Learning near-optimal behaviour from an expert's demonstrations typically relies on the assumption that the learner knows the features that the true reward function depends on. In this paper, we study the problem of learning from demonstrations in the setting where this is not the case, i.e., where there is a mismatch between the worldviews of the learner and the expert. We introduce a natural quantity, the teaching risk, which measures the potential suboptimality of policies that look optimal to the learner in this setting. We show that bounds on the teaching risk guarantee that the learner is able to find a near-optimal policy using standard algorithms based on inverse reinforcement learning. Based on these findings, we suggest a teaching scheme in which the expert can decrease the teaching risk by updating the learner's worldview, and thus ultimately enable her to find a near-optimal policy.

A dialogue act (DA) represents the meaning of an utterance at the illocutionary force level (Austin 1962) such as questions, requests, and greetings. Since DAs take charge of the most fundamental part of communication, we believe that the elucidation of DA learning mechanism is important for cognitive science and artificial intelligence. The purpose of this study is to verify that scaffolding takes place when a human teaches a robot, and to let a robot learn to estimate DAs and to make a response based on them step by step utilizing scaffolding provided by a human. To realize that, it is necessary for the robot to detect changes in utterance and rewards given by the partner and continue learning accordingly. Experimental results demonstrated that participants who continued interaction for a sufficiently long time often gave scaffolding for the robot. Although the number of experiments is still insufficient to obtain a definite conclusion, we observed that 1) the robot quickly learned to respond to DAs in most cases if the participants only spoke utterances that match the situation, 2) in the case of participants who builds scaffolding differently from what we assumed, learning did not proceed quickly, and 3) the robot could learn to estimate DAs almost exactly if the participants kept interaction for a sufficiently long time even if the scaffolding was unexpected.

We introduce PreCo, a large-scale English dataset for coreference resolution. The dataset is designed to embody the core challenges in coreference, such as entity representation, by alleviating the challenge of low overlap between training and test sets and enabling separated analysis of mention detection and mention clustering. To strengthen the training-test overlap, we collect a large corpus of about 38K documents and 12.4M words which are mostly from the vocabulary of English-speaking preschoolers. Experiments show that with higher training-test overlap, error analysis on PreCo is more efficient than the one on OntoNotes, a popular existing dataset. Furthermore, we annotate singleton mentions making it possible for the first time to quantify the influence that a mention detector makes on coreference resolution performance. The dataset is freely available at https://preschool-lab.github.

Inspired by the beauty and flying ability of birds, Leonardo da Vinci strived centuries ago to create a human-powered flapping-wing flying machine. But his designs, which da Vinci explored in his Codex on the Flight of Birds, were never developed in any practical way. Even today, mimicking bird flight still presents challenges due to the physiological complexity of a bird's flapping wings. For years, researchers at the University of Maryland's A. James Clark School of Engineering have been moving ever closer to faithfully imitating bird flight with Robo Raven, the first bird-inspired unmanned aerial vehicle (UAV) that has successfully flown with independent wing control. Robo Raven can also be programmed to perform any desired motion, enabling the UAV to perform aerobatic maneuvers.

Welcome to the Fun and Easy Machine learning Course in Python and Keras. Are you Intrigued by the field of Machine Learning? Then this course is for you! We will take you on an adventure into the amazing of field Machine Learning. Each section consists of fun and intriguing white board explanations with regards to important concepts in Machine learning as well as practical python labs which you will enhance your comprehension of this vast yet lucrative sub-field of Data Science.

Artificial Intelligence tools are rapidly changing how financial institutions operate, manage data, and interact with customers. The revolution brought by the AI – a blend of three advanced technologies: machine learning, natural language processing and cognitive computing – has huge implications for the financial services industry in Nigeria. According to Microsoft Nigeria Country Manager, Mr Akin Banuso, with the use of modern tools like Microsoft's Azure Machine Learning platform, Financial Service Providers can crunch large volumes of data faster and more accurately, which considerably lessens time-to-market to deliver products and services. "The AI has the potential to advance nearly every field of human endeavour and address countless societal challenges. This is why we are investing in not only making the technology more accessible, but also building capacity in the use of machine learning concepts to address analytical gaps in financial inclusion and other areas," Banuso says.

One of my favorite places to learn data science is an under-the-radar educational website, DataCamp. DataCamp doesn't get nearly the attention that some of the larger, more well-funded online coding schools get, but, I often find myself on one of their tutorials whenever I'm learning something new related to statistics or machine learning. Over the past few months, I've dedicated at least a few hours a week to learning the underpinnings of automation and, where I find something interesting, to blog about my experience. Unlike almost every other school or tutorial I've encountered, DataCamp has a delightfully distinct and powerful approach to education: every single piece of instruction is paired with a simple example and interactive tutorial. There are no long lectures; there are no complicated diagrams.

We study convergence properties of Stochastic Gradient Descent (SGD) for convex objectives without assumptions on smoothness or strict convexity. We consider the question of establishing that with high probability the objective evaluated at the candidate minimizer returned by SGD is close to the minimal value of the objective. We compare this result concerning the final candidate minimzer (i.e. the final model parameters learned after all gradient steps) to the online learning techniques of [Zin03] that take a rolling average of the model parameters at the different steps of SGD.

Tuning machine learning models, particularly deep learning architectures, is a complex process. Automated hyperparameter tuning algorithms often depend on specific optimization metrics. However, in many situations, a developer trades one metric against another: accuracy versus overfitting, precision versus recall, smaller models and accuracy, etc. With deep learning, not only are the model's representations opaque, the model's behavior when parameters "knobs" are changed may also be unpredictable. Thus, picking the "best" model often requires time-consuming model comparison. In this work, we introduce LAMVI-2, a visual analytics system to support a developer in comparing hyperparameter settings and outcomes. By focusing on word-embedding models ("deep learning for text") we integrate views to compare both high-level statistics as well as internal model behaviors (e.g., comparing word 'distances'). We demonstrate how developers can work with LAMVI-2 to more quickly and accurately narrow down an appropriate and effective application-specific model.

One of the common tasks in unsupervised learning is dimensionality reduction, where the goal is to find meaningful low-dimensional structures hidden in high-dimensional data. Sometimes referred to as manifold learning, this problem is closely related to the problem of localization, which aims at embedding a weighted graph into a low-dimensional Euclidean space. Several methods have been proposed for localization, and also manifold learning. Nonetheless, the robustness property of most of them is little understood. In this paper, we obtain perturbation bounds for classical scaling and trilateration, which are then applied to derive performance bounds for Isomap, Landmark Isomap, and Maximum Variance Unfolding. A new perturbation bound for procrustes analysis plays a key role.