Zobrazeno 1 - 10
of 143
pro vyhledávání: '"Dokmanic, Ivan"'
Autor:
Khorashadizadeh, AmirEhsan, Liaudat, Tobías I., Liu, Tianlin, McEwen, Jason D., Dokmanić, Ivan
Neural fields or implicit neural representations (INRs) have attracted significant attention in machine learning and signal processing due to their efficient continuous representation of images and 3D volumes. In this work, we build on INRs and intro
Externí odkaz:
http://arxiv.org/abs/2411.04995
Autor:
Liu, Tianlin, Münchmeyer, Jannes, Laurenti, Laura, Marone, Chris, de Hoop, Maarten V., Dokmanić, Ivan
We introduce the Seismic Language Model (SeisLM), a foundational model designed to analyze seismic waveforms -- signals generated by Earth's vibrations such as the ones originating from earthquakes. SeisLM is pretrained on a large collection of open-
Externí odkaz:
http://arxiv.org/abs/2410.15765
In graph learning the graph and the node features both contain noisy information about the node labels. In this paper we propose joint denoising and rewiring (JDR)--an algorithm to jointly rewire the graph and denoise the features, which improves the
Externí odkaz:
http://arxiv.org/abs/2408.07191
Feature-learning deep nets progressively collapse data to a regular low-dimensional geometry. How this phenomenon emerges from collective action of nonlinearity, noise, learning rate, and other choices that shape the dynamics, has eluded first-princi
Externí odkaz:
http://arxiv.org/abs/2407.19353
We introduce ICE-TIDE, a method for cryogenic electron tomography (cryo-ET) that simultaneously aligns observations and reconstructs a high-resolution volume. The alignment of tilt series in cryo-ET is a major problem limiting the resolution of recon
Externí odkaz:
http://arxiv.org/abs/2403.02182
Deep learning is the current de facto state of the art in tomographic imaging. A common approach is to feed the result of a simple inversion, for example the backprojection, to a convolutional neural network (CNN) which then computes the reconstructi
Externí odkaz:
http://arxiv.org/abs/2401.00816
Existing statistical learning guarantees for general kernel regressors often yield loose bounds when used with finite-rank kernels. Yet, finite-rank kernels naturally appear in several machine learning problems, e.g.\ when fine-tuning a pre-trained d
Externí odkaz:
http://arxiv.org/abs/2310.00987
Cryo-electron tomography (cryoET) is a technique that captures images of biological samples at different tilts, preserving their native state as much as possible. Along with the partial tilt series and noise, one of the major challenges in estimating
Externí odkaz:
http://arxiv.org/abs/2307.13516
Our understanding of regional seismicity from multi-station seismograms relies on the ability to associate arrival phases with their originating earthquakes. Deep-learning-based phase detection now detects small, high-rate arrivals from seismicity cl
Externí odkaz:
http://arxiv.org/abs/2307.07572
Relational inference aims to identify interactions between parts of a dynamical system from the observed dynamics. Current state-of-the-art methods fit the dynamics with a graph neural network (GNN) on a learnable graph. They use one-step message-pas
Externí odkaz:
http://arxiv.org/abs/2306.06041