Extracting information about entities remains an important research area. This paper addresses the problem of corpus-level entity typing, i.e., inferring from a large corpus that an entity is a member of a class, such as "food" or "artist". The application of entity typing we are interested in is knowledge base completion, specifically, to learn which classes an entity is a member of. We propose FIGMENT to tackle this problem. FIGMENT is embedding-based and combines (i) a global model that computes scores based on global information of an entity and (ii) a context model that first evaluates the individual occurrences of an entity and then aggregates the scores. Each of the two proposed models has specific properties. For the global model, learning high-quality entity representations is crucial because it is the only source used for the predictions. Therefore, we introduce representations using the name and contexts of entities on the three levels of entity, word, and character. We show that each level provides complementary information and a multi-level representation performs best. For the context model, we need to use distant supervision since there are no context-level labels available for entities. Distantly supervised labels are noisy and this harms the performance of models. Therefore, we introduce and apply new algorithms for noise mitigation using multi-instance learning. We show the effectiveness of our models on a large entity typing dataset built from Freebase.

Ensembles are popular methods for solving practical supervised learning problems. They reduce the risk of having underperforming models in production-grade software. Although critical, methods for learning heterogeneous regression ensembles have not been proposed at large scale, whereas in classical ML literature, stacking, cascading and voting are mostly restricted to classification problems. Regression poses distinct learning challenges that may result in poor performance, even when using well established homogeneous ensemble schemas such as bagging or boosting. In this paper, we introduce MetaBags, a novel, practically useful stacking framework for regression. MetaBags is a meta-learning algorithm that learns a set of meta-decision trees designed to select one base model (i.e. expert) for each query, and focuses on inductive bias reduction. A set of meta-decision trees are learned using different types of meta-features, specially created for this purpose - to then be bagged at meta-level. This procedure is designed to learn a model with a fair bias-variance trade-off, and its improvement over base model performance is correlated with the prediction diversity of different experts on specific input space subregions. The proposed method and meta-features are designed in such a way that they enable good predictive performance even in subregions of space which are not adequately represented in the available training data. An exhaustive empirical testing of the method was performed, evaluating both generalization error and scalability of the approach on synthetic, open and real-world application datasets. The obtained results show that our method significantly outperforms existing state-of-the-art approaches.

With the increasing demand for large amount of labeled data, crowdsourcing has been used in many large-scale data mining applications. However, most existing works in crowdsourcing mainly focus on label inference and incentive design. In this paper, we address a different problem of adaptive crowd teaching, which is a sub-area of machine teaching in the context of crowdsourcing. Compared with machines, human beings are extremely good at learning a specific target concept (e.g., classifying the images into given categories) and they can also easily transfer the learned concepts into similar learning tasks. Therefore, a more effective way of utilizing crowdsourcing is by supervising the crowd to label in the form of teaching. In order to perform the teaching and expertise estimation simultaneously, we propose an adaptive teaching framework named JEDI to construct the personalized optimal teaching set for the crowdsourcing workers. In JEDI teaching, the teacher assumes that each learner has an exponentially decayed memory. Furthermore, it ensures comprehensiveness in the learning process by carefully balancing teaching diversity and learner's accurate learning in terms of teaching usefulness.

Navigating through unstructured environments is a basic capability of intelligent creatures, and thus is of fundamental interest in the study and development of artificial intelligence. Long-range navigation is a complex cognitive task that relies on developing an internal representation of space, grounded by recognisable landmarks and robust visual processing, that can simultaneously support continuous self-localisation ("I am here") and a representation of the goal ("I am going there"). Building upon recent research that applies deep reinforcement learning to maze navigation problems, we present an end-to-end deep reinforcement learning approach that can be applied on a city scale. Recognising that successful navigation relies on integration of general policies with locale-specific knowledge, we propose a dual pathway architecture that allows locale-specific features to be encapsulated, while still enabling transfer to multiple cities. We present an interactive navigation environment that uses Google StreetView for its photographic content and worldwide coverage, and demonstrate that our learning method allows agents to learn to navigate multiple cities and to traverse to target destinations that may be kilometres away. A video summarizing our research and showing the trained agent in diverse city environments as well as on the transfer task is available at: https://sites.google.com/view/streetlearn.

PYONGYANG – North Korea has recently started to introduce state-of-the-art technology for the training of future schoolteachers in a possible world first. At the newly remodeled Pyongyang Teacher Training College, the mostly female students study how to educate kindergartners and primary school children with the aid of virtual reality and 3D display technologies. A group of Kyodo News reporters was granted rare access to the college late last week. In one classroom is installed a large widescreen monitor on which are displayed animated avatars representing primary school pupils. Speaking to the virtual children through a microphone, they respond in a timely manner.

This complete guide will teach you how to build and deploy Machine Learning models on your mobile device with TensorFlow Lite. You will understand the core architecture of TensorFlow Lite and the inbuilt models that have been optimized for mobiles. You will learn to implement smart data-intensive behavior, fast, predictive algorithms, and efficient networking capabilities with TensorFlow Lite. You will master the TensorFlow Lite Converter, which converts models to the TensorFlow Lite file format. This course will teach you how to solve real-life problems related to Artificial Intelligence--such as image, text, and voice recognition--by developing models in TensorFlow to make your applications really smart.

Implementing fully connected nets, convnets, RNNs, backprop and SGD from scratch (using pure python, numpy, or even JS) and training these models on small datasets is a great way to learn how neural nets work. Invest time to gain valuable intuition before jumping onto frameworks. This elicited a series of response tweets from François Chollet (@fchollet), creator of Keras, which, when considered collectively, presents a different point of view. Grad students knew how to implement neural nets in C in 2000. And they didn't have good intuition about them.

Data analysis is a process for inspecting, consolidating, transforming, and making sense of data in a way that guides the decision-making process. If you're interested to know the statistical data analysis techniques and implement them using the popular Java APIs and libraries, then go for this Learning Path. Packt's Video Learning Paths are a series of individual video products put together in a logical and stepwise manner such that each video builds on the skills learned in the video before it. Let's take a quick look at your learning journey. This Learning Path starts by showing you the various techniques of pre-processing your data.

Machine Learning is one of the most transformative and impactful technologies of our time. From advertising to healthcare, to self-driving cars, it is hard to find an industry that has not been or is not being revolutionized by machine learning. Using the two most popular frameworks, Tensor Flow and Scikit-Learn, this course will show you insightful tools and techniques for building intelligent systems. Using Scikit-learn you will create a Machine Learning project from scratch, and, use the Tensor Flow library to build and train professional neural networks. We will use these frameworks to build a variety of applications for problems such as ad ranking and sentiment classification.

Do your non-player characters lack drive and ambition? Are they slow, stupid and constantly banging their heads against the wall? Then this course is for you. Join Penny as she explains, demonstrates and assists you to create your very own NPCs in Unity with C#. All you need is a sound knowledge of Unity, C# and the ability to add two numbers together.