arXiv research

Physics-informed WNO learns PDE solutions without labeled data.

3D convolutional neural networks are difficult to train because they are parameter-expensive and data-hungry. To solve these problems we propose a simple technique for learning 3D convolutional kernels efficiently requiring less training data. We achieve this by factorizing the 3D kernel along the temporal dimension, r…

Optical co-processor speeds up neural network training.

Automatic summarisation is a popular approach to reduce a document to its main arguments. Recent research in the area has focused on neural approaches to summarisation, which can be very data-hungry. However, few large datasets exist and none for the traditionally popular domain of scientific publications, which opens …

Novel framework proves fast RL convergence in continuous spaces.

In this paper, we show that popular Generative Adversarial Networks (GANs) exacerbate biases along the axes of gender and skin tone when given a skewed distribution of face-shots. While practitioners celebrate synthetic data generation using GANs as an economical way to augment data for training data-hungry machine lea…

In recent years, supervised machine learning models have demonstrated tremendous success in a variety of application domains. Despite the promising results, these successful models are data hungry and their performance relies heavily on the size of training data. However, in many healthcare applications it is difficult…

Deep neural networks are data hungry models and thus face difficulties when attempting to train on small text datasets. Transfer learning is a potential solution but their effectiveness in the text domain is not as explored as in areas such as image analysis. In this paper, we study the problem of transfer learning for…

Transformer learns long-term dependencies from real-world data.

SQS uses quantum kernels to improve credit scoring with fewer data points.

The need for labour intensive pixel-wise annotation is a major limitation of many fully supervised learning methods for segmenting bioimages that can contain numerous object instances with thin separations. In this paper, we introduce a deep convolutional neural network for microscopy image segmentation. Annotation iss…

While deep learning has achieved remarkable results on various applications, it is usually data hungry and struggles to learn over non-stationary data stream. To solve these two limits, the deep learning model should not only be able to learn from a few of data, but also incrementally learn new concepts from data strea…

Generative models in molecular design tend to be richly parameterized, data-hungry neural models, as they must create complex structured objects as outputs. Estimating such models from data may be challenging due to the lack of sufficient training data. In this paper, we propose a surprisingly effective self-training a…

Proposes a synthesis algorithm using Conformal Prediction for improved Deep Learning performance.

MDNs offer a data-efficient alternative to diffusion and flow models for multimodal scientific learning.

Question classification (QC) is the primary step of the Question Answering (QA) system. Question Classification (QC) system classifies the questions in particular classes so that Question Answering (QA) System can provide correct answers for the questions. Our system categorizes the factoid type questions asked in natu…

In modern computer science education, massive open online courses (MOOCs) log thousands of hours of data about how students solve coding challenges. Being so rich in data, these platforms have garnered the interest of the machine learning community, with many new algorithms attempting to autonomously provide feedback t…

A new ML method speeds up PDE simulations without needing classical training.

In recent years, deep learning models have shown great potential in source code modeling and analysis. Generally, deep learning-based approaches are problem-specific and data-hungry. A challenging issue of these approaches is that they require training from starch for a different related problem. In this work, we propo…

PropEn uses matching to create a larger dataset for efficient design optimization.

Study proposes a new method for deep portfolio optimization using residual factors.

Study reduces memory needs for active learning with enriched queries.

New method improves Bayesian model selection for neural dynamics.

Supervised machine learning based state-of-the-art computer vision techniques are in general data hungry and pose the challenges of not having adequate computing resources and of high costs involved in human labeling efforts. Training data subset selection and active learning techniques have been proposed as possible s…

BSA-TNP improves NP scalability and accuracy for spatiotemporal data.

Generative AI models improve clinical trial data by generating survival outcomes.

Develops a Bayesian framework for symbolic regression of scientific expressions.

New analysis shows transfer learning can significantly reduce sample size for complex models.

Propagates adversarial robustness in federated learning.

SWIFT learns intrinsic rewards from LLM hidden states for efficient best-of-N sampling.

This paper explores emerging methods for estimating variable importance in machine learning.

Recently, self-supervised learning has proved to be effective to learn representations of events suitable for temporal segmentation in image sequences, where events are understood as sets of temporally adjacent images that are semantically perceived as a whole. However, although this approach does not require expensive…

This paper proposes an unsupervised learning method to solve heat equations on chips.

Unified framework for blending ML and mechanistic models in dynamical systems.

Adaptive batch size schedules improve language model training efficiency and generalization.

ECG-DelNet uses neural networks to accurately delineate ECGs, even with low-quality data.