The simplified series is obtained by first applying their univariate technique to each of the variables independently; that is, each univariate batch of data is separated into variable-length subsequences, and the obtained subsequences are then clustered as explained in Section 4.1. With this process, a set of representative univariate subsequences is obtained for each variable. Each new multivariate batch of data is then represented by a vector of distances, (d 1,d 2,...,d l), where d j represents the Euclidean distance between the j th variable-length subsequence of the new batch and its corresponding representative subsequence. As with their univariate technique, the reference of normality that is considered by this method is the same time series. The technique proposed by Hu et al. [2019] is also based on reducing the dimensionality of the time series and allows us to detect variable-length discords, while using the same time series as the reference of normality. This is based on the fact that the most unusual subsequences tend to have local regions with significantly different densities (points that are similar) in comparison to the other subsequences in the series. Each point in the new univariate time series describes the density of a local region of the input multivariate time series obtained by a sliding window. This series is also used to obtain the variable-length subsequences. Discords are identified using the Euclidean and Bhattacharyya distances simultaneously.

Existing uncertainty modeling approaches try to detect an out-of-distribution point from the in-distribution dataset. We extend this argument to detect finer-grained uncertainty that distinguishes between (a). certain points, (b). uncertain points but within the data distribution, and (c). out-of-distribution points. Our method corrects overconfident NN decisions, detects outlier points and learns to say ``I don't know'' when uncertain about a critical point between the top two predictions. In addition, we provide a mechanism to quantify class distributions overlap in the decision manifold and investigate its implications in model interpretability. Our method is two-step: in the first step, the proposed method builds a class distribution using Kernel Activation Vectors (kav) extracted from the Network. In the second step, the algorithm determines the confidence of a test point by a hierarchical decision rule based on the chi-squared distribution of squared Mahalanobis distances. Our method sits on top of a given Neural Network, requires a single scan of training data to estimate class distribution statistics, and is highly scalable to deep networks and wider pre-softmax layer. As a positive side effect, our method helps to prevent adversarial attacks without requiring any additional training. It is directly achieved when the Softmax layer is substituted by our robust uncertainty layer at the evaluation phase.

We present ConvLab-2, an open-source toolkit that enables researchers to build task-oriented dialogue systems with state-of-the-art models, perform an end-to-end evaluation, and diagnose the weakness of systems. As the successor of ConvLab (Lee et al., 2019b), ConvLab-2 inherits ConvLab's framework but integrates more powerful dialogue models and supports more datasets. Besides, we have developed an analysis tool and an interactive tool to assist researchers in diagnosing dialogue systems. The analysis tool presents rich statistics and summarizes common mistakes from simulated dialogues, which facilitates error analysis and system improvement. The interactive tool provides a user interface that allows developers to diagnose an assembled dialogue system by interacting with the system and modifying the output of each system component.

Due to world dynamics and hardware uncertainty, robots inevitably fail in task executions, leading to undesired or even dangerous executions. To avoid failures for improved robot performance, it is critical to identify and correct robot abnormal executions in an early stage. However, limited by reasoning capability and knowledge level, it is challenging for a robot to self diagnose and correct their abnormal behaviors. To solve this problem, a novel method is proposed, human-to-robot attention transfer (H2R-AT) to seek help from a human. H2R-AT is developed based on a novel stacked neural networks model, transferring human attention embedded in verbal reminders to robot attention embedded in robot visual perceiving. With the attention transfer from a human, a robot understands what and where human concerns are to identify and correct its abnormal executions. To validate the effectiveness of H2R-AT, two representative task scenarios, "serve water for a human in a kitchen" and "pick up a defective gear in a factory" with abnormal robot executions, were designed in an open-access simulation platform V-REP; $252$ volunteers were recruited to provide about 12000 verbal reminders to learn and test the attention transfer model H2R-AT. With an accuracy of $73.68\%$ in transferring attention and accuracy of $66.86\%$ in avoiding robot execution failures, the effectiveness of H2R-AT was validated.

