In recent years there has been a cascade of research in attempting to make AI systems more interpretable by providing explanations; so-called Explainable AI (XAI). Most of this research has dealt with the challenges that arise in explaining black-box deep learning systems in classification and regression tasks, with a focus on tabular and image data; for example, there is a rich seam of work on post-hoc counterfactual explanations for a variety of black-box classifiers (e.g., when a user is refused a loan, the counterfactual explanation tells the user about the conditions under which they would get the loan). However, less attention has been paid to the parallel interpretability challenges arising in AI systems dealing with time series data. This paper advances a novel technique, called Native-Guide, for the generation of proximal and plausible counterfactual explanations for instance-based time series classification tasks (e.g., where users are provided with alternative time series to explain how a classification might change). The Native-Guide method retrieves and uses native in-sample counterfactuals that already exist in the training data as "guides" for perturbation in time series counterfactual generation. This method can be coupled with both Euclidean and Dynamic Time Warping (DTW) distance measures. After illustrating the technique on a case study involving a climate classification task, we reported on a comprehensive series of experiments on both real-world and synthetic data sets from the UCR archive. These experiments provide computational evidence of the quality of the counterfactual explanations generated.

There are now many meta-learning methods, each focusing on different modeling aspects of base and meta learners, but all can be (re)formulated as specific bilevel optimization problems. This work presents BOML, a modularized optimization library that unifies several meta-learning algorithms into a common bilevel optimization framework. It provides a hierarchical optimization pipeline together with a variety of iteration modules, which can be used to solve the mainstream categories of meta-learning methods, such as meta-feature-based and meta-initialization-based formulations.

Undertaking causal inference with observational data is extremely useful across a wide range of domains including the development of medical treatments, advertisements and marketing, and policy making. There are two main challenges associated with undertaking causal inference using observational data: treatment assignment heterogeneity (i.e., differences between the treated and untreated groups), and an absence of counterfactual data (i.e. not knowing what would have happened if an individual who did get treatment, were instead to have not been treated). We address these two challenges by combining structured inference and targeted learning. To our knowledge, Targeted Variational AutoEncoder (TVAE) is the first method to incorporate targeted learning into deep latent variable models. Results demonstrate competitive and state of the art performance.

The Artificial Intelligence for Edge Devices market study now available with Market Study Report, LLC, is a collation of valuable insights related to market size, market share, profitability margin, growth dynamics and regional proliferation of this business vertical. The study further includes a detailed analysis pertaining to key challenges, growth opportunities and application segments of the Artificial Intelligence for Edge Devices market. The Artificial Intelligence for Edge Devices market report delivers an exhaustive analysis of this industry vertical and comprises of insights pertaining to the market tendencies including profits estimations, periodic deliverables, current revenue, industry share and remuneration estimations over the forecast period. A summary of the performance evaluation of the Artificial Intelligence for Edge Devices market is offered in the report. It also includes crucial information concerning to the key industry trends and projected growth rate of the said market.

A fresh report titled "Artificial Intelligence In IoT Market" conveying key insights and providing a competitive advantage to clients through a comprehensive report. The report contains 123 pages which highly exhibit on up-to-date market analysis scenario, upcoming as well as future opportunities, revenue growth, pricing and profitability. An exclusive data and facts offered in this report is collected by research and industry experts' team. Research Trades proclaims the addition of new analytical data which helps to make informed business decisions. It has been abridged with a exhaustive description of the global Artificial Intelligence In IoT Market including overview, Types, Segments, Applications and Features of the market.

The report on the AI (Artificial Intelligence) Chip industry provides an in-depth assessment of the AI (Artificial Intelligence) Chip market including technological advancements, market drivers, challenges, current and emerging trends, opportunities, threats, risks, strategic developments, product advancements, and other key features. The report covers market size estimation, share, growth rate, global position, and regional analysis of the market. The report also covers forecast estimations for investments in the AI (Artificial Intelligence) Chip industry from 2020 to 2027. The report is furnished with the latest market dynamics and economic scenario in regards to the COVID-19 pandemic. The pandemic has brought about drastic changes in the economy of the world and has affected several key segments and growth opportunities.

