At IBM Research, we are exploring new solutions for a range of health care challenges. One such challenge is emergency room (ER) overcrowding, which can lead to long wait times for treatment. Patients who use the ER for non-emergency situations are more likely to return to the ER multiple times (Poole et al. 2016), further contributing to overcrowding. Identifying those patients who are likely to return to the ER may enable hospitals to intervene to ensure access to necessary care outside the ER and potentially alleviate overcrowding. My team at IBM Research-China took on this challenge.

Gripping something with your hand is one of the first things you learn to do as an infant, but it's far from a simple task, and only gets more complex and variable as you grow up. This complexity makes it difficult for machines to teach themselves to do, but researchers at Elon Musk and Sam Altman-backed OpenAI have created a system that not only holds and manipulates objects much like a human does, but developed these behaviors all on its own. Many robots and robotic hands are already proficient at certain grips or movements -- a robot in a factory can wield a bolt gun even more dexterously than a person. But the software that lets that robot do that task so well is likely to be hand-written and extremely specific to the application. You couldn't for example, give it a pencil and ask it to write.

This is part 3 in a series. Part 1 is here and Part 2 is here. To announce Google's AutoML, Google CEO Sundar Pichai wrote, "Today, designing neural nets is extremely time intensive, and requires an expertise that limits its use to a smaller community of scientists and engineers. That's why we've created an approach called AutoML, showing that it's possible for neural nets to design neural nets. We hope AutoML will take an ability that a few PhDs have today and will make it possible in three to five years for hundreds of thousands of developers to design new neural nets for their particular needs."

Some argue that a key component of human intelligence is our ability to reason about objects and their relations (e.g. This enables us, for example, to build rich compositional models of physics (how objects or particles interact) and intuitive theories of causation (what causes what) [3]. For artificial systems, these tasks remain a challenge. Most sophisticated pattern recognition models, e.g. based on Convolutional Neural Networks (CNNs) or Recurrent Neural Networks (RNNs), lack a certain relational inductive bias [4]; impeding their ability to generalize well on problems with inherent compositional structure. In our recent ICML (2018) paper: Neural Relational Inference for Interacting Systems, we explore a class of models named Graph Neural Networks (GNNs) that reflect the inherent structure of the problem domain in their model architecture¹.

"With joyous gambols gay and still array, no longer when he'twas, while in his day at first to pass in all delightful ways around him, charming, and of all his days." Don't worry: You haven't accidentally clicked on pre-Digital Trends, by mistake. This is part of a Shakespearean sonnet created by deep learning artificial intelligence -- and, shockingly, it's actually pretty good. The bot was created by researchers at IBM Research Australia. Trained on around 26,000 real sonnets, it mimics the iambic pentameter and rhyming pattern of the poems most famously written by ol' Bill Shakespeare himself.

Physicians at the University of California, Irvine and UCI Health System have launched the UCI Center for Artificial Intelligence in Diagnostic Medicine, which seeks to advance patient care, improve health outcomes and lower costs by leveraging machine learning technology in all areas of healthcare. Led by Peter D. Chang, MD, and Daniel S. Chow, MD, neuroradiologists in the Department of Radiological Sciences, UCI School of Medicine, the center is a cross-specialty initiative with a specific focus on developing and applying deep learning neural networks to healthcare applications, such as diagnostics, disease prediction and therapy planning. "Our goal is to empower health care providers, researchers and patients through the use of artificial intelligence in healthcare," said Chang. The Center for Artificial Intelligence in Diagnostic Medicine will provide a central research core that enables all UCI faculty, physicians and researchers, to collaborate on translating AI-based concepts into clinical tools to improve individual and population health. "The center will develop machine learning tools that can be implemented for routine clinical use today," said Chow.

Tensor Processing Unit (TPU), an application specific integrated circuit, designed by Google for accelerating machine learning workloads, is going to be available at the edge. These tailor-made chips complement Cloud TPUs by inferencing machine learning models deployed at the edge. Google has also announced Cloud IoT Edge, an edge computing platform that extends Google Cloud's data processing and machine learning to edge devices. Google is the latest entrant into the edge computing market. The key competitors of Google Cloud – Amazon and Microsoft – have a comprehensive edge computing strategy.

A new system has vastly improved robots' abilities to grip, slide and manipulate objects with almost the same ease as a human hand. OpenAI, a robotics research group that's backed by tech titans including Elon Musk and Peter Thiel, trained the robot hand to be able to manipulate objects using a sophisticated system called Dactyl. Researchers let a computer simulation of a robot hand learn new movements via trial and error, which served as the dataset for the actual robot hand - meaning it required zero human intervention. Researchers at OpenAI first trained a virtual hand, powered by a neural network, to learn how to manipulate a cube using various grasps. Via simulations, the virtual hand could try out thousands of different poses in just a few seconds.

For every business that's using AI to do something groundbreaking, there are more that, well, aren't. Adobe's 2018 "Digital Trends" report found that while only 15 percent of companies are currently using AI, 31 percent have it on the agenda for the next year -- but that rising demand doesn't necessarily correlate with a rise in high-quality AI products. Much of it is fluff. I learned this the hard way in 2016. We were looking to license a model for a very specific task, and it led to horror.

Since its humble beginnings at the turn of the millennium, deep learning, as both a scientific discipline and an industry, has come a long way. From smartphone assistants to pattern recognition software, security solutions, and other applications, deep learning is becoming a multi-billion dollar business poised for great growth over the few next years. However, for deep learning agents to reach their full potential, they have to "learn" how to learn on their own. Herein lies the whole difference between supervised and unsupervised deep learning. The power and appeal of deep learning is all about their ability to recognize different types of patterns like faces, voices, objects, images, and codes.