Related papers: Using Rule-Based Labels for Weak Supervised Learni…

Transfer learning improves the performance of deep learning models by initializing them with parameters pre-trained on larger datasets. Intuitively, transfer learning is more effective when pre-training is on the in-domain datasets. A…

Training a Convolutional Neural Network (CNN) for semantic segmentation typically requires to collect a large amount of accurate pixel-level annotations, a hard and expensive task. In contrast, simple image tags are easier to gather. With…

Predicting molecular properties (e.g., atomization energy) is an essential issue in quantum chemistry, which could speed up much research progress, such as drug designing and substance discovery. Traditional studies based on density…

Neural networks are promising tools for high-throughput and accurate transmission electron microscopy (TEM) analysis of nanomaterials, but are known to generalize poorly on data that is "out-of-distribution" from their training data. Given…

Transfer learning has emerged as a powerful methodology for adapting pre-trained deep neural networks on image recognition tasks to new domains. This process consists of taking a neural network pre-trained on a large feature-rich source…

In this work we propose approaches to effectively transfer knowledge from weakly labeled web audio data. We first describe a convolutional neural network (CNN) based framework for sound event detection and classification using weakly…

Unconstrained video recognition and Deep Convolution Network (DCN) are two active topics in computer vision recently. In this work, we apply DCNs as frame-based recognizers for video recognition. Our preliminary studies, however, show that…

Chemists in search of structure-property relationships face great challenges due to limited high quality, concordant datasets. Machine learning (ML) has significantly advanced predictive capabilities in chemical sciences, but these modern…

GNNs and chemical fingerprints are the predominant approaches to representing molecules for property prediction. However, in NLP, transformers have become the de-facto standard for representation learning thanks to their strong downstream…

We present a novel framework for chemical learning based on Competitive Dimerization Networks (CDNs) - systems in which multiple molecular species, e.g. proteins or DNA/RNA oligomers, reversibly bind to form dimers. We show that these…

Machine learning has become successful in solving wireless interference management problems. Different kinds of deep neural networks (DNNs) have been trained to accomplish key tasks such as power control, beamforming and admission control.…

Recent deep networks are capable of memorizing the entire data even when the labels are completely random. To overcome the overfitting on corrupted labels, we propose a novel technique of learning another neural network, called MentorNet,…

Convolutional Neural Networks (CNNs) do not have a predictable recognition behavior with respect to the input resolution change. This prevents the feasibility of deployment on different input image resolutions for a specific model. To…

A Hyperspectral image contains much more number of channels as compared to a RGB image, hence containing more information about entities within the image. The convolutional neural network (CNN) and the Multi-Layer Perceptron (MLP) have been…

Advancements in neural machinery have led to a wide range of algorithmic solutions for molecular property prediction. Two classes of models in particular have yielded promising results: neural networks applied to computed molecular…

The extraction of interactions between chemicals and proteins from several biomedical articles is important in many fields of biomedical research such as drug development and prediction of drug side effects. Several natural language…

Labeled data used for training activity recognition classifiers are usually limited in terms of size and diversity. Thus, the learned model may not generalize well when used in real-world use cases. Semi-supervised learning augments labeled…

In the context of supervised statistical learning, it is typically assumed that the training set comes from the same distribution that draws the test samples. When this is not the case, the behavior of the learned model is unpredictable and…

Deep learning based image segmentation has achieved the state-of-the-art performance in many medical applications such as lesion quantification, organ detection, etc. However, most of the methods rely on supervised learning, which require a…

Convolutional neural networks (CNNs) are extensively beneficial for medical image processing. Medical images are plentiful, but there is a lack of annotated data. Transfer learning is used to solve the problem of lack of labeled data and…