Recent studies have shown that students follow stable behavioral patterns while learning in online educational systems. These behavioral patterns can further be used to group the students into different clusters. However, as these clusters include both high-and low-performance students, the relation between the behavioral patterns and student performance is yet to be clarified. In this work, we study the relation between students' learning behaviors and their performance, in a self-organized online learning system that allows them to freely practice with various problems and worked examples. We represent each student's behavior as a vector of high-support sequential micro-patterns. Assuming that some behavioral patterns are shared across high-and low-performance students, and some are specific to each group, we group the students according to their performance. Having this assumption, we discover both the prevalent behavioral patterns in each group, and the shared patterns across groups using discriminative non-negative matrix factorization. Our experiments show that there are such common and specific patterns in students' behavior that are discriminative among students with different performances.

Classification of hand drawn sketches with respect to content quality is extremely challenging task, comparing to usual image classification methods. In brief, we need to train computational device to able to classify the images of the same object into different classes with respect their content quality. In this paper we tested several methods of image classification, using machine learning and computer vision algorithms, to classify Draw-a-Person test images sketched by primary school students in Nigeria, aged 4 to 11 years. We collected 1000 original sketches and manually classified them (using guidelines from existing literature) according to the ages (8 classes) before testing this dataset on a computational device. The highest accuracy achieved in this experiment was 62%. We achieved this result with novel method, where we used Bag of Visual Words and K-means algorithm to count key-points on each sketch. We strongly believe that this challenging task needs further research to improve classification accuracy, we, therefore, release the complete dataset of sketches to the community.

Inspired by Vaswani’s transformer, we propose in this paper an attention-based transformer neural network with a multi-head attention mechanism for the task of student answer assessment. Results show the competitiveness of our proposed model. A highest accuracy of 71.5% was achieved when using ELMo embeddings, 10 heads of attention, and 2 layers. This is very competitive and rivals the highest accuracy achieved by a previously proposed BI-GRU-Capsnet deep network (72.5%) on the same dataset. The main advantages of using transformers over BI-GRU-Capsnet is reducing the training time and giving more space for parallelization.

Computer Science (CS) education is critical in todays world, and introductory programming courses are considered extremely difficult and frustrating, often considered a major stumbling block for students willing to pursue computer programming related careers. In this paper, we describe the design of Socratic Tutor, an Intelligent Tutoring System that can help novice programmers to better understand programming concepts. The system was inspired by the Socratic method of teaching in which the main goal is to ask a set of guiding questions about key concepts and major steps or segments of complete code examples. To evaluate the Socratic Tutor, we conducted a pilot study with 34 computer science students and the results are promising in terms of learning gains.

ByteDdance's subsidiary Beijing Diandiankankan Technology announced yesterday to release a new AI English learning App named KaiYanJianDanXue(开言简单学, literally translated as Open Language Easy Learning), which is regarded as the beginner-friendly version of Open Language. According to the introduction of the product in the App Store, the functions of this new product mainly include providing scenario learning videos and online courses from North American teachers, improving pronunciation via AI technology, and offering learners individualized learning and reviewing plans. Zhang Yiming, the founder and CEO of ByteDance, regards that the combination with technology will be an inevitable trend in future education sector. From 2017 onwards, ByteDance started to launch educational products in succession such as Learning app Haohao Xuexi (means study well), online English learning platforms GoGoKid and aiKID, English learning app Tangyuan English, and AI English learning product for children from 2 to 8-year-old named GuaGuaLong.

Moving forward on its sweeping vision to transform the future of education through artificial intelligence (AI), the University of Florida is collaborating with technology company NVIDIA to acquire the world's most advanced AI system to boost the performance of UF's powerful supercomputer. UF today announced it will be the country's first higher education institution to acquire the new NVIDIA DGX A100 -- the world's most advanced AI system. The new systems are scheduled to arrive at UF at the end of May and mark a significant step in the university's bold initiative to become a national leader in the application of AI, an expansive plan that will elevate UF in research, teaching, and economic development. The initiative includes a commitment from UF to hire 100 faculty members specifically focused on AI, in addition to the 500 new faculty hired across disciplines -- many of whom will integrate AI into their teaching and research. UF is also embarking on a unique plan to infuse AI across academic majors, creating a next generation AI-enabled workforce and democratizing a technology that has the potential to solve some of the globe's most formidable challenges.

