Soil texture is important for many environmental processes. In this paper, we study the classification of soil texture based on hyperspectral data. We develop and implement three 1-dimensional (1D) convolutional neural networks (CNN): the LucasCNN, the LucasResNet which contains an identity block as residual network, and the LucasCoordConv with an additional coordinates layer. Furthermore, we modify two existing 1D CNN approaches for the presented classification task. The code of all five CNN approaches is available on GitHub (Riese, 2019). We evaluate the performance of the CNN approaches and compare them to a random forest classifier. Thereby, we rely on the freely available LUCAS topsoil dataset. The CNN approach with the least depth turns out to be the best performing classifier. The LucasCoordConv achieves the best performance regarding the average accuracy. In future work, we can further enhance the introduced LucasCNN, LucasResNet and LucasCoordConv and include additional variables of the rich LUCAS dataset.

Machine learning systems regularly deal with structured data in real-world applications. Unfortunately, such data has been difficult to faithfully represent in a way that most machine learning techniques would expect, i.e. as a real-valued vector of a fixed, pre-specified size. In this work, we introduce a novel approach that compiles structured data into a satisfiability problem which has in its set of solutions at least (and often only) the input data. The satisfiability problem is constructed from constraints which are generated automatically a priori from a given signature, thus trivially allowing for a bag-of-words-esque vector representation of the input to be constructed. The method is demonstrated in two areas, automated reasoning and natural language processing, where it is shown to produce vector representations of natural-language sentences and first-order logic clauses that can be precisely translated back to their original, structured input forms.

One desired aspect of microservices architecture is the ability to self-adapt its own architecture and behaviour in response to changes in the operational environment. To achieve the desired high levels of self-adaptability, this research implements the distributed microservices architectures model, as informed by the MAPE-K model. The proposed architecture employs a multi adaptation agents supported by a centralised controller, that can observe the environment and execute a suitable adaptation action. The adaptation planning is managed by a deep recurrent Q-network (DRQN). It is argued that such integration between DRQN and MDP agents in a MAPE-K model offers distributed microservice architecture with self-adaptability and high levels of availability and scalability. Integrating DRQN into the adaptation process improves the effectiveness of the adaptation and reduces any adaptation risks, including resources over-provisioning and thrashing. The performance of DRQN is evaluated against deep Q-learning and policy gradient algorithms including: i) deep q-network (DQN), ii) dulling deep Q-network (DDQN), iii) a policy gradient neural network (PGNN), and iv) deep deterministic policy gradient (DDPG). The DRQN implementation in this paper manages to outperform the above mentioned algorithms in terms of total reward, less adaptation time, lower error rates, plus faster convergence and training times. We strongly believe that DRQN is more suitable for driving the adaptation in distributed services-oriented architecture and offers better performance than other dynamic decision-making algorithms. Index Terms Service oriented architecture, self-adaptive architectures, reinforcement learning, Q-learning algorithms, deep Q-Learning networks, recurrent Q-learning networks, policy approximation, multi agents environment. I. INTRODUCTION Self-adaptability refers to the ability of service oriented architecture (SOA) to modify its own structure and behaviour in response to changes in the operating environment [1]. High levels of self-adaptability present the challenges of self-organising, self-tuning, and self-healing the architecture against an interruption. Moreover, because of the services' pervasiveness, and in order to make any adaptation strategy effective and successful, adaptation actions must be considered in conjunction with So that the performed action meets the adaptation goals, objectives, and the desired architecture quality attributes [2]-[4].

In machine learning, if the training data is an unbiased sample of an underlying distribution, then the learned classification function will make accurate predictions for new samples. However, if the training data is not an unbiased sample, then there will be differences between how the training data is distributed and how the test data is distributed. Standard classifiers cannot cope with changes in data distributions between training and test phases, and will not perform well. Domain adaptation and transfer learning are sub-fields within machine learning that are concerned with accounting for these types of changes. Here, we present an introduction to these fields, guided by the question: when and how can a classifier generalize from a source to a target domain? We will start with a brief introduction into risk minimization, and how transfer learning and domain adaptation expand upon this framework. Following that, we discuss three special cases of data set shift, namely prior, covariate and concept shift. For more complex domain shifts, there are a wide variety of approaches. These are categorized into: importance-weighting, subspace mapping, domain-invariant spaces, feature augmentation, minimax estimators and robust algorithms. A number of points will arise, which we will discuss in the last section. We conclude with the remark that many open questions will have to be addressed before transfer learners and domain-adaptive classifiers become practical.

