Quality education, one of the seventeen sustainable development goals (SDGs) identified by the United Nations General Assembly, stands to benefit enormously from the adoption of artificial intelligence (AI) driven tools and technologies. The concurrent boom of necessary infrastructure, digitized data and general social awareness has propelled massive research and development efforts in the artificial intelligence for education (AIEd) sector. In this review article, we investigate how artificial intelligence, machine learning and deep learning methods are being utilized to support students, educators and administrative staff. We do this through the lens of a novel categorization approach. We consider the involvement of AI-driven methods in the education process in its entirety - from students admissions, course scheduling etc. in the proactive planning phase to knowledge delivery, performance assessment etc. in the reactive execution phase. We outline and analyze the major research directions under proactive and reactive engagement of AI in education using a representative group of 194 original research articles published in the past two decades i.e., 2003 - 2022. We discuss the paradigm shifts in the solution approaches proposed, i.e., in the choice of data and algorithms used over this time. We further dive into how the COVID-19 pandemic challenged and reshaped the education landscape at the fag end of this time period. Finally, we pinpoint existing limitations in adopting artificial intelligence for education and reflect on the path forward.

The ability to estimate human intentions and interact with human drivers intelligently is crucial for autonomous vehicles to successfully achieve their objectives. In this paper, we propose a game theoretic planning algorithm that models human opponents with an iterative reasoning framework and estimates human latent cognitive states through probabilistic inference and active learning. By modeling the interaction as a partially observable Markov decision process with adaptive state and action spaces, our algorithm is able to accomplish real-time lane changing tasks in a realistic driving simulator. We compare our algorithm's lane changing performance in dense traffic with a state-of-the-art autonomous lane changing algorithm to show the advantage of iterative reasoning and active learning in terms of avoiding overly conservative behaviors and achieving the driving objective successfully.

In district-based elections, electors cast votes in their respective districts. In each district, the party with maximum votes wins the corresponding seat in the governing body. The election result is based on the number of seats won by different parties. In this system, locations of electors across the districts may severely affect the election result even if the total number of votes obtained by different parties remains unchanged. A less popular party may end up winning more seats if their supporters are suitably distributed spatially. This happens due to various regional and social influences on individual voters which modulate their voting choice. In this paper, we explore agent-based models for district-based elections, where we consider each elector as an agent, and try to represent their social and geographical attributes and political inclinations using probability distributions. This model can be used to simulate election results by Monte Carlo sampling. The models allow us to explore the full space of possible outcomes of an electoral setting, though they can also be calibrated to actual election results for suitable values of parameters. We use Approximate Bayesian Computation (ABC) framework to estimate model parameters. We show that our model can reproduce the results of elections held in India and USA, and can also produce counterfactual scenarios.

Machine Learning (ML) is the branch of Artificial Intelligence in which we use algorithms to learn from data provided to make predictions on unseen data. Recently, the demand for Machine Learning engineers has rapidly grown across healthcare, Finance, e-commerce, etc. According to Glassdoor, the median ML Engineer Salary is $131,290 per annum. In 2021, the global ML market was valued at $15.44 billion. It is expected to grow at a significant compound annual growth rate (CAGR) above 38% until 2029.

One of the virtues of the Bayesianapproachto statistical analysisis that it gives an unambiguous definition of what it means for there to be evidence in favor of or against a particular value of a parameter. This is provided by the following principle. Principle of Evidence: if the posterior probability of an event is greater than (less than, equal to) its prior probability, then there is evidence in favor of (against, no evidence either way of) the event being true. This seems like a very simple and intuitively satisfying way of characterizing evidence and it has long been considered to be quite natural and obvious. For example, Popper (1968) The Logic of Scientific Discovery, Appendix ix "If we are asked to give a criterion of the fact that the evidence y supports or corroborates a statement x, the most obvious reply is: that y increases the probability of x." Achinstein (2001) "for a fact e to be evidence that a hypothesis h is true, it is both necessary and sufficient for e to increase h's probability over its prior probability".

A widely cited explanation for how humans think about trustworthiness posits that people consider three factors, or traits, of a person (or agent) when they evaluate trustworthiness: ability, benevolence, and integrity [20]. It is common practice for intelligent agent researchers to adapt a psychometric inventory of this three-factor model of trustworthiness for assessing users' perceived trustworthiness of agents [19]. In theory, administering the inventory prior to an interaction allows researchers to assess the role of anticipated agent trustworthiness in users' behavior, while post hoc administration allows researchers to assess whether particular elements of an interaction, perhaps an experimental manipulation, impacted users' opinions of the agent. In practice, however, people frequently misuse information when they form judgments and make decisions [11, 17]. For example, a person who is momentarily happy (sad), perhaps from reminiscing about a positive (negative) event from their recent past, is likely to rate their life satisfaction as higher (lower) than if you asked them when they were in a neutral state [25]. Regardless of the saliency of information, the normative approach is to always use it the same way.

