Knowledge Tracing (KT), which aims to model student knowledge level and predict their performance, is one of the most important applications of user modeling. Modern KT approaches model and maintain an up-to-date state of student knowledge over a set of course concepts according to students' historical performance in attempting the problems. However, KT approaches were designed to model knowledge by observing relatively small problem-solving steps in Intelligent Tutoring Systems. While these approaches were applied successfully to model student knowledge by observing student solutions for simple problems, they do not perform well for modeling complex problem solving in students.M ost importantly, current models assume that all problem attempts are equally valuable in quantifying current student knowledge.However, for complex problems that involve many concepts at the same time, this assumption is deficient. In this paper, we argue that not all attempts are equivalently important in discovering students' knowledge state, and some attempts can be summarized together to better represent student performance. We propose a novel student knowledge tracing approach, Granular RAnk based TEnsor factorization (GRATE), that dynamically selects student attempts that can be aggregated while predicting students' performance in problems and discovering the concepts presented in them. Our experiments on three real-world datasets demonstrate the improved performance of GRATE, compared to the state-of-the-art baselines, in the task of student performance prediction. Our further analysis shows that attempt aggregation eliminates the unnecessary fluctuations from students' discovered knowledge states and helps in discovering complex latent concepts in the problems.

Language features are ever-evolving in the real-world social media environment. Many trained models in natural language understanding (NLU), ineffective in semantic inference for unseen features, might consequently struggle with the deteriorating performance in dynamicity. To address this challenge, we empirically study social media NLU in a dynamic setup, where models are trained on the past data and test on the future. It better reflects the realistic practice compared to the commonly-adopted static setup of random data split. To further analyze model adaption to the dynamicity, we explore the usefulness of leveraging some unlabeled data created after a model is trained. The performance of unsupervised domain adaption baselines based on auto-encoding and pseudo-labeling and a joint framework coupling them both are examined in the experiments. Substantial results on four social media tasks imply the universally negative effects of evolving environments over classification accuracy, while auto-encoding and pseudo-labeling collaboratively show the best robustness in dynamicity.

Uncertainty estimation is essential to make neural networks trustworthy in real-world applications. Extensive research efforts have been made to quantify and reduce predictive uncertainty. However, most existing works are designed for unimodal data, whereas multi-view uncertainty estimation has not been sufficiently investigated. Therefore, we propose a new multi-view classification framework for better uncertainty estimation and out-of-domain sample detection, where we associate each view with an uncertainty-aware classifier and combine the predictions of all the views in a principled way. The experimental results with real-world datasets demonstrate that our proposed approach is an accurate, reliable, and well-calibrated classifier, which predominantly outperforms the multi-view baselines tested in terms of expected calibration error, robustness to noise, and accuracy for the in-domain sample classification and the out-of-domain sample detection tasks.

Advances in deep learning and transfer learning have paved the way for various automation classification tasks in agriculture, including plant diseases, pests, weeds, and plant species detection. However, agriculture automation still faces various challenges, such as the limited size of datasets and the absence of plant-domain-specific pretrained models. Domain specific pretrained models have shown state of art performance in various computer vision tasks including face recognition and medical imaging diagnosis. In this paper, we propose AgriNet dataset, a collection of 160k agricultural images from more than 19 geographical locations, several images captioning devices, and more than 423 classes of plant species and diseases. We also introduce AgriNet models, a set of pretrained models on five ImageNet architectures: VGG16, VGG19, Inception-v3, InceptionResNet-v2, and Xception. AgriNet-VGG19 achieved the highest classification accuracy of 94 % and the highest F1-score of 92%. Additionally, all proposed models were found to accurately classify the 423 classes of plant species, diseases, pests, and weeds with a minimum accuracy of 87% for the Inception-v3 model.Finally, experiments to evaluate of superiority of AgriNet models compared to ImageNet models were conducted on two external datasets: pest and plant diseases dataset from Bangladesh and a plant diseases dataset from Kashmir.

Many applications in image-guided surgery and therapy require fast and reliable non-linear, multi-modal image registration. Recently proposed unsupervised deep learning-based registration methods have demonstrated superior performance compared to iterative methods in just a fraction of the time. Most of the learning-based methods have focused on mono-modal image registration. The extension to multi-modal registration depends on the use of an appropriate similarity function, such as the mutual information (MI). We propose guiding the training of a deep learning-based registration method with MI estimation between an image-pair in an end-to-end trainable network. Our results show that a small, 2-layer network produces competitive results in both mono- and multi-modal registration, with sub-second run-times. Comparisons to both iterative and deep learning-based methods show that our MI-based method produces topologically and qualitatively superior results with an extremely low rate of non-diffeomorphic transformations. Real-time clinical application will benefit from a better visual matching of anatomical structures and less registration failures/outliers.

