Understanding and Improving Convolutional Neural Networks via Concatenated Rectified Linear Units

Article Abstract Recently, convolutional neural networks (CNNs) have been used as a powerful tool to solve many problems of machine learning and computer vision. In this paper, we aim to provide insight on the property of convolutional neural networks, as well as a generic method to improve the performance of many CNN architectures. Specifically, we […]

Automation and anxiety – Will smarter machines cause mass unemployment?

SITTING IN AN office in San Francisco, Igor Barani calls up some medical scans on his screen. He is the chief executive of Enlitic, one of a host of startups applying deep learning to medicine, starting with the analysis of images such as X-rays and CT scans. It is an obvious use of the technology. […]

How Artificial Intelligence Is Bringing Us Smarter Medicine

We are using intelligent machines for everything from self-driving cars to online searches. But how about leveraging artificial intelligence, or AI, to save lives? “A momentous change in health care is under way,” says Suchi Saria, an associate professor in computational biology at Johns Hopkins, with startups harnessing the recent explosion of electronic health data […]

50 Smartest Companies 2016

Our editors pick the 50 companies that best combine innovative technology with an effective business model. Read the full article at MIT Technology Review

Genetic Architect: Discovering Genomic Structure with Learned Neural Architectures

Article Abstract Each human genome is a 3 billion base pair set of encoding instructions. Decoding the genome using deep learning fundamentally differs from most tasks, as we do not know the full structure of the data and therefore cannot design architectures to suit it. As such, architectures that fit the structure of genomics should […]

Paging HAL: What Will Happen When Artificial Intelligence Comes to Radiology?

The myth of Hephaestus’ golden handmaidens illustrates mankind’s centuries-long fascination with artificial intelligence (AI). The god of the forge created his handmaidens, who could talk and perform even the most difficult tasks, to assist him in his labors, and many people have since speculated about the possible uses of AI and the forms it might […]

Eight technologies that could change healthcare beyond recognition

Smartphones, genome sequencing and wearable technology will bring benefits but also challenges to health and social care. Machine learning is a type of artificial intelligence that enables computers to learn without being explicitly programmed, meaning they can teach themselves to change when exposed to new data. New insights into big datasets Several businesses hope to […]

Thirteen Companies That Use Deep Learning To Produce Actionable Results

Our means for gathering data have largely outstripped our tools for analyzing that data. The result is a mountain of unstructured and largely inaccessible information gathered from social media, app permissions, website cookies and hardware and software service agreements. There’s gold in that mountain, but you need the right tools to get at it. For […]

ResNet in ResNet: Generalizing Residual Architectures

Article Abstract Residual networks (ResNets) have recently achieved state-of-the-art on challenging computer vision tasks. We introduce Resnet in Resnet (RiR): a deep dualstream architecture that generalizes ResNets and standard CNNs and is easily implemented with no computational overhead. RiR consistently improves performance over ResNets, outperforms architectures with similar amounts of augmentation on CIFAR-10, and establishes […]