Related papers: Chainer: A Deep Learning Framework for Acceleratin…
Traditional neuroimage analysis pipelines involve computationally intensive, time-consuming optimization steps, and thus, do not scale well to large cohort studies with thousands or tens of thousands of individuals. In this work we propose…
fastai is a deep learning library which provides practitioners with high-level components that can quickly and easily provide state-of-the-art results in standard deep learning domains, and provides researchers with low-level components…
High-energy physics experiments require fast and efficient methods for reconstructing the tracks of charged particles. The commonly used algorithms are sequential, and the required CPU power increases rapidly with the number of tracks.…
We propose a unified deep learning framework for the generation and analysis of driving scenario trajectories, and validate its effectiveness in a principled way. To model and generate scenarios of trajectories with different lengths, we…
Modern deep neural networks increasingly make use of features such as dynamic control flow, data structures and dynamic tensor shapes. Existing deep learning systems focus on optimizing and executing static neural networks which assume a…
Capsule Network is a promising concept in deep learning, yet its true potential is not fully realized thus far, providing sub-par performance on several key benchmark datasets with complex data. Drawing intuition from the success achieved…
Deep learning is increasingly attracting attention for processing big data. Existing frameworks for deep learning must be set up to specialized computer systems. Gaining sufficient computing resources therefore entails high costs of…
Deep learning has enabled ECG diagnostic models with strong performance in tasks such as arrhythmia classification and abnormality detection. However, accuracy alone is insufficient for clinical deployment because it does not explain why a…
Deep Neural Networks (DNNs) have become the de-facto standard in computer vision, as well as in many other pattern recognition tasks. A key drawback of DNNs is that the training phase can be very computationally expensive. Organizations or…
Sherpa is a hyperparameter optimization library for machine learning models. It is specifically designed for problems with computationally expensive, iterative function evaluations, such as the hyperparameter tuning of deep neural networks.…
Scaling up deep neural network capacity has been known as an effective approach to improving model quality for several different machine learning tasks. In many cases, increasing model capacity beyond the memory limit of a single…
The input data pipeline is an essential component of each machine learning (ML) training job. It is responsible for reading massive amounts of training data, processing batches of samples using complex transformations, and loading them onto…
Deep neural networks can struggle to learn continually in the face of non-stationarity. This phenomenon is known as loss of plasticity. In this paper, we identify underlying principles that lead to plastic algorithms. In particular, we…
Recent advancements in neural rendering technologies and their supporting devices have paved the way for immersive 3D experiences, significantly transforming human interaction with intelligent devices across diverse applications. However,…
To tackle interpretability in deep learning, we present a novel framework to jointly learn a predictive model and its associated interpretation model. The interpreter provides both local and global interpretability about the predictive…
The deep neural networks (DNNs) have been enormously successful in tasks that were hitherto in the human-only realm such as image recognition, and language translation. Owing to their success the DNNs are being explored for use in ever more…
Recent advances in artificial intelligence research have led to a profusion of studies that apply deep learning to problems in image analysis and natural language processing among others. Additionally, the availability of open-source…
Numerous deep learning architectures have been developed to accommodate the diversity of time series datasets across different domains. In this article, we survey common encoder and decoder designs used in both one-step-ahead and…
Today, more and more, it is necessary that most applications and documents developed in previous or current technologies to be accessible online on cloud-based infrastructures. That is why the migration of legacy systems including their…
Knowledge tracing---where a machine models the knowledge of a student as they interact with coursework---is a well established problem in computer supported education. Though effectively modeling student knowledge would have high…