Robots are well-known for being very good at some very specific things. They're often defined by words like "precision" and "repeatability" and "speed," because if you want a robot to be uniquely useful, it's usually going to have to leverage one or more of those characteristics in a way that makes it better at some specific task than humans are. Robots have been doing this for decades, typically in places like industrial settings, but things are starting to change, and roboticists are beginning to look towards other applications in more unconstrained, dynamic environments, like non-industrial settings. Such environments (our homes, for example) are the kinds of places that we really, really want robots to be useful in. We want them doing our chores so that we don't have to, ideally without causing catastrophic damage or injury at the same time.

Students are expected to be self-motivated, curious and enthusiastic about machine learning on graphs. You'll get the most out of this course by completing the (moderate time commitment) coursework, so make sure you have the free time and energy needed for that. The course will have lectures every two weeks, for four lectures, taking a total of two months to complete. Each two week cycle will begin with an interactive online lecture in a Google Hangout. This will be followed with a piece of coursework, provided as a template Google Colab notebook. A week after the lecture will be a tutorial session, where the students and tutor(s) will get together and discuss the coursework and what challenges students are having.

Working with BIG DATA requires a particular suite of data analytics tools and advanced techniques, such as machine learning (ML). Many of these tools are readily and freely available in R. This full-day session will provide participants with a hands-on training on how to use data analytics tools and machine learning methods available in R to explore, visualize, and model big data. The first half of our training session will focus on organizing (manipulating and summarizing) and visualizing (both statically and dynamically) big data in R. The second half will involve a series of short lectures on ML techniques (decision trees, random forests, and support vector machines), as well as hands-on demonstrations applying these methods in R. Examples will be drawn from the OECD's Programme for International Student Assessment (PISA). Participants will get opportunities to work through several hands-on lab sessions throughout the day.

The short duration of an input utterance is one of the most critical threats that degrade the performance of speaker verification systems. This study aimed to develop an integrated text-independent speaker verification system that inputs utterances with short duration of 2 seconds or less. We propose an approach using a teacher-student learning framework for this goal, applied to short utterance compensation for the first time in our knowledge. The core concept of the proposed system is to conduct the compensation throughout the network that extracts the speaker embedding, mainly in phonetic-level, rather than compensating via a separate system after extracting the speaker embedding. In the proposed architecture, phonetic-level features where each feature represents a segment of 130 ms are extracted using convolutional layers. A layer of gated recurrent units extracts an utterance-level feature using phonetic-level features. The proposed approach also adopts a new objective function for teacher-student learning that considers both Kullback-Leibler divergence of output layers and cosine distance of speaker embeddings layers. Experiments were conducted using deep neural networks that take raw waveforms as input, and output speaker embeddings on VoxCeleb1 dataset. The proposed model could compensate approximately 65 \% of the performance degradation due to the shortened duration.

The quest of `can machines think' and `can machines do what human do' are quests that drive the development of artificial intelligence. Although recent artificial intelligence succeeds in many data intensive applications, it still lacks the ability of learning from limited exemplars and fast generalizing to new tasks. To tackle this problem, one has to turn to machine learning, which supports the scientific study of artificial intelligence. Particularly, a machine learning problem called Few-Shot Learning (FSL) targets at this case. It can rapidly generalize to new tasks of limited supervised experience by turning to prior knowledge, which mimics human's ability to acquire knowledge from few examples through generalization and analogy. It has been seen as a test-bed for real artificial intelligence, a way to reduce laborious data gathering and computationally costly training, and antidote for rare cases learning. With extensive works on FSL emerging, we give a comprehensive survey for it. We first give the formal definition for FSL. Then we point out the core issues of FSL, which turns the problem from "how to solve FSL" to "how to deal with the core issues". Accordingly, existing works from the birth of FSL to the most recent published ones are categorized in a unified taxonomy, with thorough discussion of the pros and cons for different categories. Finally, we envision possible future directions for FSL in terms of problem setup, techniques, applications and theory, hoping to provide insights to both beginners and experienced researchers.

