We derive a data-driven method for the approximation of the Koopman generator called gEDMD, which can be regarded as a straightforward extension of EDMD (extended dynamic mode decomposition). This approach is applicable to deterministic and stochastic dynamical systems. It can be used for computing eigenvalues, eigenfunctions, and modes of the generator and for system identification. In addition to learning the governing equations of deterministic systems, which then reduces to SINDy (sparse identification of nonlinear dynamics), it is possible to identify the drift and diffusion terms of stochastic differential equations from data. Moreover, we apply gEDMD to derive coarse-grained models of high-dimensional systems, and also to determine efficient model predictive control strategies. We highlight relationships with other methods and demonstrate the efficacy of the proposed methods using several guiding examples and prototypical molecular dynamics problems.

This paper presents a methodology and workflow that overcome the limitations of the conventional Generative Adversarial Networks (GANs) for geological facies modeling. It attempts to improve the training stability and guarantee the diversity of the generated geology through interpretable latent vectors. The resulting samples are ensured to have the equal probability (or an unbiased distribution) as from the training dataset. This is critical when applying GANs to generate unbiased and representative geological models that can be further used to facilitate objective uncertainty evaluation and optimal decision-making in oil field exploration and development. We proposed and implemented a new variant of GANs called Info-WGAN for the geological facies modeling that combines Information Maximizing Generative Adversarial Network (InfoGAN) with Wasserstein distance and Gradient Penalty (GP) for learning interpretable latent codes as well as generating stable and unbiased distribution from the training data. Different from the original GAN design, InfoGAN can use the training images with full, partial, or no labels to perform disentanglement of the complex sedimentary types exhibited in the training dataset to achieve the variety and diversity of the generated samples. This is accomplished by adding additional categorical variables that provide disentangled semantic representations besides the mere randomized latent vector used in the original GANs. By such means, a regularization term is used to maximize the mutual information between such latent categorical codes and the generated geological facies in the loss function. Furthermore, the resulting unbiased sampling by Info-WGAN makes the data conditioning much easier than the conventional GANs in geological modeling because of the variety and diversity as well as the equal probability of the unconditional sampling by the generator.

Amharic is the official language of the Federal Democratic Republic of Ethiopia. There are lots of historic Amharic and Ethiopic handwritten documents addressing various relevant issues including governance, science, religious, social rules, cultures and art works which are very reach indigenous knowledge. The Amharic language has its own alphabet derived from Ge'ez which is currently the liturgical language in Ethiopia. Handwritten character recognition for non Latin scripts like Amharic is not addressed especially using the advantages of the state of the art techniques. This research work designs for the first time a model for Amharic handwritten character recognition using a convolutional neural network. The dataset was organized from collected sample handwritten documents and data augmentation was applied for machine learning. The model was further enhanced using multi-task learning from the relationships of the characters. Promising results are observed from the later model which can further be applied to word prediction.

Given a data set and a subset of labels the problem of semi-supervised learning on point clouds is to extend the labels to the entire data set. In this paper we extend the labels by minimising the constrained discrete $p$-Dirichlet energy. Under suitable conditions the discrete problem can be connected, in the large data limit, with the minimiser of a weighted continuum $p$-Dirichlet energy with the same constraints. We take advantage of this connection by designing numerical schemes that first estimate the density of the data and then apply PDE methods, such as pseudo-spectral methods, to solve the corresponding Euler-Lagrange equation. We prove that our scheme is consistent in the large data limit for two methods of density estimation: kernel density estimation and spline kernel density estimation.

Current cameras are capable of recording high resolution video. While viewing on a mobile device, a user can manually zoom into this high resolution video to get more detailed view of objects and activities. However, manual zooming is not suitable for surveillance and monitoring. It is tiring to continuously keep zooming into various regions of the video. Also, while viewing one region, the operator may miss activities in other regions. In this paper, we propose sZoom, a framework to automatically zoom into a high resolution surveillance video. The proposed framework selectively zooms into the sensitive regions of the video to present details of the scene, while still preserving the overall context required for situation assessment. A multi-variate Gaussian penalty is introduced to ensure full coverage of the scene. The method achieves near real-time performance through a number of timing optimizations. An extensive user study shows that, while watching a full HD video on a mobile device, the system enhances the security operator's efficiency in understanding the details of the scene by 99% on the average compared to a scaled version of the original high resolution video. The produced video achieved 46% higher ratings for usefulness in a surveillance task.

Sequential pulling policies to flatten and smooth fabrics have applications from surgery to manufacturing to home tasks such as bed making and folding clothes. Due to the complexity of fabric states and dynamics, we apply deep imitation learning to learn policies that, given color or depth images of a rectangular fabric sample, estimate pick points and pull vectors to spread the fabric to maximize coverage. To generate data, we develop a fabric simulator and an algorithmic demonstrator that has access to complete state information. We train policies in simulation using domain randomization and dataset aggregation (DAgger) on three tiers of difficulty in the initial randomized configuration. We present results comparing five baseline policies to learned policies and report systematic comparisons of color vs. depth images as inputs. In simulation, learned policies achieve comparable or superior performance to analytic baselines. In 120 physical experiments with the da Vinci Research Kit (dVRK) surgical robot, policies trained in simulation attain 86% and 69% final coverage for color and depth inputs, respectively, suggesting the feasibility of learning fabric smoothing policies from simulation. Supplementary material is available at https://sites.google.com/view/ fabric-smoothing.

