Related papers: New Directions in International Masterclasses
Multimodal Large Models (MLMs) are becoming a significant research focus, combining powerful large language models with multimodal learning to perform complex tasks across different data modalities. This review explores the latest…
In this paper, we present a novel approach, Momentum$^2$ Teacher, for student-teacher based self-supervised learning. The approach performs momentum update on both network weights and batch normalization (BN) statistics. The teacher's…
Metric learning seeks to embed images of objects suchthat class-defined relations are captured by the embeddingspace. However, variability in images is not just due to different depicted object classes, but also depends on other latent…
The performance of over 2000 students in introductory calculus-based electromagnetism (E&M) courses at four large research universities was measured using the Brief Electricity and Magnetism Assessment (BEMA). Two different curricula were…
Neural network (NN) model chemistries (MCs) promise to facilitate the accurate exploration of chemical space and simulation of large reactive systems. One important path to improving these models is to add layers of physical detail,…
We present an overview of the capabilities that the International Linear Collider (ILC) offers for precision measurements that probe the Standard Model. First, we discuss the improvements that the ILC will make in precision electroweak…
Analyzing and evaluating students' progress in any learning environment is stressful and time consuming if done using traditional analysis methods. This is further exasperated by the increasing number of students due to the shift of focus…
The fast-growing demands in using Large Language Models (LLMs) to tackle complex multi-step data science tasks create an emergent need for accurate benchmarking. There are two major gaps in existing benchmarks: (i) the lack of standardized,…
Over the last five years, the McGill University Office of Science Education (OSE) has partnered with faculty members from the Department of Physics to form an education research group with the aim of charting the progression of student…
Current measurements of the low and high redshift Universe are in tension if we restrict ourselves to the standard six parameter model of flat $\Lambda$CDM. This tension has two parts. First, the Planck satellite data suggest a higher…
The ability of a classifier to take on new information and classes by evolving the classifier without it having to be fully retrained is known as incremental learning. Incremental learning has been successfully applied to many…
Recent developments in machine learning (ML) techniques present a promising new analysis method for high-speed imaging in astroparticle physics experiments, for example with imaging atmospheric Cherenkov telescopes (IACTs). In particular,…
Interactive Machine Learning (IML) is an iterative learning process that tightly couples a human with a machine learner, which is widely used by researchers and practitioners to effectively solve a wide variety of real-world application…
Inverse Distance Weighted models (IDW) have been widely used for predicting and modeling multidimensional space in multimodal industrial processes. However, the more complex the structure of multidimensional space, the lower the performance…
Although deep learning approaches have stood out in recent years due to their state-of-the-art results, they continue to suffer from catastrophic forgetting, a dramatic decrease in overall performance when training with new classes added…
In many real-life tasks of application of supervised learning approaches, all the training data are not available at the same time. The examples are lifelong image classification or recognition of environmental objects during interaction of…
Class-imbalance is one of the major challenges in real world datasets, where a few classes (called majority classes) constitute much more data samples than the rest (called minority classes). Learning deep neural networks using such…
MAGIC, 17 meters of diameter, is the world's largest single dish Imaging Atmospheric Cherenkov Telescope, and reaches in the analysis the lowest energy threshold (60 GeV) among the VHE gamma detectors. Completed in September 2004, MAGIC…
The proposed ICAL experiment at INO aims to identify the neutrino mass hierarchy from observations of atmospheric neutrinos, and help improve the precision on the atmospheric neutrino mixing parameters. While the design of ICAL is primarily…
Most modern neural networks for classification fail to take into account the concept of the unknown. Trained neural networks are usually tested in an unrealistic scenario with only examples from a closed set of known classes. In an attempt…