The Vatican's Pontifical Academy for Life, which began the year by urging the ethical development and application of artificial intelligence (AI), has announced an effort to use technology to fight world hunger, which has worsened during the pandemic. The Vatican institution, in collaboration with IBM, Microsoft and the UN Food and Agriculture Organization, or FAO, is encouraging governments, nonprofits and corporations to assure that technology is used to feed everyone, and to make farmers' lives more efficient and productive. In its quest to assure the transparent, responsible and inclusive use of AI, the Vatican and FAO are pushing for solutions in agriculture that will benefit not just the well off, but also the poor. "We need to face the biggest challenges on the planet," said John E. Kelly III, executive vice president of IBM. Kelly, who participated in the FAO and Pontifical Academy's Sept. 24 virtual conference announcing the effort against hunger, was one of the signers of the Vatican's call for AI ethics in February. The Vatican's effort to promote ethical AI for social good includes a new program to use digital technology to ensure a more sustainable and efficient global food supply.

Artificial Intelligence (AI) is the study of "intelligent agents" which can be define as any device that perceives its environment and takes appropriate action that makes the highest probability of achieving its goals. Additionally, it can also be define as a system's ability to interpret external data, learn from gathered data and use those learnings to realize specific goals through adaptation. It is also called as machine intelligence and attributed to the nature of intelligence demonstrated by machines. Some of the features of artificial intelligence are; successfully understanding human language, contending at the highest level in strategic games systems such as chess and go, autonomously operating cars, intelligent routing in content delivery networks and military simulations and others. To solve the problem of learning and perceiving the immediate environment, many approaches have been taken such as statistical methods, computational intelligence, versions of search and mathematical optimization, artificial neural networks, and methods based on statistic, probability and economics.

Multicasting in wireless systems is a natural way to exploit the redundancy in user requests in a Content Centric Network. Power control and optimal scheduling can significantly improve the wireless multicast network's performance under fading. However, the model based approaches for power control and scheduling studied earlier are not scalable to large state space or changing system dynamics. In this paper, we use deep reinforcement learning where we use function approximation of the Q-function via a deep neural network to obtain a power control policy that matches the optimal policy for a small network. We show that power control policy can be learnt for reasonably large systems via this approach. Further we use multi-timescale stochastic optimization to maintain the average power constraint. We demonstrate that a slight modification of the learning algorithm allows tracking of time varying system statistics. Finally, we extend the multi-timescale approach to simultaneously learn the optimal queueing strategy along with power control. We demonstrate scalability, tracking and cross layer optimization capabilities of our algorithms via simulations. The proposed multi-timescale approach can be used in general large state space dynamical systems with multiple objectives and constraints, and may be of independent interest.

The impressive performance exhibited by modern machine learning models hinges on the ability to train such models on a very large amounts of labeled data. However, since access to large volumes of labeled data is often limited or expensive, it is desirable to alleviate this bottleneck by carefully curating the training set. Optimal experimental design is a well-established paradigm for selecting data point to be labeled so to maximally inform the learning process. Unfortunately, classical theory on optimal experimental design focuses on selecting examples in order to learn underparameterized (and thus, non-interpolative) models, while modern machine learning models such as deep neural networks are overparameterized, and oftentimes are trained to be interpolative. As such, classical experimental design methods are not applicable in many modern learning setups. Indeed, the predictive performance of underparameterized models tends to be variance dominated, so classical experimental design focuses on variance reduction, while the predictive performance of overparameterized models can also be, as is shown in this paper, bias dominated or of mixed nature. In this paper we propose a design strategy that is well suited for overparameterized regression and interpolation, and we demonstrate the applicability of our method in the context of deep learning by proposing a new algorithm for single-shot deep active learning.