Related papers: A learning by confusion approach to characterize p…

The computation of bounce action in a phase transition involves solving partial differential equations, inherently introducing non-negligible numerical uncertainty. Deriving characteristic temperatures and properties of this transition…

This paper studies the large-scale subspace clustering (LSSC) problem with million data points. Many popular subspace clustering methods cannot directly handle the LSSC problem although they have been considered as state-of-the-art methods…

Continual learning (CL) has emerged as a pivotal paradigm to enable large language models (LLMs) to dynamically adapt to evolving knowledge and sequential tasks while mitigating catastrophic forgetting-a critical limitation of the static…

The theory of first order density-driven phase transitions with frustration due to the long range Coulomb (LRC) interaction develop on paper I of this series is applied to the following physical systems: i) the low density electron gas ii)…

Continual learning (CL) enables animals to learn new tasks without erasing prior knowledge. CL in artificial neural networks (NNs) is challenging due to catastrophic forgetting, where new learning degrades performance on older tasks. While…

We propose a novel deep layer cascade (LC) method to improve the accuracy and speed of semantic segmentation. Unlike the conventional model cascade (MC) that is composed of multiple independent models, LC treats a single deep model as a…

Most continual learning (CL) algorithms have focused on tackling the stability-plasticity dilemma, that is, the challenge of preventing the forgetting of previous tasks while learning new ones. However, they have overlooked the impact of…

Quantum phase transitions have been shown to be highly beneficial for quantum sensing, owing to diverging quantum Fisher information close to criticality. In this work we consider a periodically modulated Lipkin-Meshkov-Glick model to show…

Controller design faces a trade-off between robustness and performance, and the reliability of linear controllers has caused many practitioners to focus on the former. However, there is renewed interest in improving system performance to…

We study the phase diagram of a system of $2\times2\times2$ hard cubes on a three dimensional cubic lattice. Using Monte Carlo simulations, we show that the system exhibits four different phases as the density of cubes is increased:…

Large Language Models (LLMs) have demonstrated efficacy in various linguistic applications, including question answering and controlled text generation. However, studies into their ability to switch between opposite styles of responses in…

We present a binary classifier based on neural networks to detect gapped quantum phases. By considering the errors on top of a suitable reference state describing the gapped phase, we show that a neural network trained on the errors can…

Machine learning-based classifiers are commonly evaluated by metrics like accuracy, but deeper analysis is required to understand their strengths and weaknesses. MLMC is a visual exploration tool that tackles the challenge of multi-label…

Classifiers often learn to be biased corresponding to the class-imbalanced dataset, especially under the semi-supervised learning (SSL) set. While previous work tries to appropriately re-balance the classifiers by subtracting a…

Task Free online continual learning (TF-CL) is a challenging problem where the model incrementally learns tasks without explicit task information. Although training with entire data from the past, present as well as future is considered as…

The detection of phase transitions is a fundamental challenge in condensed matter physics, traditionally addressed through analytical methods and direct numerical simulations. In recent years, machine learning techniques have emerged as…

Class probabilities predicted by most multiclass classifiers are uncalibrated, often tending towards over-confidence. With neural networks, calibration can be improved by temperature scaling, a method to learn a single corrective…

Federated Continual Learning (FCL) leverages inter-client collaboration to balance new knowledge acquisition and prior knowledge retention in non-stationary data. However, existing batch-based FCL methods lack adaptability to streaming…

Clinical diagnosis requires sequential evidence acquisition under uncertainty. However, most Large Language Model (LLM) based diagnostic systems assume fully observed patient information and therefore do not explicitly model how clinical…

Common cross-validation (CV) methods like k-fold cross-validation or Monte-Carlo cross-validation estimate the predictive performance of a learner by repeatedly training it on a large portion of the given data and testing on the remaining…