Artificial Intelligence (AI) is arguably the most revolutionary technology in several decades that would completely turn the world upside down and then shape it along with new contours. AI will reinvent everything from the nature of work to our modes of communication and transportation. The'creative destruction' unleashed by AI would make a large number of current skills and jobs redundant while opening avenues for new skills. The preeminence of AI and its far-reaching influence can be gauged from the fact that the nascent AI rivalry between USA and China has been dubbed as'The New Space Race'. In 2018, increase in AI-based applications, anxiety about a'war of the worlds' esque robotic workforce and China outpacing USA in the number of AI startups and AI related patents were the most highlighted AI trends.

There's a bot for that; Samsung envisions a future where robots will manage key aspects of our daily lives, from health to retail. With smart assistants on the rise, the market for connected living is soaring to new heights. Canalys estimates that the number of smart assistant-compatible devices in US homes will increase by 400% over the next three years, reaching 1.6 billion devices across the country by 2022. Samsung presented their vision for the future of connected living at CES 2019, moving beyond voice assistants with a suite of robots designed "to manage activities of daily living." Following in the steps of Honda's Empower, Experience, Empathy Robotics Concept from last year's CES, Samsung's "companions for the future" are designed to make our lives easier, with human-centric support for everything from health management to personal shopping.

This book is an introductory overview of Ethem's detailed text on ML. The text itself has gotten mostly mixed or bad reviews due to a lot of math and algorithms notated without a lot of detailed explanations, however, this is a general reader intro and doesn't go into math, algos in detail, trees, Bayesian logic or even pseudocode, it is more an up to date overview of the field as it exists at this writing. Alpaydin's expensive text, btw, is also available in a very inexpensive Asian edition here on Amazon if you want to brave that difficult book without a lot of investment (Introduction To Machine Learning 3Rd Edition). The present volume is sortof a "ML for Dummies" only updated for the current craze with big data management. There is a lot of history and background that an experienced ML person will find too basic, but as a High School intro or general interested reader intro it is excellent.

Automatic human affect recognition is a key step towards more natural human-computer interaction. Recent trends include recognition in the wild using a fusion of audiovisual and physiological sensors, a challenging setting for conventional machine learning algorithms. Since 2010, novel deep learning algorithms have been applied increasingly in this field. In this paper, we review the literature on human affect recognition between 2010 and 2017, with a special focus on approaches using deep neural networks. By classifying a total of 950 studies according to their usage of shallow or deep architectures, we are able to show a trend towards deep learning. Reviewing a subset of 233 studies that employ deep neural networks, we comprehensively quantify their applications in this field. We find that deep learning is used for learning of (i) spatial feature representations, (ii) temporal feature representations, and (iii) joint feature representations for multimodal sensor data. Exemplary state-of-the-art architectures illustrate the progress. Our findings show the role deep architectures will play in human affect recognition, and can serve as a reference point for researchers working on related applications.

The rise of the machines is coming. Automation, robotics, machine learning and artificial intelligence (AI) are all being used by many businesses around the world. There has been a logical fear that any or all of these will become job eaters in the future, that millions of people will have to learn new skills to stay employed in the years to come. What if, despite all of these job-killing fears, they actually prove to be jobs-makers? Dun & Bradstreet conducted a survey of attendees at the recent AI World Conference and Expo, and respondents from 40% of the organizations said that their companies actually are adding more jobs as a result of deploying artificial intelligence in their businesses.

FMCG giant Procter & Gamble (P&G) unveiled six new cutting-edge products on Sunday at the Consumer Electronics Show in Las Vegas. The new products and services include an Olay AI skin advisor platform, an Oral-B AI toothbrush and a Heated Razor by GilletteLabs. "We're living in a time of mass disruption, where the exponential power of technology combined with shifting societal and environmental forces are transforming consumer experiences everyday," said P&G chief brand officer Marc Pritchard. "P&G is integrating cutting-edge technologies into everyday products and services to improve people's lives. We're combining what's needed with what's possible. P&G chief research, development and innovation officer, Kathy Fish said the company is "innovating faster than ever, combining more than 180 years of capability with the entrepreneurial spirit of a lean startup". "As consumers are changing, so are we.