, Anuj Karpatne, Vipin Kumar
Various data fusion methods have been proposed in the literature that mainly rely on individual timesteps when both datasets are available to learn a mapping between features values at different resolutions using local relationships between pixels.
no code implementations • 13 Nov 2017 • Anuj Karpatne, Imme Ebert-Uphoff, Sai Ravela, Hassan Ali Babaie, Vipin Kumar
Geosciences is a field of great societal relevance that requires solutions to several urgent problems facing our humanity and the planet.
1 code implementation • 13 Nov 2017 • Gowtham Atluri, Anuj Karpatne, Vipin Kumar
Large volumes of spatio-temporal data are increasingly collected and studied in diverse domains including, climate science, social sciences, neuroscience, epidemiology, transportation, mobile health, and Earth sciences.
2 code implementations • 31 Oct 2017 • Arka Daw, Anuj Karpatne, William Watkins, Jordan Read, Vipin Kumar
This paper introduces a framework for combining scientific knowledge of physics-based models with neural networks to advance scientific discovery.
no code implementations • 27 Dec 2016 • Anuj Karpatne, Gowtham Atluri, James Faghmous, Michael Steinbach, Arindam Banerjee, Auroop Ganguly, Shashi Shekhar, Nagiza Samatova, Vipin Kumar
Theory-guided data science (TGDS) is an emerging paradigm that aims to leverage the wealth of scientific knowledge for improving the effectiveness of data science models in enabling scientific discovery.