Recent advances in unmanned aerial vehicle (UAV) technology have revolutionized a broad class of civil and military applications. However, the designs of wireless technologies that enable real-time streaming of high-definition video between UAVs and ground clients present a conundrum. Most existing adaptive bitrate (ABR) algorithms are not optimized for the air-to-ground links, which usually fluctuate dramatically due to the dynamic flight states of the UAV. In this paper, we present SA-ABR, a new sensor-augmented system that generates ABR video streaming algorithms with the assistance of various kinds of inherent sensor data that are used to pilot UAVs. By incorporating the inherent sensor data with network observations, SA-ABR trains a deep reinforcement learning (DRL) model to extract salient features from the flight state information and automatically learn an ABR algorithm to adapt to the varying UAV channel capacity through the training process. SA-ABR does not rely on any assumptions or models about UAV's flight states or the environment, but instead, it makes decisions by exploiting temporal properties of past throughput through the long short-term memory (LSTM) to adapt itself to a wide range of highly dynamic environments. We have implemented SA-ABR in a commercial UAV and evaluated it in the wild. We compare SA-ABR with a variety of existing state-of-the-art ABR algorithms, and the results show that our system outperforms the best known existing ABR algorithm by 21.4% in terms of the average quality of experience (QoE) reward.

Mixed effects (ME) models inform a vast array of problems in the physical and social sciences, and are pervasive in meta-analysis. We consider ME models where the random effects component is linear. We then develop an efficient approach for a broad problem class that allows nonlinear measurements, priors, and constraints, and finds robust estimates in all of these cases using trimming in the associated marginal likelihood. We illustrate the efficacy of the approach on a range of applications for meta-analysis of global health data. Constraints and priors are used to impose monotonicity, convexity and other characteristics on dose-response relationships, while nonlinear observations enable new epidemiological analyses in place of approximations. Robust extensions ensure that spurious studies do not drive our understanding of between-study heterogeneity. The software accompanying this paper is disseminated as an open-source Python package called limeTR.

While it provides a good foundation to system modeling, analysis, and an understanding of the real world, its application to algorithm design suffers from computational intractability. In this work, we develop a new framework of uncertainty variables to model uncertainty. A simple uncertainty variable is characterized by an uncertainty set, in which its realization is bound to lie, while the conditional uncertainty is characterized by a set map, from a given realization of a variable to a set of possible realizations of another variable. We prove Bayes' law and the law of total probability equivalents for uncertainty variables. We define a notion of independence, conditional independence, and pairwise independence for a collection of uncertainty variables, and show that this new notion of independence preserves the properties of independence defined over random variables. We then develop a graphical model, namely Bayesian uncertainty network, a Bayesian network equivalent defined over a collection of uncertainty variables, and show that all the natural conditional independence properties, expected out of a Bayesian network, hold for the Bayesian uncertainty network. We also define the notion of point estimate, and show its relation with the maximum a posteriori estimate.

Subsampling Generative Adversarial Networks: Density Ratio Estimation in Feature Space with Softplus Loss Xin Ding 1 1 University of British Columbia September 25, 2019 Abstract Filtering out unrealistic images from trained generative adversarial networks (GANs) starts attracting people's attention recently. Two density ratio based subsampling methods--Discriminator Rejection Sampling (DRS) and Metropolis-Hastings GAN (MH-GAN)--are recently proposed, and their effectiveness in improving GANs are demonstrated on multiple datasets. However, DRS and MH-GAN are developed based on discriminator based density ratio estimation (DRE) methods so they may not work well if the discriminator in the trained GAN is far away from its optimality. Moreover, they do not apply to some GANs (e.g., MMD-GAN). In this paper, we propose a novel Softplus (SP) loss for DRE based on which we develop a sample-based DRE method in a feature space learned by a specially designed and pre-trained ResNet-34 (DRE-F-SP). We derive the rate of convergence of a density ratio model trained under the SP loss. Then, we introduce three different density ratio based subsampling methods (DRE-F-SP RS, DRE-F-SP MH, and DRE-F-SP SIR) for GANs based on DRE-F-SP. Our subsampling methods do not rely on the optimality of the discriminator and are suitable for all types of GANs. We empirically show our subsampling approach can substantially outperform DRS and MH-GAN on a synthetic dataset and the CIF AR-10 dataset, using multiple GANs. 1 Introduction Generative adversarial networks (GANs) first introduced by [1] are well-known and powerful generative models for image synthesis and have been applied to various types of image-related tasks [2, 3, 4, 5, 6, 7]. The vanilla GANs proposed by [1] consist of two neural networks: a generator and a discriminator. The generator is trained to generate fake images to fool the discriminator while the discriminator is trained to distinguish fake images from real ones. To enhance the quality of fake images generated from the vanilla GANs, many subsequent works have been done on improving the training procedure of GANs, such as adopting large scale training schemes (e.g., BigGAN [8]), novel normalization methods (e.g., SN-GAN [9]), advanced GAN architectures (e.g., SAGAN [10]), and different loss functions (e.g., WGAN [11, 12] and MMD-GAN [13]). Instead of improving the training procedure, we are more interested in post-processing fake images from a trained GAN (i.e., subsampling fake images to filter out unrealistic images).