Zobrazeno 1 - 10
of 69
pro vyhledávání: '"Azencot, Omri"'
Autor:
Ren, Pu, Nakata, Rie, Lacour, Maxime, Naiman, Ilan, Nakata, Nori, Song, Jialin, Bi, Zhengfa, Malik, Osman Asif, Morozov, Dmitriy, Azencot, Omri, Erichson, N. Benjamin, Mahoney, Michael W.
Predicting high-fidelity ground motions for future earthquakes is crucial for seismic hazard assessment and infrastructure resilience. Conventional empirical simulations suffer from sparse sensor distribution and geographically localized earthquake l
Externí odkaz:
http://arxiv.org/abs/2407.15089
One of the fundamental representation learning tasks is unsupervised sequential disentanglement, where latent codes of inputs are decomposed to a single static factor and a sequence of dynamic factors. To extract this latent information, existing met
Externí odkaz:
http://arxiv.org/abs/2406.18131
Autor:
Kaufman, Ilya, Azencot, Omri
Data augmentation (DA) methods tailored to specific domains generate synthetic samples by applying transformations that are appropriate for the characteristics of the underlying data domain, such as rotations on images and time warping on time series
Externí odkaz:
http://arxiv.org/abs/2406.10914
Autor:
Nochumsohn, Liran, Azencot, Omri
Data augmentation serves as a popular regularization technique to combat overfitting challenges in neural networks. While automatic augmentation has demonstrated success in image classification tasks, its application to time-series problems, particul
Externí odkaz:
http://arxiv.org/abs/2405.00319
Graph generation is integral to various engineering and scientific disciplines. Nevertheless, existing methodologies tend to overlook the generation of edge attributes. However, we identify critical applications where edge attributes are essential, m
Externí odkaz:
http://arxiv.org/abs/2402.04046
Generating realistic time series data is important for many engineering and scientific applications. Existing work tackles this problem using generative adversarial networks (GANs). However, GANs are unstable during training, and they can suffer from
Externí odkaz:
http://arxiv.org/abs/2310.02619
Autor:
Kaufman, Ilya, Azencot, Omri
Deep neural networks have been demonstrated to achieve phenomenal success in many domains, and yet their inner mechanisms are not well understood. In this paper, we investigate the curvature of image manifolds, i.e., the manifold deviation from being
Externí odkaz:
http://arxiv.org/abs/2305.19730
Unsupervised disentanglement is a long-standing challenge in representation learning. Recently, self-supervised techniques achieved impressive results in the sequential setting, where data is time-dependent. However, the latter methods employ modalit
Externí odkaz:
http://arxiv.org/abs/2305.15924
Disentangling complex data to its latent factors of variation is a fundamental task in representation learning. Existing work on sequential disentanglement mostly provides two factor representations, i.e., it separates the data to time-varying and ti
Externí odkaz:
http://arxiv.org/abs/2303.17264
Regularising the parameter matrices of neural networks is ubiquitous in training deep models. Typical regularisation approaches suggest initialising weights using small random values, and to penalise weights to promote sparsity. However, these widely
Externí odkaz:
http://arxiv.org/abs/2212.12086