Interest in the field of Explainable Artificial Intelligence has been growing for decades, and has accelerated recently. As Artificial Intelligence models have become more complex, and often more opaque, with the incorporation of complex machine learning techniques, explainability has become more critical. Recently, researchers have been investigating and tackling explainability with a user-centric focus, looking for explanations to consider trustworthiness, comprehensibility, explicit provenance, and context-awareness. In this chapter, we leverage our survey of explanation literature in Artificial Intelligence and closely related fields and use these past efforts to generate a set of explanation types that we feel reflect the expanded needs of explanation for today's artificial intelligence applications. We define each type and provide an example question that would motivate the need for this style of explanation. We believe this set of explanation types will help future system designers in their generation and prioritization of requirements and further help generate explanations that are better aligned to users' and situational needs.

Explainability has been an important goal since the early days of Artificial Intelligence. Several approaches for producing explanations have been developed. However, many of these approaches were tightly coupled with the capabilities of the artificial intelligence systems at the time. With the proliferation of AI-enabled systems in sometimes critical settings, there is a need for them to be explainable to end-users and decision-makers. We present a historical overview of explainable artificial intelligence systems, with a focus on knowledge-enabled systems, spanning the expert systems, cognitive assistants, semantic applications, and machine learning domains. Additionally, borrowing from the strengths of past approaches and identifying gaps needed to make explanations user- and context-focused, we propose new definitions for explanations and explainable knowledge-enabled systems.

Technology is altering the lives of people and thus changing all business practices and operations. As a result, every industry is now focusing on adopting new and innovative technologies in their business ventures. The customer service industry is no exception in this case as it has turned into a unique turning point for businesses. Now, customers are having access to the product information as businesses have access to the customer data and other means of reaching their customers. Thus, it has become necessary for business organizations to offer an engaging and useful customer service experience in all aspects.

Life's most valuable asset is health. Continuously understanding the state of our health and modeling how it evolves is essential if we wish to improve it. Given the opportunity that people live with more data about their life today than any other time in history, the challenge rests in interweaving this data with the growing body of knowledge to compute and model the health state of an individual continually. This dissertation presents an approach to build a personal model and dynamically estimate the health state of an individual by fusing multi-modal data and domain knowledge. The system is stitched together from four essential abstraction elements: 1. the events in our life, 2. the layers of our biological systems (from molecular to an organism), 3. the functional utilities that arise from biological underpinnings, and 4. how we interact with these utilities in the reality of daily life. Connecting these four elements via graph network blocks forms the backbone by which we instantiate a digital twin of an individual. Edges and nodes in this graph structure are then regularly updated with learning techniques as data is continuously digested. Experiments demonstrate the use of dense and heterogeneous real-world data from a variety of personal and environmental sensors to monitor individual cardiovascular health state. State estimation and individual modeling is the fundamental basis to depart from disease-oriented approaches to a total health continuum paradigm. Precision in predicting health requires understanding state trajectory. By encasing this estimation within a navigational approach, a systematic guidance framework can plan actions to transition a current state towards a desired one. This work concludes by presenting this framework of combining the health state and personal graph model to perpetually plan and assist us in living life towards our goals.

The goal of this challenge is to test the potential of Reinforcement Learning (RL) to control electrical power transmission, in the most cost-effective manner, while keeping people and equipment safe from harm. Solving this challenge may have very positive impacts on society, as governments move to decarbonize the electricity sector and to electrify other sectors, to help reach IPCC climate goals. Existing software, computational methods and optimal powerflow solvers are not adequate for real-time network operations on short temporal horizons in a reasonable computational time. With recent changes in electricity generation and consumption patterns, system operation is moving to become more of a stochastic rather than a deterministic control problem. In order to overcome these complexities, new computational methods are required. The intention of this challenge is to explore RL as a solution method for electricity network control. There may be under-utilized, cost-effective flexibility in the power network that RL techniques can identify and capitalize on, that human operators and traditional solution techniques are unaware of or unaccustomed to. An RL agent that can act in conjunction, or in parallel with human network operators, will optimize grid security and reliability, allowing more renewable resources to be connected while minimizing the cost and maintaining supply to customers, and preventing damage to electrical equipment. Another aim of the project is to broaden the audience for the problem of electricity network control and to foster collaboration between experts in both the power systems community and the wider RL/ML community.

