Prior work in standardized science exams requires support from large text corpus, such as targeted science corpus from Wikipedia or SimpleWikipedia. However, retrieving knowledge from the large corpus is time-consuming and questions embedded in complex semantic representation may interfere with retrieval. Inspired by the dual process theory in cognitive science, we propose a MetaQA framework, where system 1 is an intuitive meta-classifier and system 2 is a reasoning module. Specifically, our method based on meta-learning method and large language model BERT, which can efficiently solve science problems by learning from related example questions without relying on external knowledge bases. We evaluate our method on AI2 Reasoning Challenge (ARC), and the experimental results show that meta-classifier yields considerable classification performance on emerging question types. The information provided by meta-classifier significantly improves the accuracy of reasoning module from 46.6% to 64.2%, which has a competitive advantage over retrieval-based QA methods.

A computational paradigm based on neuroscientific concepts is proposed and shown to be capable of online unsupervised clustering. Because it is an online method, it is readily amenable to streaming realtime applications and is capable of dynamically adjusting to macro-level input changes. All operations, both training and inference, are localized and efficient. The paradigm is implemented as a cognitive column that incorporates five key elements: 1) temporal coding, 2) an excitatory neuron model for inference, 3) winner-take-all inhibition, 4) a column architecture that combines excitation and inhibition, 5) localized training via spike timing de-pendent plasticity (STDP). These elements are described and discussed, and a prototype column is given. The prototype column is simulated with a semi-synthetic benchmark and is shown to have performance characteristics on par with classic k-means. Simulations reveal the inner operation and capabilities of the column with emphasis on excitatory neuron response functions and STDP implementations.

In the "Method" section, we present a novel approach Abstract-- E-Learning systems (ELS) and Intelligent Tutoring Systems (ITS) play a significant part in today's education Second, It can be adaptively retrained by the user's "Results" section, we present the evaluation results. The NCF got significantly better results than the EduRank with an AP I. INTRODUCTION In the "Discussion" section, we interpret (ITS) play a significant part in today's education A. Recommendation Systems in E-learning resources such as lectures, summaries, exercises, and exams. Their is generating a personalized test for a target learner. Furthermore, they used the tensor factorization algorithm to under a certain context. They applied their algorithms on the KDD difficulty, capabilities, context, learning styles, and habits.

As a comprehensive indicator of mathematical thinking and intelligence, the number sense (Dehaene 2011) bridges the induction of symbolic concepts and the competence of problem-solving. To endow such a crucial cognitive ability to machine intelligence, we propose a dataset, Machine Number Sense (MNS), consisting of visual arithmetic problems automatically generated using a grammar model--And-Or Graph (AOG). These visual arithmetic problems are in the form of geometric figures: each problem has a set of geometric shapes as its context and embedded number symbols. Solving such problems is not trivial; the machine not only has to recognize the number, but also to interpret the number with its contexts, shapes, and relations (e.g., symmetry) together with proper operations. We benchmark the MNS dataset using four predominant neural network models as baselines in this visual reasoning task. Comprehensive experiments show that current neural-network-based models still struggle to understand number concepts and relational operations. We show that a simple brute-force search algorithm could work out some of the problems without context information. Crucially, taking geometric context into account by an additional perception module would provide a sharp performance gain with fewer search steps. Altogether, we call for attention in fusing the classic search-based algorithms with modern neural networks to discover the essential number concepts in future research.

These elements have a diverse heritage in learning and management theory, and the way they are implemented will vary from one organization to another. Most or all of them are present, we believe, in every successful effort to raise the caliber of digital skills in an organization. When an initiative is designed effectively, the elements complement one another. Together, these elements create an immersive workplace environment that makes it easy to build new habits and learn new skills, continually reminding people of the progress they've made and the learning yet to come. Just as learning a new language is easier if you move to a community where it is constantly spoken, learning digital proficiency is easier if you are surrounded by other people who are fluent with the relevant technologies. But such widespread fluency is not the situation in businesses today. Training Industry, an organization and information source devoted to "the business of learning," estimates that organizations spent more than $362 billion on employee training and education in 2018 alone, reflecting a growth rate of 1.2 percent per year. Yet as Harvard Business School professor Michael Beer had already pointed out in 2016 in Harvard Business Review, organizations "are not getting a good return on their investment.

SAS is committed to building a global community of innovators that use technology to ignite positive change for people and the planet. This Earth Day, SAS and the International Institute for Applied Systems Analysis (IIASA) are implementing the next generation of crowd-driven artificial intelligence (AI) to help power AI algorithms designed to help us better understand our planet. IIASA is an independent, international research institute that is known for its expertise in systems analysis and providing policy solutions and baseline information on pressing concerns for humanity. IIASA is placing a spotlight on the issue of deforestation to learn about the application of AI to elucidate the interconnectivity of Earth's ecosystems. Today, our systems are changing rapidly, approaching levels that exceed existing human experiences, scientific understanding, and traditional modeling capabilities, making it increasingly difficult for humans to intervene efficiently, effectively and in a timely manner.