Many real-world problems are characterized by a large number of observations, confounding and spurious correlations, partially observable states, and distal, dynamic rewards with hierarchical reward structures. Such conditions make it hard for both animal and machines to learn complex skills. The learning process requires discovering what is important and what can be ignored, how the reward function is structured, and how to reuse knowledge across different tasks that share common properties. For these reasons, the application of standard reinforcement learning (RL) algorithms (Sutton and Barto, 2018) to solve structured problems is often not effective. Limitations of current RL algorithms include the problem of exploration with sparse rewards (Pathak et al., 2017), dealing with partially observable Markov decision problems (POMDP) (Ladosz et al., 2021), coping with large amounts of confounding stimuli (Thrun, 2000; Kim et al., 2019), and reusing skills for efficiently learning multiple task in a lifelong learning setting (Mendez and Eaton, 2020). Standard reinforcement learning algorithms are best suited when the problem can be formulated as a single-task problem in observable Markov decision problem (MDP). Under these assumptions, with complete observability and with static and frequent rewards, deep reinforcement learning (DRL) (Mnih et al., 2015; Li, 2017) has gained popularity due to the ability to learn an approximated Q-value function directly from raw pixel data in the Atari 2600 platform. This and similar algorithms stack multiple frames to derive states of an MDP, and use a basic ɛ-greedy exploration policy. In more complex cases with partial observability and sparse rewards, extensions have been proposed to include more advanced exploration techniques (Ladosz et al., 2022), e.g.

Deep Learning (DL) holds great promise in reshaping the healthcare industry owing to its precision, efficiency, and objectivity. However, the brittleness of DL models to noisy and out-of-distribution inputs is ailing their deployment in the clinic. Most models produce point estimates without further information about model uncertainty or confidence. This paper introduces a new Bayesian DL framework for uncertainty quantification in segmentation neural networks: SUPER-Net: trustworthy medical image Segmentation with Uncertainty Propagation in Encoder-decodeR Networks. SUPER-Net analytically propagates, using Taylor series approximations, the first two moments (mean and covariance) of the posterior distribution of the model parameters across the nonlinear layers. In particular, SUPER-Net simultaneously learns the mean and covariance without expensive post-hoc Monte Carlo sampling or model ensembling. The output consists of two simultaneous maps: the segmented image and its pixelwise uncertainty map, which corresponds to the covariance matrix of the predictive distribution. We conduct an extensive evaluation of SUPER-Net on medical image segmentation of Magnetic Resonances Imaging and Computed Tomography scans under various noisy and adversarial conditions. Our experiments on multiple benchmark datasets demonstrate that SUPER-Net is more robust to noise and adversarial attacks than state-of-the-art segmentation models. Moreover, the uncertainty map of the proposed SUPER-Net associates low confidence (or equivalently high uncertainty) to patches in the test input images that are corrupted with noise, artifacts, or adversarial attacks. Perhaps more importantly, the model exhibits the ability of self-assessment of its segmentation decisions, notably when making erroneous predictions due to noise or adversarial examples.

We introduce CriticSMC, a new algorithm for planning as inference built from a composition of sequential Monte Carlo with learned Soft-Q function heuristic factors. These heuristic factors, obtained from parametric approximations of the marginal likelihood ahead, more effectively guide SMC towards the desired target distribution, which is particularly helpful for planning in environments with hard constraints placed sparsely in time. Compared with previous work, we modify the placement of such heuristic factors, which allows us to cheaply propose and evaluate large numbers of putative action particles, greatly increasing inference and planning efficiency. CriticSMC is compatible with informative priors, whose density function need not be known, and can be used as a model-free control algorithm. Our experiments on collision avoidance in a high-dimensional simulated driving task show that CriticSMC significantly reduces collision rates at a low computational cost while maintaining realism and diversity of driving behaviors across vehicles and environment scenarios.

The standard assumption in reinforcement learning (RL) is that agents observe feedback for their actions immediately. However, in practice feedback is often observed in delay. This paper studies online learning in episodic Markov decision process (MDP) with unknown transitions, adversarially changing costs, and unrestricted delayed bandit feedback. More precisely, the feedback for the agent in episode $k$ is revealed only in the end of episode $k + d^k$, where the delay $d^k$ can be changing over episodes and chosen by an oblivious adversary. We present the first algorithms that achieve near-optimal $\sqrt{K + D}$ regret, where $K$ is the number of episodes and $D = \sum_{k=1}^K d^k$ is the total delay, significantly improving upon the best known regret bound of $(K + D)^{2/3}$.