Creating bilingual dictionary is the first crucial step in enriching low-resource languages. Especially for the closely-related ones, it has been shown that the constraint-based approach is useful for inducing bilingual lexicons from two bilingual dictionaries via the pivot language. However, if there are no available machine-readable dictionaries as input, we need to consider manual creation by bilingual native speakers. To reach a goal of comprehensively create multiple bilingual dictionaries, even if we already have several existing machine-readable bilingual dictionaries, it is still difficult to determine the execution order of the constraint-based approach to reducing the total cost. Plan optimization is crucial in composing the order of bilingual dictionaries creation with the consideration of the methods and their costs. We formalize the plan optimization for creating bilingual dictionaries by utilizing Markov Decision Process (MDP) with the goal to get a more accurate estimation of the most feasible optimal plan with the least total cost before fully implementing the constraint-based bilingual lexicon induction. We model a prior beta distribution of bilingual lexicon induction precision with language similarity and polysemy of the topology as $\alpha$ and $\beta$ parameters. It is further used to model cost function and state transition probability. We estimated the cost of all investment plan as a baseline for evaluating the proposed MDP-based approach with total cost as an evaluation metric. After utilizing the posterior beta distribution in the first batch of experiments to construct the prior beta distribution in the second batch of experiments, the result shows 61.5\% of cost reduction compared to the estimated all investment plan and 39.4\% of cost reduction compared to the estimated MDP optimal plan. The MDP-based proposal outperformed the baseline on the total cost.

In this thesis, I explore the possibilities of conducting Bayesian optimization techniques in high dimensional domains. Although high dimensional domains can be defined to be between hundreds and thousands of dimensions, we will primarily focus on problem settings that occur between two and 20 dimensions. As such, we focus on solutions to practical problems, such as tuning the parameters for an electron accelerator, or for even simpler tasks that can be run and optimized just in time with a standard laptop at hand. Our main contributions are 1.) comparing how the log-likelihood affects the angle-difference in the real projection matrix, and the found matrix matrix, 2.) an extensive analysis of current popular methods including strengths and shortcomings, 3.) a short analysis on how dimensionality reduction techniques can be used for feature selection, and 4.) a novel algorithm called "BORING", which allows for a simple fallback mechanism if the matrix identification fails, as well as taking into consideration "passive" subspaces which provide small perturbations of the function at hand. The main features of BORING are 1.) the possibility to identify the subspace (unlike most other optimization algorithms), and 2.) to provide a much lower penalty to identify the subspace if identification fails, as optimization is still the primary goal.

Fast machine learning-based surrogate models are trained to emulate slow, high-fidelity engineering simulation models to accelerate engineering design tasks. This introduces uncertainty as the surrogate is only an approximation of the original model. Bayesian methods can quantify that uncertainty, and deep learning models exist that follow the Bayesian paradigm. These models, namely Bayesian neural networks and Gaussian process models, enable us to give predictions together with an estimate of the model's uncertainty. As a result we can derive uncertainty-aware surrogate models that can automatically suspect unseen design samples that cause large emulation errors. For these samples, the high-fidelity model can be queried instead. This outlines how the Bayesian paradigm allows us to hybridize fast, but approximate, and slow, but accurate models. In this paper, we train two types of Bayesian models, dropout neural networks and stochastic variational Gaussian Process models, to emulate a complex high dimensional building energy performance simulation problem. The surrogate model processes 35 building design parameters (inputs) to estimate 12 different performance metrics (outputs). We benchmark both approaches, prove their accuracy to be competitive, and show that errors can be reduced by up to 30% when the 10% of samples with the highest uncertainty are transferred to the high-fidelity model.

Recurrent neural networks (RNNs) with rich feature vectors of past values can provide accurate point forecasts for series that exhibit complex serial dependence. We propose two approaches to constructing deep time series probabilistic models based on a variant of RNN called an echo state network (ESN). The first is where the output layer of the ESN has stochastic disturbances and a shrinkage prior for additional regularization. The second approach employs the implicit copula of an ESN with Gaussian disturbances, which is a deep copula process on the feature space. Combining this copula with a non-parametrically estimated marginal distribution produces a deep distributional time series model. The resulting probabilistic forecasts are deep functions of the feature vector and also marginally calibrated. In both approaches, Bayesian Markov chain Monte Carlo methods are used to estimate the models and compute forecasts. The proposed deep time series models are suitable for the complex task of forecasting intraday electricity prices. Using data from the Australian National Electricity Market, we show that our models provide accurate probabilistic price forecasts. Moreover, the models provide a flexible framework for incorporating probabilistic forecasts of electricity demand as additional features. We demonstrate that doing so in the deep distributional time series model in particular, increases price forecast accuracy substantially.