Computer vision is an Artificial Intelligence technology that allows computers to understand and label images, is now used in convenience stores, driverless car testing, daily medical diagnostics and in monitoring the health of crops and livestock. In this session, we will have Dr. Nicholas Nicoloudis and Abinaya Seenivasan from @SAP along with Aruna Kolluru from @Dell Technologies to discuss various applications of Computer Vision. The content is as below: 1. What is Computer Vision? 2. Technologies involved, including Machine Learning techniques. Please join me and feel free to ask questions.

Tensor networks (TN) have found a wide use in machine learning, and in particular, TN and deep learning bear striking similarities. In this work, we propose the quantum-classical hybrid tensor networks (HTN) which combine tensor networks with classical neural networks in a uniform deep learning framework to overcome the limitations of regular tensor networks in machine learning. We first analyze the limitations of regular tensor networks in the applications of machine learning involving the representation power and architecture scalability. We conclude that in fact the regular tensor networks are not competent to be the basic building blocks of deep learning. Then, we discuss the performance of HTN which overcome all the deficiency of regular tensor networks for machine learning. In this sense, we are able to train HTN in the deep learning way which is the standard combination of algorithms such as Back Propagation and Stochastic Gradient Descent. We finally provide two applicable cases to show the potential applications of HTN, including quantum states classification and quantum-classical autoencoder. These cases also demonstrate the great potentiality to design various HTN in deep learning way.

Active learning is a framework in which the learning machine can select the samples to be used for training. This technique is promising, particularly when the cost of data acquisition and labeling is high. In active learning, determining the timing at which learning should be stopped is a critical issue. In this study, we propose a criterion for automatically stopping active learning. The proposed stopping criterion is based on the difference in the expected generalization errors and hypothesis testing. We derive a novel upper bound for the difference in expected generalization errors before and after obtaining a new training datum based on PAC-Bayesian theory. Unlike ordinary PAC-Bayesian bounds, though, the proposed bound is deterministic; hence, there is no uncontrollable trade-off between the confidence and tightness of the inequality. We combine the upper bound with a statistical test to derive a stopping criterion for active learning. We demonstrate the effectiveness of the proposed method via experiments with both artificial and real datasets.

Currently, the divergence in distributions of design and operational data, and large computational complexity are limiting factors in the adoption of CNNs in real-world applications. For instance, person re-identification systems typically rely on a distributed set of cameras, where each camera has different capture conditions. This can translate to a considerable shift between source (e.g. lab setting) and target (e.g. operational camera) domains. Given the cost of annotating image data captured for fine-tuning in each target domain, unsupervised domain adaptation (UDA) has become a popular approach to adapt CNNs. Moreover, state-of-the-art deep learning models that provide a high level of accuracy often rely on architectures that are too complex for real-time applications. Although several compression and UDA approaches have recently been proposed to overcome these limitations, they do not allow optimizing a CNN to simultaneously address both. In this paper, we propose an unexplored direction -- the joint optimization of CNNs to provide a compressed model that is adapted to perform well for a given target domain. In particular, the proposed approach performs unsupervised knowledge distillation (KD) from a complex teacher model to a compact student model, by leveraging both source and target data. It also improves upon existing UDA techniques by progressively teaching the student about domain-invariant features, instead of directly adapting a compact model on target domain data. Our method is compared against state-of-the-art compression and UDA techniques, using two popular classification datasets for UDA -- Office31 and ImageClef-DA. In both datasets, results indicate that our method can achieve the highest level of accuracy while requiring a comparable or lower time complexity.