Traditional learning-based approaches to student modeling generalize poorly to underrepresented student groups due to biases in data availability. In this paper, we propose a methodology for predicting student performance from their online learning activities that optimizes inference accuracy over different demographic groups such as race and gender. Building upon recent foundations in federated learning, in our approach, personalized models for individual student subgroups are derived from a global model aggregated across all student models via meta-gradient updates that account for subgroup heterogeneity. To learn better representations of student activity, we augment our approach with a self-supervised behavioral pretraining methodology that leverages multiple modalities of student behavior (e.g., visits to lecture videos and participation on forums), and include a neural network attention mechanism in the model aggregation stage. Through experiments on three real-world datasets from online courses, we demonstrate that our approach obtains substantial improvements over existing student modeling baselines in predicting student learning outcomes for all subgroups. Visual analysis of the resulting student embeddings confirm that our personalization methodology indeed identifies different activity patterns within different subgroups, consistent with its stronger inference ability compared with the baselines.

Challenges inherent to autonomous wintertime navigation in forests include lack of reliable a Global Navigation Satellite System (GNSS) signal, low feature contrast, high illumination variations and changing environment. This type of off-road environment is an extreme case of situations autonomous cars could encounter in northern regions. Thus, it is important to understand the impact of this harsh environment on autonomous navigation systems. To this end, we present a field report analyzing teach-and-repeat navigation in a subarctic forest while subject to fluctuating weather, including light and heavy snow, rain and drizzle. First, we describe the system, which relies on point cloud registration to localize a mobile robot through a boreal forest, while simultaneously building a map. We experimentally evaluate this system in over 18.8 km of autonomous navigation in the teach-and-repeat mode. Over 14 repeat runs, only four manual interventions were required, three of which were due to localization failure and another one caused by battery power outage. We show that dense vegetation perturbs the GNSS signal, rendering it unsuitable for navigation in forest trails. Furthermore, we highlight the increased uncertainty related to localizing using point cloud registration in forest trails. We demonstrate that it is not snow precipitation, but snow accumulation, that affects our system's ability to localize within the environment. Finally, we expose some challenges and lessons learned from our field campaign to support better experimental work in winter conditions. Our dataset is available online.

Both in the domains of Feature Selection and Interpretable AI, there exists a desire to `rank' features based on their importance. Such feature importance rankings can then be used to either: (1) reduce the dataset size or (2) interpret the Machine Learning model. In the literature, however, such Feature Rankers are not evaluated in a systematic, consistent way. Many papers have a different way of arguing which feature importance ranker works best. This paper fills this gap, by proposing a new evaluation methodology. By making use of synthetic datasets, feature importance scores can be known beforehand, allowing more systematic evaluation. To facilitate large-scale experimentation using the new methodology, a benchmarking framework was built in Python, called fseval. The framework allows running experiments in parallel and distributed over machines on HPC systems. By integrating with an online platform called Weights and Biases, charts can be interactively explored on a live dashboard. The software was released as open-source software, and is published as a package on the PyPi platform. The research concludes by exploring one such large-scale experiment, to find the strengths and weaknesses of the participating algorithms, on many fronts.

Deep supervision, or known as 'intermediate supervision' or 'auxiliary supervision', is to add supervision at hidden layers of a neural network. This technique has been increasingly applied in deep neural network learning systems for various computer vision applications recently. There is a consensus that deep supervision helps improve neural network performance by alleviating the gradient vanishing problem, as one of the many strengths of deep supervision. Besides, in different computer vision applications, deep supervision can be applied in different ways. How to make the most use of deep supervision to improve network performance in different applications has not been thoroughly investigated. In this paper, we provide a comprehensive in-depth review of deep supervision in both theories and applications. We propose a new classification of different deep supervision networks, and discuss advantages and limitations of current deep supervision networks in computer vision applications.

A machine learning program has been used to distinguish between cancerous and healthy cells by identifying patterns in characteristic combinations of genes.

Researchers have demonstrated that artificial intelligence may be performed using small nanomagnets that interact like neurons in the brain. Researchers have shown it is possible to perform artificial intelligence using tiny nanomagnets that interact like neurons in the brain. The new technology, developed by a team led by Imperial College London researchers, could significantly reduce the energy cost of artificial intelligence (AI), which is currently doubling globally every 3.5 months. In a paper published today (May 5, 2022) in the journal Nature Nanotechnology, the international team has produced the first proof that networks of nanomagnets can be used to perform AI-like processing. The researchers showed nanomagnets can be used for'time-series prediction' tasks, such as predicting and regulating insulin levels in diabetic patients.

Computer science tools offer powerful solutions to problems that physical scientists encounter. However, their potential remains untapped due to limited channels for knowledge sharing and a lack of visibility into the state of the art applications. The "Machine Learning for Polar Regions" workshop will serve as an opportunity to close the existing gaps between machine learning (ML) experts and polar scientists by identifying current obstacles and opportunities for cross-disciplinary collaboration. The ultimate goal of the workshop is to educate polar scientists and machine learning experts on each respective field and create a strategic roadmap to accelerate research through a coordinated, cross-disciplinary effort. The Workshop will start with presentations from climate and machine learning experts on current trends in each field, together and separately.

Thousands of emperor penguins waddling around Antarctica have a stalker: A yellow rover tracking their every move. ECHO is a remote-controlled ground robot that silently spies on the emperor penguin colony in Atka Bay. The robot is being monitored by the Single Penguin Observation and Tracking observatory. Both the SPOT observatory, which is also remote-operated through a satellite link, and the ECHO robot capture photographs and videos of animal population in the Arctic. The research is part of the Marine Animal Remote Sensing Lab (MARE), designed to measure the health of the Antarctic marine ecosystem.

The new method, developed by a team led by Imperial College London researchers, could slash the energy cost of artificial intelligence (AI), which is currently doubling globally every 3.5 months. In a paper published today in Nature Nanotechnology, the international team have produced the first proof that networks of nanomagnets can be used to perform AI-like processing. The researchers showed nanomagnets can be used for'time-series prediction' tasks, such as predicting and regulating insulin levels in diabetic patients. Artificial intelligence that uses'neural networks' aims to replicate the way parts of the brain work, where neurons talk to each other to process and retain information. A lot of the maths used to power neural networks was originally invented by physicists to describe the way magnets interact, but at the time it was too difficult to use magnets directly as researchers didn't know how to put data in and get information out.

Self-Organizing Maps (SOMs, Kohonen networks) belong to neural network models of the unsupervised class. In this paper, we present the generalized setup for non-Euclidean SOMs. Most data analysts take it for granted to use some subregions of a flat space as their data model; however, by the assumption that the underlying geometry is non-Euclidean we obtain a new degree of freedom for the techniques that translate the similarities into spatial neighborhood relationships. We improve the traditional SOM algorithm by introducing topology-related extensions. Our proposition can be successfully applied to dimension reduction, clustering or finding similarities in big data (both hierarchical and non-hierarchical).