Contextual embeddings, such as ELMo and BERT, move beyond global word representations like Word2Vec and achieve ground-breaking performance on a wide range of natural language processing tasks. Contextual embeddings assign each word a representation based on its context, thereby capturing uses of words across varied contexts and encoding knowledge that transfers across languages. In this survey, we review existing contextual embedding models, cross-lingual polyglot pre-training, the application of contextual embeddings in downstream tasks, model compression, and model analyses.

Deep Learning (DL) is vulnerable to out-of-distribution and adversarial examples resulting in incorrect outputs. To make DL more robust, several posthoc anomaly detection techniques to detect (and discard) these anomalous samples have been proposed in the recent past. This survey tries to provide a structured and comprehensive overview of the research on anomaly detection for DL based applications. We provide a taxonomy for existing techniques based on their underlying assumptions and adopted approaches. We discuss various techniques in each of the categories and provide the relative strengths and weaknesses of the approaches. Our goal in this survey is to provide an easier yet better understanding of the techniques belonging to different categories in which research has been done on this topic. Finally, we highlight the unsolved research challenges while applying anomaly detection techniques in DL systems and present some high-impact future research directions.

Comprehensive surveys on GNNs were provided by Hamilton et al. (2017a), Zhou et al. (2018), and Wu et al. (2019). Despite GNNs' empirical successes in various fields, Xu et al. (2019) and Morris et al. (2019) demonstrated that GNNs cannot distinguish some pairs of graphs. This indicates that GNNs cannot correctly classify these graphs with any parameters unless the labels of these graphs are the same. This result contrasts with the universal approximation power of multi layer perceptrons (Cybenko, 1989; Hornik et al., 1989; Hornik, 1991). Furthermore, Sato et al. (2019a) showed that GNNs are at most as powerful as distributed local algorithms (Angluin, 1980; Suomela, 2013). Thus there are many combinatorial problems that GNNs cannot solve other than the graph isomorphism problem. Consequently, various provably powerful GNN models have been proposed to overcome the limitations of GNNs. This survey provides an extensive overview of the expressive power of GNNs and various GNN models to overcome these limitations.

Autonomous driving is of great interest to industry and academia alike. The use of machine learning approaches for autonomous driving has long been studied, but mostly in the context of perception. In this paper we take a deeper look on the so called end-to-end approaches for autonomous driving, where the entire driving pipeline is replaced with a single neural network. We review the learning methods, input and output modalities, network architectures and evaluation schemes in end-to-end driving literature. Interpretability and safety are discussed separately, as they remain challenging for this approach. Beyond providing a comprehensive overview of existing methods, we conclude the review with an architecture that combines the most promising elements of the end-to-end autonomous driving systems.

Human gait refers to a daily motion that represents not only mobility, but it can also be used to identify the walker by either human observers or computers. Recent studies reveal that gait even conveys information about the walker's emotion. Individuals in different emotion states may show different gait patterns. The mapping between various emotions and gait patterns provides a new source for automated emotion recognition. Compared to traditional emotion detection biometrics, such as facial expression, speech and physiological parameters, gait is remotely observable, more difficult to imitate, and requires less cooperation from the subject. These advantages make gait a promising source for emotion detection. This article reviews current research on gait-based emotion detection, particularly on how gait parameters can be affected by different emotion states and how the emotion states can be recognized through distinct gait patterns. We focus on the detailed methods and techniques applied in the whole process of emotion recognition: data collection, preprocessing, and classification. At last, we discuss possible future developments of efficient and effective gait-based emotion recognition using the state of the art techniques on intelligent computation and big data.