Search Results for author:
Found 18 papers, 5 papers with code
Predicated Diffusion: Predicate Logic-Based Attention Guidance for Text-to-Image Diffusion Models
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.
Good Lattice Training: Physics-Informed Neural Networks Accelerated by Number Theory
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.
Deep Curvilinear Editing: Commutative and Nonlinear Image Manipulation for Pretrained Deep Generative Model
Recent studies have investigated a way of manipulating the latent variable to determine the images to be generated.
FINDE: Neural Differential Equations for Finding and Preserving Invariant Quantities
However, these models incorporate the underlying structures, and in most situations where neural networks learn unknown systems, these structures are also unknown.
Cancer Subtyping by Improved Transcriptomic Features Using Vector Quantized Variational Autoencoder
As such, existing methods often impose unrealistic assumptions to extract useful features from the data while avoiding overfitting to spurious correlations.
Automated Cancer Subtyping via Vector Quantization Mutual Information Maximization
Cancer subtyping is crucial for understanding the nature of tumors and providing suitable therapy.
Neural Symplectic Form: Learning Hamiltonian Equations on General Coordinate Systems
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.
KAM Theory Meets Statistical Learning Theory: Hamiltonian Neural Networks with Non-Zero Training Loss
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.
Symplectic Adjoint Method for Exact Gradient of Neural ODE with Minimal Memory
The symplectic adjoint method obtains the exact gradient (up to rounding error) with memory proportional to the number of uses plus the network size.
ChartPointFlow for Topology-Aware 3D Point Cloud Generation
Then, a map conditioned on a label is assigned to a continuous subset of a point cloud, similar to a chart of a manifold.
Target-Oriented Deformation of Visual-Semantic Embedding Space
Multimodal embedding is a crucial research topic for cross-modal understanding, data mining, and translation.
Generative adversarial network based on chaotic time series
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.
Deep Energy-Based Modeling of Discrete-Time Physics
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.
Exploring Uncertainty Measures for Image-Caption Embedding-and-Retrieval Task
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.
Data Augmentation using Random Image Cropping and Patching for Deep CNNs
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.
Deep Generative Model using Unregularized Score for Anomaly Detection with Heterogeneous Complexity
Empirical results demonstrate that the unregularized score is robust to the inherent complexity of samples and can be used to better detect anomalies.
Deep Neural Generative Model of Functional MRI Images for Psychiatric Disorder Diagnosis
This study applied the proposed model to diagnose schizophrenia and bipolar disorders.
A Novel Weight-Shared Multi-Stage CNN for Scale Robustness
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.
