Humans ability to transfer knowledge through teaching is one of the essential aspects for human intelligence. A human teacher can track the knowledge of students to customize the teaching on students needs. With the rise of online education platforms, there is a similar need for machines to track the knowledge of students and tailor their learning experience. This is known as the Knowledge Tracing (KT) problem in the literature. Effectively solving the KT problem would unlock the potential of computer-aided education applications such as intelligent tutoring systems, curriculum learning, and learning materials' recommendation. Moreover, from a more general viewpoint, a student may represent any kind of intelligent agents including both human and artificial agents. Thus, the potential of KT can be extended to any machine teaching application scenarios which seek for customizing the learning experience for a student agent (i.e., a machine learning model). In this paper, we provide a comprehensive and systematic review for the KT literature. We cover a broad range of methods starting from the early attempts to the recent state-of-the-art methods using deep learning, while highlighting the theoretical aspects of models and the characteristics of benchmark datasets. Besides these, we shed light on key modelling differences between closely related methods and summarize them in an easy-to-understand format. Finally, we discuss current research gaps in the KT literature and possible future research and application directions.

The model-based reinforcement learning paradigm, which uses planning algorithms and neural network models, has recently achieved unprecedented results in diverse applications, leading to what is now known as deep reinforcement learning. These agents are quite complex and involve multiple components, factors that can create challenges for research. In this work, we propose a new modular software architecture suited for these types of agents, and a set of building blocks that can be easily reused and assembled to construct new model-based reinforcement learning agents. These building blocks include planning algorithms, policies, and loss functions. We illustrate the use of this architecture by combining several of these building blocks to implement and test agents that are optimized to three different test environments: Cartpole, Minigrid, and Tictactoe. One particular planning algorithm, made available in our implementation and not previously used in reinforcement learning, which we called averaged minimax, achieved good results in the three tested environments. Experiments performed with this architecture have shown that the best combination of planning algorithm, policy, and loss function is heavily problem dependent. This result provides evidence that the proposed architecture, which is modular and reusable, is useful for reinforcement learning researchers who want to study new environments and techniques.

Instead of using current deep-learning segmentation models (like the UNet and variants), we approach the segmentation problem using trained Convolutional Neural Network (CNN) classifiers, which automatically extract important features from classified targets for image classification. Those extracted features can be visualized and formed heatmaps using Gradient-weighted Class Activation Mapping (Grad-CAM). This study tested whether the heatmaps could be used to segment the classified targets. We also proposed an evaluation method for the heatmaps; that is, to re-train the CNN classifier using images filtered by heatmaps and examine its performance. We used the mean-Dice coefficient to evaluate segmentation results. Results from our experiments show that heatmaps can locate and segment partial tumor areas. But only use of the heatmaps from CNN classifiers may not be an optimal approach for segmentation. In addition, we have verified that the predictions of CNN classifiers mainly depend on tumor areas, and dark regions in Grad-CAM's heatmaps also contribute to classification.

Classification models are a fundamental component of physical-asset management technologies such as structural health monitoring (SHM) systems and digital twins. Previous work introduced \textit{risk-based active learning}, an online approach for the development of statistical classifiers that takes into account the decision-support context in which they are applied. Decision-making is considered by preferentially querying data labels according to \textit{expected value of perfect information} (EVPI). Although several benefits are gained by adopting a risk-based active learning approach, including improved decision-making performance, the algorithms suffer from issues relating to sampling bias as a result of the guided querying process. This sampling bias ultimately manifests as a decline in decision-making performance during the later stages of active learning, which in turn corresponds to lost resource/utility. The current paper proposes two novel approaches to counteract the effects of sampling bias: \textit{semi-supervised learning}, and \textit{discriminative classification models}. These approaches are first visualised using a synthetic dataset, then subsequently applied to an experimental case study, specifically, the Z24 Bridge dataset. The semi-supervised learning approach is shown to have variable performance; with robustness to sampling bias dependent on the suitability of the generative distributions selected for the model with respect to each dataset. In contrast, the discriminative classifiers are shown to have excellent robustness to the effects of sampling bias. Moreover, it was found that the number of inspections made during a monitoring campaign, and therefore resource expenditure, could be reduced with the careful selection of the statistical classifiers used within a decision-supporting monitoring system.

A wide range of modern applications, especially in Bayesian inference framework [1], require the study of probability density functions (pdfs) which can be evaluated stochastically, i.e., only noisy evaluations can be obtained [2, 3, 4, 5]. For instance, this is the case of the pseudo-marginal approaches and doubly intractable posteriors [6, 7], approximate Bayesian computation (ABC) and likelihood-free schemes [8, 9], where the target density cannot be computed in closed-form. The noisy scenario also appears naturally when mini-batches of data are employed instead of considering the complete likelihood of huge amounts of data [10, 11]. More recently, the analysis of noisy functions of densities is required in reinforcement learning (RL), especially in direct policy search which is an important branch of RL, with applications in robotics [12, 13]. The topic of inference in noisy settings (or where a function is known with a certain degree of uncertainty) is also of interest in the inverse problem literature, such as in the calibration of expensive computer codes [14, 15]. This is also the case when the construction of an emulator is considered, as a surrogate model [4, 16, 17].

