Convolutional networks have enjoyed much success in many computer vision applications.
The convolution operation however has a significant weakness in that it only operates on a …

The well-designed structures in neural networks reflect the prior knowledge incorporated
into the models. However, though different models have various priors, we are used to …

In this paper, a neural architecture search (NAS) framework is proposed for 3D medical
image segmentation, to automatically optimize a neural architecture from a large design …

Recently, deep learning is one of the most popular techniques in artificial intelligence.
However, to construct a deep learning model, various components must be set up, including …

Backward locking and update locking are well-known sources of inefficiency in
backpropagation that prevent from concurrently updating layers. Several works have …

Deep neural networks successfully pervaded many applications domains and are
increasingly used in critical decision processes. Understanding their workings is desirable …

Automated machine learning (AutoML) methods improve upon existing models by
optimizing various aspects of their design. While present methods focus on hyperparameters …

We present a simplified computational rule for the back-propagation formulas for artificial
neural networks. In this work, we provide a generic two-step rule for the back-propagation …

In recent years, deep neural networks have revolutionized many application domains of
machine learning and are key components of many critical decision or predictive processes …

Object detection is a rapidly-evolving field with applications varying from medicine to self-
driving vehicles. As the performance of the deep learning algorithms grow exponentially …