Entry level positions require at least a bachelor's degree while positions entailing supervision, leadership or administrative roles frequently require masters or doctoral degrees. Candidates can find degree programs that offer specific majors in AI or pursue an AI specialisation from within majors such as computer science, health informatics, graphic design, information technology or engineering. AI and machine learning involve software that has been programmed to interact with the world in ways that would otherwise be thought of as human. AI depends on knowledge about the world as well as programs or algorithms to intelligently process that knowledge. Today, most AI programs are specifically coded to do one task.

Domain randomization is a popular technique for improving domain transfer, often used in a zero-shot setting when the target domain is unknown or cannot easily be used for training. In this work, we empirically examine the effects of domain randomization on agent generalization. Our experiments show that domain randomization may lead to suboptimal, high-variance policies, which we attribute to the uniform sampling of environment parameters. We propose Active Domain Randomization, a novel algorithm that learns a parameter sampling strategy. Our method looks for the most informative environment variations within the given randomization ranges by leveraging the discrepancies of policy rollouts in randomized and reference environment instances. We find that training more frequently on these instances leads to better overall agent generalization. In addition, when domain randomization and policy transfer fail, Active Domain Randomization offers more insight into the deficiencies of both the chosen parameter ranges and the learned policy, allowing for more focused debugging. Our experiments across various physics-based simulated and a real-robot task show that this enhancement leads to more robust, consistent policies.

We use a geometric digraph family called class cover catch digraphs (CCCDs) to tackle the class imbalance problem in statistical classification. CCCDs provide graph theoretic solutions to the class cover problem and have been employed in classification. We assess the classification performance of CCCD classifiers by extensive Monte Carlo simulations, comparing them with other classifiers commonly used in the literature. In particular, we show that CCCD classifiers perform relatively well when one class is more frequent than the other in a two-class setting, an example of the class imbalance problem. We also point out the relationship between class imbalance and class overlapping problems, and their influence on the performance of CCCD classifiers and other classification methods as well as some state-of-the-art algorithms which are robust to class imbalance by construction. Experiments on both simulated and real data sets indicate that CCCD classifiers are robust to the class imbalance problem. CCCDs substantially undersample from the majority class while preserving the information on the discarded points during the undersampling process. Many state-of-the-art methods, however, keep this information by means of ensemble classifiers, but CCCDs yield only a single classifier with the same property, making it both appealing and fast.

How is popularity gained online? Is being successful strictly related to rapidly becoming viral in an online platform or is it possible to acquire popularity in a steady and disciplined fashion? What are other temporal characteristics that can unveil the popularity of online content? To answer these questions, we leverage a multi-faceted temporal analysis of the evolution of popular online contents. Here, we present dipm-SC: a multi-dimensional shape-based time-series clustering algorithm with a heuristic to find the optimal number of clusters. First, we validate the accuracy of our algorithm on synthetic datasets generated from benchmark time series models. Second, we show that dipm-SC can uncover meaningful clusters of popularity behaviors in a real-world Twitter dataset. By clustering the multidimensional time-series of the popularity of contents coupled with other domain-specific dimensions, we uncover two main patterns of popularity: bursty and steady temporal behaviors. Moreover, we find that the way popularity is gained over time has no significant impact on the final cumulative popularity.

Unfortunately for our new AI overlords, the crusade to take over the world has been stopped in its tracks by an unlikely hurdle: a 16-year-old's math test. Faced with the same level of exam that a 16-year-old in the U.K. would take, according to a new paper by Google's DeepMind, its cutting-edge AI flunked. The algorithm was trained on the sorts of algebra, calculus, and other types of math questions that would appear on a 16-year-old's math exam according to the U.K. national curriculum, according to DeepMind research published online on Tuesday. The researchers tested several types of AI and found that algorithms struggle to translate a question as it appears on a test, full of words and symbols and functions, into the actual operations needed to solve it, according to an article on Medium. It turns out, according to the research, that even a simple math problem involves a great deal of brainpower, as people learn to automatically learn to make sense of mathematical operations, memorize the order in which to perform them, and know how to turn word problems into equations.