The TriRhenaTech alliance presents a collection of accepted papers of the cancelled tri-national 'Upper-Rhine Artificial Inteeligence Symposium' planned for 13th May 2020 in Karlsruhe. The TriRhenaTech alliance is a network of universities in the Upper-Rhine Trinational Metropolitan Region comprising of the German universities of applied sciences in Furtwangen, Kaiserslautern, Karlsruhe, and Offenburg, the Baden-Wuerttemberg Cooperative State University Loerrach, the French university network Alsace Tech (comprised of 14 'grandes \'ecoles' in the fields of engineering, architecture and management) and the University of Applied Sciences and Arts Northwestern Switzerland. The alliance's common goal is to reinforce the transfer of knowledge, research, and technology, as well as the cross-border mobility of students.

As one kind of architecture from the deep learning family, deep semantic segmentation network (DSSN) achieves a certain degree of success on the semantic segmentation task and obviously outperforms the traditional methods based on hand-crafted features. As a classic data-driven technique, DSSN can be trained by an end-to-end mechanism and competent for employing the low-level and mid-level cues (i.e., the discriminative image structure) to understand images, but lacks the high-level inference ability. By contrast, human beings have an excellent inference capacity and can be able to reliably interpret the RS imagery only when human beings master the basic RS domain knowledge. In literature, ontological modeling and reasoning is an ideal way to imitate and employ the domain knowledge of human beings, but is still rarely explored and adopted in the RS domain. To remedy the aforementioned critical limitation of DSSN, this paper proposes a collaboratively boosting framework (CBF) to combine data-driven deep learning module and knowledge-guided ontological reasoning module in an iterative way.

We deal with the problem of generating textual captions from optical remote sensing (RS) images using the notion of deep reinforcement learning. Due to the high inter-class similarity in reference sentences describing remote sensing data, jointly encoding the sentences and images encourages prediction of captions that are semantically more precise than the ground truth in many cases. To this end, we introduce an Actor Dual-Critic training strategy where a second critic model is deployed in the form of an encoder-decoder RNN to encode the latent information corresponding to the original and generated captions. While all actor-critic methods use an actor to predict sentences for an image and a critic to provide rewards, our proposed encoder-decoder RNN guarantees high-level comprehension of images by sentence-to-image translation. We observe that the proposed model generates sentences on the test data highly similar to the ground truth and is successful in generating even better captions in many critical cases. Extensive experiments on the benchmark Remote Sensing Image Captioning Dataset (RSICD) and the UCM-captions dataset confirm the superiority of the proposed approach in comparison to the previous state-of-the-art where we obtain a gain of sharp increments in both the ROUGE-L and CIDEr measures.

So you're interested in AI? Then join our online event, TNW2020, where you'll hear how artificial intelligence is transforming industries and businesses. The Game of Life is a grid-based automaton that is very popular in discussions about science, computation, and artificial intelligence. It is an interesting idea that shows how very simple rules can yield very complicated results. Despite its simplicity, however, the Game of Life remains a challenge to artificial neural networks, AI researchers at Swarthmore College and the Los Alamos National Laboratory have shown in a recent paper. Titled, "It's Hard for Neural Networks To Learn the Game of Life," their research investigates how neural networks explore the Game of Life and why they often miss finding the right solution.

The graph represents a network of 1,076 Twitter users whose tweets in the requested range contained "iiot machinelearning", or who were replied to or mentioned in those tweets. The network was obtained from the NodeXL Graph Server on Friday, 02 October 2020 at 10:43 UTC. The requested start date was Friday, 02 October 2020 at 00:01 UTC and the maximum number of tweets (going backward in time) was 7,500. The tweets in the network were tweeted over the 2-day, 9-hour, 4-minute period from Tuesday, 29 September 2020 at 14:35 UTC to Thursday, 01 October 2020 at 23:40 UTC. Additional tweets that were mentioned in this data set were also collected from prior time periods.

Fifty million artificial neurons--a number roughly equivalent to the brain of a small mammal--were delivered from Portland, Oregon-based Intel Corp. to Sandia National Laboratories last month, said Sandia project leader Craig Vineyard. The neurons will be assembled to advance a relatively new kind of computing, called neuromorphic, based on the principles of the human brain. Its artificial components pass information in a manner similar to the action of living neurons, electrically pulsing only when a synapse in a complex circuit has absorbed enough charge to produce an electrical spike. "With a neuromorphic computer of this scale," Vineyard said, "we have a new tool to understand how brain-based computers are able to do impressive feats that we cannot currently do with ordinary computers." Improved algorithms and computer circuitry can create wider applications for neuromorphic computers, said Vineyard. Sandia manager of cognitive and emerging computing John Wagner said, "This very large neural computer will let us test how brain-inspired processors use information at increasingly realistic scales as they come to actually approximate the processing power of brains.