no code implementations • 5 Feb 2024 • Saiful Khan, Scott Jones, Benjamin Bach, Jaehoon Cha, Min Chen, Julie Meikle, Jonathan C Roberts, Jeyan Thiyagalingam, Jo Wood, Panagiotis D. Ritsos
Motivated initially by the need to communicate time series data during the COVID-19 pandemic, we developed a novel computer-assisted method for meta-authoring of stories, which enables the design of storyboards that include feature-action patterns in anticipation of potential features that may appear in dynamically arrived or selected data.
no code implementations • 11 Dec 2023 • Varshitha Chennamsetti, Gregor von Laszewski, Ruochen Gu, Laiba Mehnaz, Juri Papay, Samuel Jackson, Jeyan Thiyagalingam, Sergey V. Samsonau, Geoffrey C. Fox
We provide a description of the cloud masking benchmark, as well as a summary of our submission to MLCommons on the benchmark experiment we conducted.
1 code implementation • 1 Nov 2023 • Kuangdai Leng, Mallikarjun Shankar, Jeyan Thiyagalingam
Automatic differentiation (AD) is a critical step in physics-informed machine learning, required for computing the high-order derivatives of network output w. r. t.
no code implementations • 12 Sep 2023 • Kuangdai Leng, Jeyan Thiyagalingam
Convolution is a fundamental operation in image processing and machine learning.
1 code implementation • 1 Dec 2022 • Kuangdai Leng, Jeyan Thiyagalingam
Inspired by this pitfall, we prove that a linear PDE up to the $n$-th order can be strictly satisfied by an MLP with $C^n$ activation functions when the weights of its output layer lie on a certain hyperplane, as called the out-layer-hyperplane.
no code implementations • 9 Sep 2022 • Jola Mirecka, Marjan Famili, Anna Kotańska, Nikolai Juraschko, Beatriz Costa-Gomes, Colin M. Palmer, Jeyan Thiyagalingam, Tom Burnley, Mark Basham, Alan R. Lowe
In this work we present affinity-VAE: a framework for automatic clustering and classification of objects in multidimensional image data based on their similarity.
no code implementations • 16 Mar 2022 • Luisa Lucie-Smith, Hiranya V. Peiris, Andrew Pontzen, Brian Nord, Jeyan Thiyagalingam, Davide Piras
The additional dimension in the representation contains information about the infalling material in the outer profiles of dark matter halos, thus discovering the splashback boundary of halos without prior knowledge of the halos' dynamical history.
no code implementations • 20 Feb 2022 • Jaehoon Cha, Jeyan Thiyagalingam
Noting the importance of factorizing (or disentangling) the latent space, we propose a novel, non-probabilistic disentangling framework for autoencoders, based on the principles of symmetry transformations in group-theory.
no code implementations • 25 Oct 2021 • Jeyan Thiyagalingam, Mallikarjun Shankar, Geoffrey Fox, Tony Hey
In this paper, we describe our approach to the development of scientific machine learning benchmarks and review other approaches to benchmarking scientific machine learning.
2 code implementations • 20 Nov 2020 • Luisa Lucie-Smith, Hiranya V. Peiris, Andrew Pontzen, Brian Nord, Jeyan Thiyagalingam
We train a three-dimensional convolutional neural network (CNN) to predict the mass of dark matter halos from the initial conditions, and quantify in full generality the amounts of information in the isotropic and anisotropic aspects of the initial density field about final halo masses.