482 citations · 604 across the 16 of their papers we have counts for
16 papers
Number Theoretic Accelerated Learning of Physics-Informed Neural Networks
Takashi Matsubara, Takaharu Yaguchi
Physics-informed neural networks solve partial differential equations by training neural networks. Since this method approximates infinite-dimensional PDE solutions with finite col…
Deep Curvilinear Editing: Commutative and Nonlinear Image Manipulation for Pretrained Deep Generative Model
Takehiro Aoshima, Takashi Matsubara
Semantic editing of images is the fundamental goal of computer vision. Although deep learning methods, such as generative adversarial networks (GANs), are capable of producing high…
FINDE: Neural Differential Equations for Finding and Preserving Invariant Quantities
Takashi Matsubara, Takaharu Yaguchi
Many real-world dynamical systems are associated with first integrals (a.k.a. invariant quantities), which are quantities that remain unchanged over time. The discovery and underst…
Cancer Subtyping by Improved Transcriptomic Features Using Vector Quantized Variational Autoencoder
Zheng Chen, Ziwei Yang, Lingwei Zhu +5
Defining and separating cancer subtypes is essential for facilitating personalized therapy modality and prognosis of patients. The definition of subtypes has been constantly recali…
Automated Cancer Subtyping via Vector Quantization Mutual Information Maximization
Zheng Chen, Lingwei Zhu, Ziwei Yang +1
Cancer subtyping is crucial for understanding the nature of tumors and providing suitable therapy. However, existing labelling methods are medically controversial, and have driven…
An Error Analysis Framework for Neural Network Modeling of Dynamical Systems
Shunpei Terakawa, Takashi Matsubara, Takaharu Yaguchi
We propose a theoretical framework for investigating a modeling error caused by numerical integration in the learning process of dynamics. Recently, learning equations of motion to…
KAM Theory Meets Statistical Learning Theory: Hamiltonian Neural Networks with Non-Zero Training Loss
Yuhan Chen, Takashi Matsubara, Takaharu Yaguchi
Many physical phenomena are described by Hamiltonian mechanics using an energy function (the Hamiltonian). Recently, the Hamiltonian neural network, which approximates the Hamilton…
Symplectic Adjoint Method for Exact Gradient of Neural ODE with Minimal Memory
Takashi Matsubara, Yuto Miyatake, Takaharu Yaguchi
A neural network model of a differential equation, namely neural ODE, has enabled the learning of continuous-time dynamical systems and probabilistic distributions with high accura…
ChartPointFlow for Topology-Aware 3D Point Cloud Generation
Takumi Kimura, Takashi Matsubara, Kuniaki Uehara
A point cloud serves as a representation of the surface of a three-dimensional (3D) shape. Deep generative models have been adapted to model their variations typically using a map…
Target-Oriented Deformation of Visual-Semantic Embedding Space
Takashi Matsubara
Multimodal embedding is a crucial research topic for cross-modal understanding, data mining, and translation. Many studies have attempted to extract representations from given enti…
Generative adversarial network based on chaotic time series
Makoto Naruse, Takashi Matsubara, Nicolas Chauvet +3
Generative adversarial network (GAN) is gaining increased importance in artificially constructing natural images and related functionalities wherein two networks called generator a…
Exploring Uncertainty Measures for Image-Caption Embedding-and-Retrieval Task
Kenta Hama, Takashi Matsubara, Kuniaki Uehara +1
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. O…
Data Augmentation using Random Image Cropping and Patching for Deep CNNs
Ryo Takahashi, Takashi Matsubara, Kuniaki Uehara
Deep convolutional neural networks (CNNs) have achieved remarkable results in image processing tasks. However, their high expression ability risks overfitting. Consequently, data a…
Deep Generative Model using Unregularized Score for Anomaly Detection with Heterogeneous Complexity
Takashi Matsubara, Kenta Hama, Ryosuke Tachibana +1
Accurate and automated detection of anomalous samples in a natural image dataset can be accomplished with a probabilistic model for end-to-end modeling of images. Such images have…
Deep Neural Generative Model of Functional MRI Images for Psychiatric Disorder Diagnosis
Takashi Matsubara, Tetsuo Tashiro, Kuniaki Uehara
Accurate diagnosis of psychiatric disorders plays a critical role in improving the quality of life for patients and potentially supports the development of new treatments. Many stu…
A Novel Weight-Shared Multi-Stage CNN for Scale Robustness
Ryo Takahashi, Takashi Matsubara, Kuniaki Uehara
Convolutional neural networks (CNNs) have demonstrated remarkable results in image classification for benchmark tasks and practical applications. The CNNs with deeper architectures…