22 papers · ranked by Valyu relevance
Nikita Moshkov, Botond Mathe, Attila Kertesz-Farkas, Reka Hollandi + 1 more
'Peter Horvath'] Recent advancements in deep learning have revolutionized the way microscopy images of cells are processed. Deep learning network architectures have a large number of parameters, thus, in order to reach high accuracy, they require a massive amount of annotated data. A common way of improving accuracy…
Nikita Moshkov, Botond Mathe, Attila Kertesz-Farkas, Reka Hollandi + 1 more
Recent advancements in deep learning have revolutionized the way microscopy images of cells are processed. Deep learning network architectures have a large number of parameters, thus, in order to reach high accuracy, they require massive amount of annotated data. A common way of improving accuracy builds on the…
Loris Cino, Cosimo Distante, Alessandro Martella, Pier Luigi Mazzeo + 1 more
Despite significant advancements in the automatic classification of skin lesions using artificial intelligence (AI) algorithms, skepticism among physicians persists. This reluctance is primarily due to the lack of transparency and explainability inherent in these models, which hinders their widespread acceptance in…
Haoyu Xiong, Xinchun Zhang, Leixin Yang, Yu Xiang + 2 more
'Arkaitz Zubiaga'] Test-time augmentation (TTA) is a well-established technique that involves aggregating transformed examples of test inputs during the inference stage. The goal is to enhance model performance and reduce the uncertainty of predictions. Despite its advantages of not requiring additional training or…
Ildoo Kim, Young-Hoon Kim, Sungwoong Kim
Data augmentation has been actively studied for robust neural networks. Most of the recent data augmentation methods focus on augmenting datasets during the training phase. At the testing phase, simple transformations are still widely used for test-time augmentation. This paper proposes a novel instance-level testtime…
Divya Shanmugam, Helen Lu, Swami Sankaranarayanan, John Guttag
A conformal classifier produces a set of predicted classes and provides a probabilistic guarantee that the set includes the true class. Unfortunately, it is often the case that conformal classifiers produce uninformatively large sets. In this work, we show that test-time augmentation (TTA)–a technique that introduces…
Peter B. R. Hartog, Fabian Krüger, Samuel Genheden, Igor V. Tetko
Stakeholders of machine learning models desire explainable artificial intelligence (XAI) to produce human-understandable and consistent interpretations. In computational toxicity, augmentation of text-based molecular representations has been used successfully for transfer learning on downstream tasks. Augmentations of…
Brian Kenji Iwana, Seiichi Uchida, Friedhelm Schwenker
In recent times, deep artificial neural networks have achieved many successes in pattern recognition. Part of this success can be attributed to the reliance on big data to increase generalization. However, in the field of time series recognition, many datasets are often very small. One method of addressing this problem…
Yusra A. Ameen, Dalia M. Badary, Ahmad Elbadry I. Abonnoor, Khaled F. Hussain + 1 more
'Khaled F. Hussain' 'Adel A. Sewisy'] Background Applying deep learning to digital histopathology is hindered by the scarcity of manually annotated datasets. While data augmentation can ameliorate this obstacle, its methods are far from standardized. Our aim was to systematically explore the effects of skipping data…
Brian Kenji Iwana, Seiichi Uchida
In recent times, deep artificial neural networks have achieved many successes in pattern recognition. Part of this success can be attributed to the reliance on big data to increase generalization. However, in the field of time series recognition, many datasets are often very small. One method of addressing this problem…
Qingsong Wen, Liang Sun, Fan Yang, Xiaomin Song + 3 more
'Xue Wang' 'Huan Xu'] Deep learning performs remarkably well on many time series analysis tasks recently. The superior performance of deep neural networks relies heavily on a large number of training data to avoid overfitting. However, the labeled data of many realworld time series applications may be limited such as…
Zijun Gao, Lingbo Li, Tianhua Xu
—Data Augmentation (DA) has become a critical approach in Time Series Classification (TSC), primarily for its capacity to expand training datasets, enhance model robustness, introduce diversity, and reduce overfitting. However, the current landscape of DA in TSC is plagued with fragmented literature reviews, nebulous…
Romain Ilbert, Thai V. Hoang, Zonghua Zhang
—Our study investigates the impact of data augmentation on the performance of multivariate time series models, focusing on datasets from the UCR archive. Despite the limited size of these datasets, we achieved classification accuracy improvements in 10 out of 13 datasets using the ROCKET and InceptionTime models. This…
Daniel Choi, Cordelia Yip, Andrew Choi, Junho Park
Synthetic augmentation can silently harm subject-disjoint EEG generalization. We propose trustgated augmentation (TGA), a control layer that scores synthetic windows with a teacher trained on real data for label consistency and confidence; only samples above a confidence quantile q are eligible. A fail-closed selector…
Jacob M. Williams, Ashok Samal, Matthew R. Johnson
Many signals, particularly of biological origin, suffer from a signal-to-noise ratio sufficiently low that it can be difficult to classify individual examples reliably, even with relatively sophisticated machine-learning techniques such as deep learning. In some cases, the noise can be high enough that it is even…
Vikram Sundar, Lucy Colwell
Machine learning models that predict which small molecule ligands bind a single protein target report high levels of accuracy for held-out test data. An important challenge is to extrapolate and make accurate predictions for new protein targets. Improvements in drug-target interaction (DTI) models that address this…
Authors not listed
Data augmentation can alleviate the limitations of small molecular datasets for generative deep learning, by ‘artificially inflating’ the number of instances available for training. SMILES enumeration – whereby multiple valid SMILES strings are used to represent the same molecules – has resulted particularly beneficial…
Paulina Kieliba, Danielle Clode, Roni O Maimon-Mor, Tamar R. Makin
From hand tools to cyborgs, humans have long been fascinated by the opportunities afforded by augmenting ourselves. Here, we studied how motor augmentation with an extra robotic thumb (the Third Thumb) impacts the biological hand representation in the brains of able-bodied people. Participants were tested on a variety…
Jakub Poziemski, Artur Yurkevych, Pawel Siedlecki
The advancement of computational methods in drug discovery, particularly through the use of machine learning (ML) and deep learning (DL), has significantly enhanced the precision of binding affinity predictions. Despite progress in computer-aided drug discovery (CADD) accurate prediction of binding affinity remains a…
Authors not listed
The ongoing threat of global warming necessitates a shift towards clean energy sources to meet rising demands while reducing carbon emissions. Polymer electrolyte fuel cells (PEFCs) represent a promising technology for both mobile and stationary applications but their poor operational lifetimes and frequent faults are…
Authors not listed
Active learning (AL) can significantly accelerate drug discovery by iteratively selecting informative molecules, reducing experimental workload. However, existing AL studies typically assume access to large datasets, an unrealistic scenario for most academic labs. Here, we investigate AL strategies tailored…
Esther Heid, Charles J. McGill, Florence H. Vermeire, William H. Green
Characterizing uncertainty in machine learning models has recently gained interest in the context of machine learning reliability, robustness, safety, and active learning. Here, we separate the total uncertainty into contributions from noise in the data (aleatoric) and shortcomings of the model (epistemic), further…