Related papers: Improving Compound Activity Classification via Dee…
Transfer Learning enables Convolutional Neural Networks (CNN) to acquire knowledge from a source domain and transfer it to a target domain, where collecting large-scale annotated examples is time-consuming and expensive. Conventionally,…
Transfer learning for deep neural networks is the process of first training a base network on a source dataset, and then transferring the learned features (the network's weights) to a second network to be trained on a target dataset. This…
Being expensive and time-consuming to collect massive COVID-19 image samples to train deep classification models, transfer learning is a promising approach by transferring knowledge from the abundant typical pneumonia datasets for COVID-19…
Application of intelligent systems especially in smart homes and health-related topics has been drawing more attention in the last decades. Training Human Activity Recognition (HAR) models -- as a major module -- requires a fair amount of…
Transfer learning is widely used in deep neural network models when there are few labeled examples available. The common approach is to take a pre-trained network in a similar task and finetune the model parameters. This is usually done…
Sensor-based human activity recognition (HAR) has been an active research area, owing to its applications in smart environments, assisted living, fitness, healthcare, etc. Recently, deep learning based end-to-end training has resulted in…
Human activity recognition (HAR) research has increased in recent years due to its applications in mobile health monitoring, activity recognition, and patient rehabilitation. The typical approach is training a HAR classifier offline with…
Continual learning (CL) over non-stationary data streams remains one of the long-standing challenges in deep neural networks (DNNs) as they are prone to catastrophic forgetting. CL models can benefit from self-supervised pre-training as it…
Deep neural networks often suffer from a critical limitation known as catastrophic forgetting, where performance on past tasks degrades after learning new ones. This paper introduces a novel continual learning approach inspired by human…
The sensor-based human activity recognition (HAR) in mobile application scenarios is often confronted with sensor modalities variation and annotated data deficiency. Given this observation, we devised a graph-inspired deep learning approach…
Chemical representations derived from deep learning are emerging as a powerful tool in areas such as drug discovery and materials innovation. Currently, this methodology has three major limitations - the cost of representation generation,…
Deep learning methods are successfully used in applications pertaining to ubiquitous computing, health, and well-being. Specifically, the area of human activity recognition (HAR) is primarily transformed by the convolutional and recurrent…
Recently, machine learning (ML) has gained popularity in the early stages of drug discovery. This trend is unsurprising given the increasing volume of relevant experimental data and the continuous improvement of ML algorithms. However,…
Pre-training a deep neural network on the ImageNet dataset is a common practice for training deep learning models, and generally yields improved performance and faster training times. The technique of pre-training on one task and then…
In this paper, we empirically evaluate the utility of transfer and multi-task learning on a challenging semantic classification task: semantic interpretation of noun--noun compounds. Through a comprehensive series of experiments and…
Neural Architecture Search (NAS) methods have been shown to outperform hand-designed models and help to democratize AI. However, NAS methods often start from scratch with each new task, making them computationally expensive and limiting…
Accurate and robust drug response prediction is of utmost importance in precision medicine. Although many models have been developed to utilize the representations of drugs and cancer cell lines for predicting cancer drug responses (CDR),…
We present neural activation coding (NAC) as a novel approach for learning deep representations from unlabeled data for downstream applications. We argue that the deep encoder should maximize its nonlinear expressivity on the data for…
Detailed mobile sensing data from phones, watches, and fitness trackers offer an unparalleled opportunity to quantify and act upon previously unmeasurable behavioral changes in order to improve individual health and accelerate responses to…
In the domain of air traffic control (ATC) systems, efforts to train a practical automatic speech recognition (ASR) model always faces the problem of small training samples since the collection and annotation of speech samples are expert-…