We propose a cumulative oversampling (CO) technique for Thompson Sampling (TS) that can be used to construct optimistic parameter estimates using significantly fewer samples from the posterior distributions compared to existing oversampling frameworks. We apply CO to a new budgeted variant of the Influence Maximization (IM) semi-bandits with linear generalization of edge weights. Combining CO with the oracle we designed for the offline problem, our online learning algorithm tackles the budget allocation, parameter learning, and reward maximization challenges simultaneously. We prove that our online learning algorithm achieves a scaled regret comparable to that of the UCB-based algorithms for IM semi-bandits. It is the first regret bound for TS-based algorithms for IM semi-bandits that does not depend linearly on the reciprocal of the minimum observation probability of an edge. In numerical experiments, our algorithm outperforms all UCB-based alternatives by a large margin.

In many applications, it is desirable to extract only the relevant information from complex input data, which involves making a decision about which input features are relevant. The information bottleneck method formalizes this as an information-theoretic optimization problem by maintaining an optimal tradeoff between compression (throwing away irrelevant input information), and predicting the target. In many problem settings, including the reinforcement learning problems we consider in this work, we might prefer to compress only part of the input. This is typically the case when we have a standard conditioning input, such as a state observation, and a "privileged" input, which might correspond to the goal of a task, the output of a costly planning algorithm, or communication with another agent. In such cases, we might prefer to compress the privileged input, either to achieve better generalization (e.g., with respect to goals) or to minimize access to costly information (e.g., in the case of communication). Practical implementations of the information bottleneck based on variational inference require access to the privileged input in order to compute the bottleneck variable, so although they perform compression, this compression operation itself needs unrestricted, lossless access. In this work, we propose the variational bandwidth bottleneck, which decides for each example on the estimated value of the privileged information before seeing it, i.e., only based on the standard input, and then accordingly chooses stochastically, whether to access the privileged input or not. We formulate a tractable approximation to this framework and demonstrate in a series of reinforcement learning experiments that it can improve generalization and reduce access to computationally costly information.

Data stream poses additional challenges to statistical classification tasks because distributions of the training and target samples may differ as time passes. Such distribution change in streaming data is called concept drift. Numerous histogram-based distribution change detection methods have been proposed to detect drift. Most histograms are developed on grid-based or tree-based space partitioning algorithms which makes the space partitions arbitrary, unexplainable, and may cause drift blind-spots. There is a need to improve the drift detection accuracy for histogram-based methods with the unsupervised setting. To address this problem, we propose a cluster-based histogram, called equal intensity k-means space partitioning (EI-kMeans). In addition, a heuristic method to improve the sensitivity of drift detection is introduced. The fundamental idea of improving the sensitivity is to minimize the risk of creating partitions in distribution offset regions. Pearson's chi-square test is used as the statistical hypothesis test so that the test statistics remain independent of the sample distribution. The number of bins and their shapes, which strongly influence the ability to detect drift, are determined dynamically from the sample based on an asymptotic constraint in the chi-square test. Accordingly, three algorithms are developed to implement concept drift detection, including a greedy centroids initialization algorithm, a cluster amplify-shrink algorithm, and a drift detection algorithm. For drift adaptation, we recommend retraining the learner if a drift is detected. The results of experiments on synthetic and real-world datasets demonstrate the advantages of EI-kMeans and show its efficacy in detecting concept drift.

In recent years, neural networks have demonstrated an outstanding ability to achieve complex learning tasks across various domains. However, they suffer from the "catastrophic forgetting" problem when they face a sequence of learning tasks, where they forget the old ones as they learn new tasks. This problem is also highly related to the "stability-plasticity dilemma". The more plastic the network, the easier it can learn new tasks, but the faster it also forgets previous ones. Conversely, a stable network cannot learn new tasks as fast as a very plastic network. However, it is more reliable to preserve the knowledge it has learned from the previous tasks. Several solutions have been proposed to overcome the forgetting problem by making the neural network parameters more stable, and some of them have mentioned the significance of dropout in continual learning. However, their relationship has not been sufficiently studied yet. In this paper, we investigate this relationship and show that a stable network with dropout learns a gating mechanism such that for different tasks, different paths of the network are active. Our experiments show that the stability achieved by this implicit gating plays a very critical role in leading to performance comparable to or better than other involved continual learning algorithms to overcome catastrophic forgetting.