no code implementations • 3 Oct 2023 • Kota Sueyoshi, Takashi Matsubara
We consider that the root of the above issues lies in the text encoder, which often focuses only on individual words and neglects the logical relationships between them.
no code implementations • 26 Jul 2023 • Takashi Matsubara, Takaharu Yaguchi
However, the solutions to PDEs are inherently infinite-dimensional, and the distance between the output and the solution is defined by an integral over the domain.
no code implementations • CVPR 2023 • Takehiro Aoshima, Takashi Matsubara
Recent studies have investigated a way of manipulating the latent variable to determine the images to be generated.
no code implementations • 1 Oct 2022 • Takashi Matsubara, Takaharu Yaguchi
However, these models incorporate the underlying structures, and in most situations where neural networks learn unknown systems, these structures are also unknown.
no code implementations • 20 Jul 2022 • Zheng Chen, Ziwei Yang, Lingwei Zhu, Guang Shi, Kun Yue, Takashi Matsubara, Shigehiko Kanaya, MD Altaf-Ul-Amin
As such, existing methods often impose unrealistic assumptions to extract useful features from the data while avoiding overfitting to spurious correlations.
1 code implementation • 22 Jun 2022 • Zheng Chen, Lingwei Zhu, Ziwei Yang, Takashi Matsubara
Cancer subtyping is crucial for understanding the nature of tumors and providing suitable therapy.
no code implementations • NeurIPS 2021 • Yuhan Chen, Takashi Matsubara, Takaharu Yaguchi
In this study, we propose a model that learns the symplectic form from data using neural networks, thereby providing a method for learning Hamiltonian equations from data represented in general coordinate systems, which are not limited to the generalized coordinates and the generalized momenta.
no code implementations • 22 Feb 2021 • Yuhan Chen, Takashi Matsubara, Takaharu Yaguchi
To apply the KAM theory, we provide a generalization error bound for Hamiltonian neural networks by deriving an estimate of the covering number of the gradient of the multi-layer perceptron, which is the key ingredient of the model.
1 code implementation • NeurIPS 2021 • Takashi Matsubara, Yuto Miyatake, Takaharu Yaguchi
The symplectic adjoint method obtains the exact gradient (up to rounding error) with memory proportional to the number of uses plus the network size.
no code implementations • 4 Dec 2020 • Takumi Kimura, Takashi Matsubara, Kuniaki Uehara
Then, a map conditioned on a label is assigned to a continuous subset of a point cloud, similar to a chart of a manifold.
1 code implementation • 15 Oct 2019 • Takashi Matsubara
Multimodal embedding is a crucial research topic for cross-modal understanding, data mining, and translation.
no code implementations • 24 May 2019 • Makoto Naruse, Takashi Matsubara, Nicolas Chauvet, Kazutaka Kanno, Tianyu Yang, Atsushi Uchida
Here we utilize chaotic time series generated experimentally by semiconductor lasers for the latent variables of GAN whereby the inherent nature of chaos can be reflected or transformed into the generated output data.
1 code implementation • NeurIPS 2020 • Takashi Matsubara, Ai Ishikawa, Takaharu Yaguchi
Physical phenomena in the real world are often described by energy-based modeling theories, such as Hamiltonian mechanics or the Landau theory, which yield various physical laws.
no code implementations • 9 Apr 2019 • Kenta Hama, Takashi Matsubara, Kuniaki Uehara, Jianfei Cai
With the wide development of black-box machine learning algorithms, particularly deep neural network (DNN), the practical demand for the reliability assessment is rapidly rising.
1 code implementation • 22 Nov 2018 • Ryo Takahashi, Takashi Matsubara, Kuniaki Uehara
We also confirmed that deep CNNs with RICAP achieve better results on classification tasks using CIFAR-100 and ImageNet and an image-caption retrieval task using Microsoft COCO.
no code implementations • 16 Jul 2018 • Takashi Matsubara, Kenta Hama, Ryosuke Tachibana, Kuniaki Uehara
Empirical results demonstrate that the unregularized score is robust to the inherent complexity of samples and can be used to better detect anomalies.
no code implementations • 18 Dec 2017 • Takashi Matsubara, Tetsuo Tashiro, Kuniaki Uehara
This study applied the proposed model to diagnose schizophrenia and bipolar disorders.
no code implementations • 12 Feb 2017 • Ryo Takahashi, Takashi Matsubara, Kuniaki Uehara
The proposed WSMS-Net is easily combined with existing deep CNNs such as ResNet and DenseNet and enables them to acquire robustness to object scaling.