Related papers: Improving Compound Activity Classification via Dee…

Deep neural networks (DNNs) are the de facto standard for essential use cases, such as image classification, computer vision, and natural language processing. As DNNs and datasets get larger, they require distributed training on…

Bayesian inference promises to ground and improve the performance of deep neural networks. It promises to be robust to overfitting, to simplify the training procedure and the space of hyperparameters, and to provide a calibrated measure of…

Despite the rapid and significant advancements in deep learning for Quantitative Structure-Activity Relationship (QSAR) models, the challenge of learning robust molecular representations that effectively generalize in real-world scenarios…

Learning representations of well-trained neural network models holds the promise to provide an understanding of the inner workings of those models. However, previous work has either faced limitations when processing larger networks or was…

Deep neural networks produce state-of-the-art results when trained on a large number of labeled examples but tend to overfit when small amounts of labeled examples are used for training. Creating a large number of labeled examples requires…

Breast cancer is a major global health issue that affects millions of women worldwide. Classification of breast cancer as early and accurately as possible is crucial for effective treatment and enhanced patient outcomes. Deep transfer…

In the realm of practical fine-grained visual classification applications rooted in deep learning, a common scenario involves training a model using a pre-existing dataset. Subsequently, a new dataset becomes available, prompting the desire…

Inductive transfer learning has had a big impact on computer vision and NLP domains but has not been used in the area of recommender systems. Even though there has been a large body of research on generating recommendations based on…

Machine learning approaches have become popular for molecular modeling tasks, including molecular force fields and properties prediction. Traditional supervised learning methods suffer from scarcity of labeled data for particular tasks,…

Fine-Grained Visual Categorization (FGVC) is a challenging topic in computer vision. It is a problem characterized by large intra-class differences and subtle inter-class differences. In this paper, we tackle this problem in a weakly…

Convolutional neural networks (CNNs) have achieved high performance in synthetic aperture radar (SAR) automatic target recognition (ATR). However, the performance of CNNs depends heavily on a large amount of training data. The insufficiency…

Random delays weaken the temporal correspondence between actions and subsequent state feedback, making it difficult for agents to identify the true propagation process of action effects. In cross-task scenarios, changes in task objectives…

Generalized Category Discovery is a crucial real-world task. Despite the improved performance on known categories, current methods perform poorly on novel categories. We attribute the poor performance to two reasons: biased knowledge…

Knowledge transfer impacts the performance of deep learning -- the state of the art for image classification tasks, including automated melanoma screening. Deep learning's greed for large amounts of training data poses a challenge for…

Transfer learning is widely used for training machine learning models. Here, we study the role of transfer learning for training fully convolutional networks (FCNs) for medical image segmentation. Our experiments show that although transfer…

Modern paradigms for robot imitation train expressive policy architectures on large amounts of human demonstration data. Yet performance on contact-rich, deformable-object, and long-horizon tasks plateau far below perfect execution, even…

Representation learning based on multi-task pretraining has become a powerful approach in many domains. In particular, task-aware representation learning aims to learn an optimal representation for a specific target task by sampling data…

Continual learning (CL) has been a critical topic in contemporary deep neural network applications, where higher levels of both forward and backward transfer are desirable for an effective CL performance. Existing CL strategies primarily…

Annotating training data for sequence tagging of texts is usually very time-consuming. Recent advances in transfer learning for natural language processing in conjunction with active learning open the possibility to significantly reduce the…

In the realm of deep learning, spatial attention mechanisms have emerged as a vital method for enhancing the performance of convolutional neural networks. However, these mechanisms possess inherent limitations that cannot be overlooked.…