相关论文: Deep Generative Modeling-based Data Augmentation w…

We present an empirical evaluation of fMRI data augmentation via synthesis. For synthesis we use generative mod-els trained on real neuroimaging data to produce novel task-dependent functional brain images. Analyzed generative mod-els…

The spatiotemporal resolution of Partial Differential Equations (PDEs) plays important roles in the mathematical description of the world's physical phenomena. In general, scientists and engineers solve PDEs numerically by the use of…

One way to expand the available dataset for training AI models in the medical field is through the use of Generative Adversarial Networks (GANs) for data augmentation. GANs work by employing a generator network to create new data samples…

Deep Learning (DL) methods have emerged as one of the most powerful tools for functional approximation and prediction. While the representation properties of DL have been well studied, uncertainty quantification remains challenging and…

The distribution of resources in the subsurface is deeply linked to the variations of its physical properties. Generative modeling has long been used to predict those physical properties while quantifying the associated uncertainty. But…

Deep Neural Networks (DNNs) rely heavily on dense arithmetic operations, motivating the use of Approximate Multipliers (AxMs) to reduce energy consumption in hardware accelerators. However, a rigorous mathematical characterization of how…

Neural Stochastic Differential Equations (Neural SDEs) have emerged as powerful mesh-free generative models for continuous stochastic processes, with critical applications in fields such as finance, physics, and biology. Previous…

Mesh-based simulations play a key role when modeling complex physical systems that, in many disciplines across science and engineering, require the solution of parametrized time-dependent nonlinear partial differential equations (PDEs). In…

Deep Neural Networks (DNNs) are increasingly deployed across applications. However, ensuring their reliability remains a challenge, and in many situations, alternative models with similar functionality and accuracy are available.…

Deep learning models need a sufficient amount of data in order to be able to find the hidden patterns in it. It is the purpose of generative modeling to learn the data distribution, thus allowing us to sample more data and augment the…

In many mechanistic medical, biological, physical and engineered spatiotemporal dynamic models the numerical solution of partial differential equations (PDEs) can make simulations impractically slow. Biological models require the…

Annotating the right data for training deep neural networks is an important challenge. Active learning using uncertainty estimates from Bayesian Neural Networks (BNNs) could provide an effective solution to this. Despite being theoretically…

Generative Adversarial Networks (GANs) have been used widely to generate large volumes of synthetic data. This data is being utilized for augmenting with real examples in order to train deep Convolutional Neural Networks (CNNs). Studies…

Deep Neural Networks (DNNs) show a significant impact on medical imaging. One significant problem with adopting DNNs for skin cancer classification is that the class frequencies in the existing datasets are imbalanced. This problem hinders…

We develop the sparse VAE for unsupervised representation learning on high-dimensional data. The sparse VAE learns a set of latent factors (representations) which summarize the associations in the observed data features. The underlying…

Generative models are a class of AI models capable of creating new instances of data by learning and sampling from their statistical distributions. In recent years, these models have gained prominence in machine learning due to the…

Training robust supervised deep learning models for many geospatial applications of computer vision is difficult due to dearth of class-balanced and diverse training data. Conversely, obtaining enough training data for many applications is…

Due to the constraints on model performance imposed by the size of the training data, data augmentation has become an essential technique in deep learning. However, most existing data augmentation methods are affected by information loss…

Energy-based models (EBM) have become increasingly popular within computer vision. EBMs bring a probabilistic approach to training deep neural networks (DNN) and have been shown to enhance performance in areas such as calibration,…

Supervised deep learning methods are enjoying enormous success in many practical applications of computer vision and have the potential to revolutionize robotics. However, the marked performance degradation to biases and imbalanced data…