The use of deep learning, machine learning and other artificial intelligence approaches in healthcare is rapidly increasing. Over the next two days, Health Data Management highlights companies bringing a variety of approaches to the use of AI in the industry. Today's list includes 25 companies; yesterday, we featured 15 vendors with artificial intelligence offerings in healthcare.

In the past 10 years, the best-performing artificial-intelligence systems -- such as the speech recognizers on smartphones or Google's latest automatic translator -- have resulted from a technique called "deep learning." Deep learning is in fact a new name for an approach to artificial intelligence called neural networks, which have been going in and out of fashion for more than 70 years. Neural networks were first proposed in 1944 by Warren McCullough and Walter Pitts, two University of Chicago researchers who moved to MIT in 1952 as founding members of what's sometimes called the first cognitive science department. Neural nets were a major area of research in both neuroscience and computer science until 1969, when, according to computer science lore, they were killed off by the MIT mathematicians Marvin Minsky and Seymour Papert, who a year later would become co-directors of the new MIT Artificial Intelligence Laboratory. The technique then enjoyed a resurgence in the 1980s, fell into eclipse again in the first decade of the new century, and has returned like gangbusters in the second, fueled largely by the increased processing power of graphics chips. "There's this idea that ideas in science are a bit like epidemics of viruses," says Tomas Poggio, the Eugene McDermott Professor of Brain and Cognitive Sciences at MIT, an investigator at MIT's McGovern Institute for Brain Research, and director of MIT's Center for Brains, Minds, and Machines.

This is Deep Learning, Machine Learning, and Data Science Prerequisites: The Numpy Stack in Python. One question or concern I get a lot is that people want to learn deep learning and data science, so they take these courses, but they get left behind because they don't know enough about the Numpy stack in order to turn those concepts into code. Even if I write the code in full, if you don't know Numpy, then it's still very hard to read. This course is designed to remove that obstacle - to show you how to do things in the Numpy stack that are frequently needed in deep learning and data science. This forms the basis for everything else.

October 06, 2016 Posted by Sujith Ravi, Staff Research Scientist, Google Research Recently, there have been significant advances in Machine Learning that enable computer systems to solve complex real-world problems. One of those advances is Google's large scale, graph-based machine learning platform, built by the Expander team in Google Research. A technology that is behind many of the Google products and features you may use everyday, graph-based machine learning is a powerful tool that can be used to power useful features such as reminders in Inbox and smart messaging in Allo, or used in conjunction with deep neural networks to power the latest image recognition system in Google Photos. Learning with Minimal Supervision Much of the recent success in deep learning, and machine learning in general, can be attributed to models that demonstrate high predictive capacity when trained on large amounts of labeled data -- often millions of training examples. This is commonly referred to as "supervised learning" since it requires supervision, in the form of labeled data, to train the machine learning systems.

Powerful machine-learning methods have taken the tech world by storm in recent years, vastly improving voice and image recognition, machine translation, and many other things. Now these techniques are poised to upend countless other industries, including the world of finance. But progress may be stymied by a significant problem: it's often impossible to explain how these "deep learning" algorithms reach a decision (see "The Dark Secret at the Heart of AI"). Adam Wenchel, vice president of machine learning and data innovation at Capital One, says the company would like to use deep learning for all sorts of functions, including deciding who is granted a credit card. But it cannot do that because the law requires companies to explain the reason for any such decision to a prospective customer.

Hailed as giving birth to the "fourth industrial revolution," artificial intelligence (AI) is being developed in yet another field -- cancer diagnosis. Medical and research institutions are developing AI technology to diagnose cancer using "deep learning." One example is the Japan Society of Pathology, which began developing AI technology in February at 29 institutions, including The University of Tokyo Hospital and Kyushu University Hospital, to reduce the load on the country's overworked pathologists. The system being developed by the society compiles images of tissue samples from patients at the participating institutions into a database, where AI then decides if the case is cancer or not, learning from its past successes and failures, a method called deep learning. Pathology is a field of medicine where doctors examine samples of body tissues using a microscope and decide whether the patient has a disease, such as cancer.

Associating image regions with text queries has been recently explored as a new way to bridge visual and linguistic representations. A few pioneering approaches have been proposed based on recurrent neural language models trained generatively (e.g., generating captions), but achieving somewhat limited localization accuracy. To better address natural-language-based visual entity localization, we propose a discriminative approach. We formulate a discriminative bimodal neural network (DBNet), which can be trained by a classifier with extensive use of negative samples. Our training objective encourages better localization on single images, incorporates text phrases in a broad range, and properly pairs image regions with text phrases into positive and negative examples. Experiments on the Visual Genome dataset demonstrate the proposed DBNet significantly outperforms previous state-of-the-art methods both for localization on single images and for detection on multiple images. We we also establish an evaluation protocol for natural-language visual detection.

We propose a neural machine translation architecture that models the surrounding text in addition to the source sentence. These models lead to better performance, both in terms of general translation quality and pronoun prediction, when trained on small corpora, although this improvement largely disappears when trained with a larger corpus. We also discover that attention-based neural machine translation is well suited for pronoun prediction and compares favorably with other approaches that were specifically designed for this task.

Abstract-- Deep learning is an established framework for learning hierarchical data representations. While compute power is in abundance, one of the main challenges in applying this framework to robotic grasping has been obtaining the amount of data needed to learn these representations, and structuring the data to the task at hand. Among contemporary approaches in the literature, we highlight key properties that have encouraged the use of deep learning techniques, and in this paper, detail our experience in developing a simulator for collecting cylindrical precision grasps of a multi-fingered dexterous robotic hand. Grasping and manipulation are important and challenging problems in Robotics. For grasp synthesis or pre-grasp planning, there are currently two dominant approaches: analytical and data-driven (i.e. Analytic approaches typically optimize some measure of force-or form-closure [22] [6], and provide guarantees on grasp properties such as: disturbance rejection, dexterity, equilibrium, and stability [23]. These models often require full knowledge of the object geometry, surface friction, and other intrinsic characteristics.

This paper presents a theoretical, idealized model of the thinking process with the following characteristics: 1) the model can produce complex thought sequences and can be generalized to new inputs, 2) it can receive and maintain input information indefinitely for the generation of thoughts and later use, and 3) it supports learning while executing. The crux of the model lies within the concept of internal consistency, or the generated thoughts should always be consistent with the inputs from which they are created. Its merit, apart from the capability to generate new creative thoughts from an internal mechanism, depends on the potential to help training to generalize better. This is consequently enabled by separating input information into several parts to be handled by different processing components with a focus mechanism to fetch information for each. This modularized view with the focus binds the model with the computationally capable Turing machines. And as a final remark, this paper constructively shows that the computational complexity of the model is at least, if not surpass, that of a universal Turing machine.