Related papers: From Data Quality to Model Quality: an Exploratory…

The essence of deep learning is to exploit data to train a deep neural network (DNN) model. This work explores the reverse process of generating data from a model, attempting to reveal the relationship between the data and the model. We…

Data inherently possesses dual attributes: samples and targets. For targets, knowledge distillation has been widely employed to accelerate model convergence, primarily relying on teacher-generated soft target supervision. Conversely, recent…

Machine learning software, deep neural networks (DNN) software in particular, discerns valuable information from a large dataset, a set of data. Outcomes of such DNN programs are dependent on the quality of both learning programs and…

Software metrics offer a quantitative basis for predicting the software development process. In this way, software quality can be improved very easily. Software quality should be achieved to satisfy the customer with decreasing the software…

In order to introduce an integrated research information system, this will provide scientific institutions with the necessary information on research activities and research results in assured quality. Since data collection, duplication,…

Large-scale models are pretrained on massive web-crawled datasets containing documents of mixed quality, making data filtering essential. A popular method is Classifier-based Quality Filtering (CQF), which trains a binary classifier to…

Motion blur, out of focus, insufficient spatial resolution, lossy compression and many other factors can all cause an image to have poor quality. However, image quality is a largely ignored issue in traditional pattern recognition…

High-quality data is necessary for modern machine learning. However, the acquisition of such data is difficult due to noisy and ambiguous annotations of humans. The aggregation of such annotations to determine the label of an image leads to…

Label noise is common in large real-world datasets, and its presence harms the training process of deep neural networks. Although several works have focused on the training strategies to address this problem, there are few studies that…

Due to the over-emphasize of the quantity of data, the data quality has often been overlooked. However, not all training data points contribute equally to learning. In particular, if mislabeled, it might actively damage the performance of…

Model complexity is a fundamental problem in deep learning. In this paper we conduct a systematic overview of the latest studies on model complexity in deep learning. Model complexity of deep learning can be categorized into expressive…

Empirical and LLM-based research in model-driven engineering increasingly relies on datasets of software models, for instance, to train or evaluate machine learning techniques for modeling support. These datasets have a significant impact…

The efficacy of machine learning models is typically determined by computing their accuracy on test data sets. However, this may often be misleading, since the test data may not be representative of the problem that is being studied. With…

Deep learning (DL) defines a new data-driven programming paradigm where the internal system logic is largely shaped by the training data. The standard way of evaluating DL models is to examine their performance on a test dataset. The…

Deep Learning-based code generators have seen significant advancements in recent years. Tools such as GitHub Copilot are used by thousands of developers with the main promise of a boost in productivity. However, researchers have recently…

Uncertainty quantification in neural network promises to increase safety of AI systems, but it is not clear how performance might vary with the training set size. In this paper we evaluate seven uncertainty methods on Fashion MNIST and…

The quality of underlying training data is very crucial for building performant machine learning models with wider generalizabilty. However, current machine learning (ML) tools lack streamlined processes for improving the data quality. So,…

A systematic, comparative investigation into the effects of low-quality data reveals a stark spectrum of robustness across modern probabilistic models. We find that autoregressive language models, from token prediction to…

Transfer learning allows practitioners to recognize and apply knowledge learned in previous tasks (source task) to new tasks or new domains (target task), which share some commonality. The two important factors impacting the performance of…

Software quality assurance has been a heated topic for several decades. If factors that influence software quality can be identified, they may provide more insight for better software development management. More precise quality assurance…