Delivering useful hydrological forecasts is critical for urban and agricultural water management, hydropower generation, flood protection and management, drought mitigation and alleviation, and river basin planning and management, among others. In this work, we present and appraise a new methodology for hydrological time series forecasting. This methodology is based on simple combinations. The appraisal is made by using a big dataset consisted of 90-year-long mean annual river flow time series from approximately 600 stations. Covering large parts of North America and Europe, these stations represent various climate and catchment characteristics, and thus can collectively support benchmarking. Five individual forecasting methods and 26 variants of the introduced methodology are applied to each time series. The application is made in one-step ahead forecasting mode. The individual methods are the last-observation benchmark, simple exponential smoothing, complex exponential smoothing, automatic autoregressive fractionally integrated moving average (ARFIMA) and Facebook's Prophet, while the 26 variants are defined by all the possible combinations (per two, three, four or five) of the five afore-mentioned methods. The findings have both practical and theoretical implications. The simple methodology of the study is identified as well-performing in the long run. Our large-scale results are additionally exploited for finding an interpretable relationship between predictive performance and temporal dependence in the river flow time series, and for examining one-year ahead river flow predictability.

Thanks to popular science fiction, almost any person on Earth has some knowledge of AI. For business purposes and utilizing advanced technologies there are deeper reasons to look into Artificial Intelligence. Saving time and money, increasing productivity and revenues, avoiding human factor errors is what you get from AI right off the top of a hat. Hundreds of artificial intelligence companies are already conquering markets. The main purpose of our article is not reviewing pros and cons, rather offering AI development companies which can assist your business strategy for consideration. On one hand, our list does not include big-guns like Amazon, Alexa or Apple, and on the other, we also discarded plenty of startups with questionable reputation. We handpicked only those tech companies who, in our opinion, are able to cope with the most challenging AI projects and have positive customer feedback.

Cyberlaw as a discipline saw some massive advances in 2019. These advances were seen in different thrust areas of this discipline. The first significant element of 2019 was the determined focus of sovereign governments across the world, to come up with strong national cybersecurity legislations and legislative frameworks. Consequently, different countries and sovereign governments started moving in the direction of trying to regulate cybersecurity. These regulations normally took two distinctive manifestations.

Temporal abstraction refers to the ability of an agent to use behaviours of controllers which act for a limited, variable amount of time. The options framework describes such behaviours as consisting of a subset of states in which they can initiate, an internal policy and a stochastic termination condition. However, much of the subsequent work on option discovery has ignored the initiation set, because of difficulty in learning it from data. We provide a generalization of initiation sets suitable for general function approximation, by defining an interest function associated with an option. We derive a gradient-based learning algorithm for interest functions, leading to a new interest-option-critic architecture. We investigate how interest functions can be leveraged to learn interpretable and reusable temporal abstractions. We demonstrate the efficacy of the proposed approach through quantitative and qualitative results, in both discrete and continuous environments.

One of the well-known challenges in computer vision tasks is the visual diversity of images, which could result in an agreement or disagreement between the learned knowledge and the visual content exhibited by the current observation. In this work, we first define such an agreement in a concepts learning process as congruency. Formally, given a particular task and sufficiently large dataset, the congruency issue occurs in the learning process whereby the task-specific semantics in the training data are highly varying. We propose a Direction Concentration Learning (DCL) method to improve congruency in the learning process, where enhancing congruency influences the convergence path to be less circuitous. The experimental results show that the proposed DCL method generalizes to state-of-the-art models and optimizers, as well as improves the performances of saliency prediction task, continual learning task, and classification task. Moreover, it helps mitigate the catastrophic forgetting problem in the continual learning task. The code is publicly available at https://github.com/luoyan407/congruency.

The graph represents a network of 3,290 Twitter users whose tweets in the requested range contained "govtech", or who were replied to or mentioned in those tweets. The network was obtained from the NodeXL Graph Server on Monday, 23 December 2019 at 07:09 UTC. The requested start date was Monday, 23 December 2019 at 01:01 UTC and the maximum number of days (going backward) was 14. The maximum number of tweets collected was 5,000. The tweets in the network were tweeted over the 13-day, 9-hour, 49-minute period from Monday, 09 December 2019 at 01:50 UTC to Sunday, 22 December 2019 at 11:39 UTC.

Gradients of neural networks can be computed efficiently for any architecture, but some applications require differential operators with higher time complexity. We describe a family of restricted neural network architectures that allow efficient computation of a family of differential operators involving dimension-wise derivatives, used in cases such as computing the divergence. Our proposed architecture has a Jacobian matrix composed of diagonal and hollow (non-diagonal) components. We can then modify the backward computation graph to extract dimension-wise derivatives efficiently with automatic differentiation. We demonstrate these cheap differential operators for solving root-finding subproblems in implicit ODE solvers, exact density evaluation for continuous normalizing flows, and evaluating the Fokker-Planck equation for training stochastic differential equation models.

Cascading portfolio scheduling is a static algorithm selection strategy which uses a sample of test instances to compute an optimal ordering (a cascading schedule) of a portfolio of available algorithms. The algorithms are then applied to each future instance according to this cascading schedule, until some algorithm in the schedule succeeds. Cascading algorithm scheduling has proven to be effective in several applications, including QBF solving and the generation of ImageNet classification models. It is known that the computation of an optimal cascading schedule in the offline phase is NP-hard. In this paper we study the parameterized complexity of this problem and establish its fixed-parameter tractability by utilizing structural properties of the success relation between algorithms and test instances. Our findings are significant as they reveal that in spite of the intractability of the problem in its general form, one can indeed exploit sparseness or density of the success relation to obtain non-trivial runtime guarantees for finding an optimal cascading schedule.

Time series with non-uniform intervals occur in many applications, and are difficult to model using standard recurrent neural networks (RNNs). We generalize RNNs to have continuous-time hidden dynamics defined by ordinary differential equations (ODEs), a model we call ODE-RNNs. Furthermore, we use ODE-RNNs to replace the recognition network of the recently-proposed Latent ODE model. Both ODE-RNNs and Latent ODEs can naturally handle arbitrary time gaps between observations, and can explicitly model the probability of observation times using Poisson processes. We show experimentally that these ODE-based models outperform their RNN-based counterparts on irregularly-sampled data.

We propose a stochastic optimization method for minimizing loss functions, which can be expressed as an expected value, that adap-tively controls the batch size used in the computation of gradient approximations and the step size used to move along such directions, eliminating the need for the user to tune the learning rate. The proposed method exploits local curvature information and ensures that search directions are descent directions with high probability using an acute-angle test. The method is proved to have, under reasonable assumptions, a global linear rate of convergence on self-concordant functions with high probability. Numerical experiments show that this method is able to choose the best learning rates and compares favorably to fine-tuned SGD for training logistic regression and Deep Neural Networks (DNNs). We also propose an adaptive version of ADAM that eliminates the need to tune the base learning rate and compares favorably to fine-tuned ADAM for training DNNs.