Conspiracy theories about Covid-19 thrived in the comments on YouTube videos featuring Bill Gates despite the Google-owned platform's policies against misinformation. The new study examined a dataset of 38,564 YouTube comments that were drawn from three videos - all of which featured Gates and related to Covid-19 - that were posted by Fox News, Vox and China Global Television Network. Comments on the videos covered a range of topics, including the philanthropist's role in vaccine development and distribution, his connection to convicted sex offender Jeffrey Epstein, 5G networks and concepts around Gates being able to control people through human microchipping. The researchers used topic modelling and qualitative content analysis to determine that comments for each video were'heavily' dominated by conspiratorial statements. Conspiracy theories thrived in the comments on YouTube videos featuring Bill Gates (above) despite the Google-owned platform's policies against misinformation Gates, who co-founded Microsoft and remains a controversial figure, predicted a killer virus would originate in China and spread globally.

The onshoring and buildout of dozens of fabs, many costing tens of billions of dollars, is beginning to spill over into other areas that are critical for chip manufacturing. Materials, in particular, which often gets little attention outside of chip manufacturing, witnessed a big spike in September 2022. In fact, seven materials companies covered in this report made up more than a third of the month's total reported investments, with three of the companies garnering more than $200 million. Other investment targets were sputtering equipment and evaporation materials for deposition, high-purity polycrystalline silicon, fluorine-containing electronic gases, and silicon carbide. In the AI hardware arena, numerous startups are focusing on in-memory and near-memory compute, reducing the volume of data that needs to be moved back and forth between memory and processing elements. Novel architectures also are appearing, such as one that uses sparse mathematics.

ALEX – Alternative Experts is seeking a DevOps Engineer II to provide pipeline development support and infrastructure management across our cutting-edge AI/ML tool set. This is an early career-stage role (4 or more years of experience) and will directly influence our technology development efforts. This is an exciting new opportunity to work with our team of professionals to deliver AI based tools to our customers.

There are more than 30 species of dolphins in the world, the Māui dolphin, which lives off the west coast of the North Island, New Zealand, faces a threat of extinction. To save this rarest of the world's dolphins, a nonprofit organization has been formed called MAUI63 (Marine Animal Unmanned Identification, with 63 representing the estimated number of Māui dolphins when this initiative began in 2018). The team's scientists and conservationists use an AI-powered drone to locate, track, identify, and ultimately protect these and Hector's dolphins. The Māui dolphin population has declined further since the project began, as a 2021 survey counted only 54. Hector's and Māui dolphins are small coastal dolphins found only in New Zealand.

Published in "IEEE Robotics and Automation Magazine", DOI: 10.1109/MRA.2020.3044911 Matin Macktoobian, Denis Gillet, and Jean-Paul Kneib The authors are with the School of Engineering, Swiss Federal Institute of Technology in Lausanne (EPFL), Lausanne, Switzerland (e-mail: matin.macktoobian@epfl.ch; Abstract This paper introduces the emerging field of astrobotics, that is, a recently-established branch of robotics to be of service to astrophysics and observational astronomy. We first describe a modern requirement of dark matter studies, i.e., the generation of the map of the observable universe, using astrobots. Astrobots differ from conventional two-degree-of-freedom robotic manipulators in two respects. First, the dense formation of astrobots give rise to the extremely overlapping dynamics of neighboring astrobots which make them severely subject to collisions. Second, the structure of astrobots and their mechanical specifications are specialized due to the embedded optical fibers passed through them. We focus on the coordination problem of astrobots whose solutions shall be collision-free, fast execution, and complete in terms of the astrobots' convergence rates. We also illustrate the significant impact of astrobots assignments to observational targets on the quality of coordination solutions To present the current state of the field, we elaborate the open problems including next-generation astrophysical projects including 20,000 astrobots, and other fields, such as space debris tracking, in which astrobots may be potentially used. Astrobotics is an emerging field of swarm robotics aiming to the development and control of astrobots [1, 2] to be of service to astrophysical studies and cosmological spectroscopic observations. In particular, astrobotics addresses a wide range of swarm-robotic-related topics (see, Figure 1) which exhibit challenging problems in design, interaction, coordination, and mission planning corresponding to astrobots. There have been many astrophysical projects, such as the SDSS family [3] which seek the generation of the map of the observable universe.