Understanding capabilities and limitations of different network architectures is of fundamental importance to machine learning. Bayesian inference on Gaussian processes has proven to be a viable approach for studying recurrent and deep networks in the limit of infinite layer width, $n\to\infty$. Here we present a unified and systematic derivation of the mean-field theory for both architectures that starts from first principles by employing established methods from statistical physics of disordered systems. The theory elucidates that while the mean-field equations are different with regard to their temporal structure, they yet yield identical Gaussian kernels when readouts are taken at a single time point or layer, respectively. Bayesian inference applied to classification then predicts identical performance and capabilities for the two architectures. Numerically, we find that convergence towards the mean-field theory is typically slower for recurrent networks than for deep networks and the convergence speed depends non-trivially on the parameters of the weight prior as well as the depth or number of time steps, respectively. Our method exposes that Gaussian processes are but the lowest order of a systematic expansion in $1/n$. The formalism thus paves the way to investigate the fundamental differences between recurrent and deep architectures at finite widths $n$.

AI and humans bring complementary skills to group deliberations. Modeling this group decision making is especially challenging when the deliberations include an element of risk and an exploration-exploitation process of appraising the capabilities of the human and AI agents. To investigate this question, we presented a sequence of intellective issues to a set of human groups aided by imperfect AI agents. A group's goal was to appraise the relative expertise of the group's members and its available AI agents, evaluate the risks associated with different actions, and maximize the overall reward by reaching consensus. We propose and empirically validate models of human-AI team decision making under such uncertain circumstances, and show the value of socio-cognitive constructs of prospect theory, influence dynamics, and Bayesian learning in predicting the behavior of human-AI groups.

Traffic signal control is an important problem in urban mobility with a significant potential of economic and environmental impact. While there is a growing interest in Reinforcement Learning (RL) for traffic control, the work so far has focussed on learning through interactions which, in practice, is costly. Instead, real experience data on traffic is available and could be exploited at minimal costs. Recent progress in offline or batch RL has enabled just that. Model-based offline RL methods, in particular, have been shown to generalize to the experience data much better than others. We build a model-based learning framework, A-DAC, which infers a Markov Decision Process (MDP) from dataset with pessimistic costs built in to deal with data uncertainties. The costs are modeled through an adaptive shaping of rewards in the MDP which provides better regularization of data compared to the prior related work. A-DAC is evaluated on a complex signalized roundabout using multiple datasets varying in size and in batch collection policy. The evaluation results show that it is possible to build high performance control policies in a data efficient manner using simplistic batch collection policies.

As is frequently the case in the sciences, ideas seem to be hanging around in the air and are often discovered by several thinkers independently in a span of years or even months. Something similar took place at the turn of the 19th century when scientists increasingly became aware of the importance of stochastic processes such as random walks in the sciences. In a span of years, random walks popped up in the context of mosquito populations (where they were tied to the spread of disease), Brownian motion of molecules (part of Einstein's annus mirabilis), acoustics, and the financial market. To start formally, a random walk is a stochastic process that describes the path of a subject in a mathematical space, which can be constituted by something like the integers, but also a 2-dimensional or higher-dimensional Euclidian space. We can illustrate this with a simple intuitive example.

This paper proposes an efficient approach to learning disentangled representations with causal mechanisms based on the difference of conditional probabilities in original and new distributions. We approximate the difference with models' generalization abilities so that it fits in the standard machine learning framework and can be efficiently computed. In contrast to the state-of-the-art approach, which relies on the learner's adaptation speed to new distribution, the proposed approach only requires evaluating the model's generalization ability. We provide a theoretical explanation for the advantage of the proposed method, and our experiments show that the proposed technique is 1.9-11.0 Causal reasoning is a fundamental tool that has shown significant impact in different disciplines (Rubin & Waterman, 2006; Ramsey et al., 2010; Rotmensch et al., 2017; Schölkopf et al., 2021), and it has roots in work by David Hume in the eighteenth century (Hume, 2003) and classical AI (Pearl, 2003). Causality has been mainly studied from a statistical perspective (Pearl, 2009; Peters et al., 2016; Greenland et al., 1999; Pearl, 2018) with Judea Pearl's work on the causal calculus leading its statistical development. More recently, there has been a growing interest in integrating statistical techniques into machine learning to leverage their benefits. Welling raises a particular question about how to disentangle correlation from causation in machine learning settings to take advantage of the sample efficiency and generalization abilities of causal reasoning (Welling, 2015). Although machine learning has achieved important results on a variety of tasks like computer vision and games over the past decade (e.g., Mnih et al. (2015); Silver et al. (2017); Szegedy et al. (2017); Hudson & Manning (2018)), current approaches can struggle to generalize when the test data distribution is much different from the training distribution (common in real applications). Further, these successful methods are typically "data-hungry", requiring an abundance of labeled examples to perform well across data distributions. In statistical settings, encoding the causal structure in models has been shown to have significant efficiency advantages.