Aside from the immature design of many AI applications, another ethical pitfall presents itself in the way we are using these applications. We are designing AI for tasks that could (and should) be done by humans and neglecting to use AI where it is urgently needed -- namely, in repairing our online ecosystem. It is human nature to have opinions. Many of pride ourselves on the fact-based nature of our opinions -- whether they be based on news stories, personal experience, a book we read recently, etc. However, even the strongest opinions are subject to bias, and it is becoming easier than ever to bias our opinions through social media.

Deloitte Global predicts that the industry for smart speakers--internet-connected speakers with integrated digital voice assistants--will be worth US$7 billion in 2019, selling 164 million units at an average selling price of US$43.1 We expect 2018 sales of 98 million units at an average of US$44 each, for a total industry revenue of US$4.3 billion. This 63 percent growth rate would make smart speakers the fastest-growing connected device category worldwide in 2019, and lead to an installed base of more than 250 million units by year-end.2 Robust sales performance in 2019, although high, will represent a deceleration from the prior year: In Q2 of 2018, smart speaker sales were up 187 percent year over year.3 Smart speakers have, literally, a world of opportunity for growth. Much of that opportunity comes from expansion into non-English-speaking countries.

Recently, I've curated a list of 50 Finnish startups in the field of AI & Machine Learning for those who are looking for business partners or companies to invest in. If you are an international investor who wants to connect with one of the startups, feel free to drop me a message. I can make the intro and provide the companies' investor pitch deck to you if it is available. You can also use Finder.fi to check the company's revenue development. If you are an ambitious entrepreneur (based in Finland) who is working on the next world-changing idea and is looking for funding, let's meet! I'll be happy to discuss how we can help you with the fundraising process (for free). Most of the following information is from the company website. But if you've spotted an error, please let me know and I will revise accordingly. "AISpotter has developed a time-saving, fast service for coaches all around the world. Our goal is to combine high-end technology and sports of any kind. With real-time analysis, coaches and teams are given the power to be one step ahead in team development." "We've taken over 30 years of recognized University of Oulu Machine Vision Group technology and adapted it to improve your sports game. By combining state-of-the-art machine learning and computer vision in our unique way, we provide automatic and fast analysis service for your game."

Call takers of the Victorian triple zero (000) hotline will soon be making life-saving decisions using a revolutionary artificial intelligence (AI) technology that will fast-track urgent care to people suffering cardiac arrests. According to a recent press release, Minister for Health Jenny Mikakos has announced that Ambulance Victoria would receive AU$ 1.71 million from the Victorian Government's Safer Care Victoria Innovation Fund for two ground-breaking new projects. She explained that they are always looking for new, cutting edge ways to innovate and deliver the very best and safest care. All Victorians deserve access to world-class treatment when they need it most, no matter where they live. The first project is the Artificial Intelligence in Cardiac Arrest project, which will receive $1.36 million. It will help ESTA triple zero operators identify signs of cardiac arrest over the phone, which will save an additional 185 lives each year.

Australia's Monash University has secured AU$ 4.3 million from the Australian Research Data Commons (ARDC) to lead four major data and cloud infrastructure science projects. These projects will reportedly advance the artificial intelligence (AI), data science and research technology capabilities at the university. All of the projects focus on building scalable data environments for data-centric research, sensitive data and strengthening the use of AI techniques, such as machine learning (ML). The University will work in partnership with other leading research organisations and universities to deliver these projects. Doing so will harness the combined resources and knowledge to achieve improved high-performance data environments for researchers.

We study the problem of community detection in multi-layer networks, where pairs of nodes can be related in multiple modalities. We introduce a general framework, i.e., mixture multi-layer stochastic block model (MMSBM), which includes many earlier models as special cases. We propose a tensor-based algorithm (TWIST) to reveal both global/local memberships of nodes, and memberships of layers. We show that the TWIST procedure can accurately detect the communities with small misclassification error as the number of nodes and/or the number of layers increases. Numerical studies confirm our theoretical findings. To our best knowledge, this is the first systematic study on the mixture multi-layer networks using tensor decomposition. The method is applied to two real datasets: worldwide trading networks and malaria parasite genes networks, yielding new and interesting findings.