Today, many decisions made in medicine are based upon prior observations, training, memory, and flawed studies. With artificial intelligence (AI)- based tools, doctors will have powerful tools to make better diagnoses and treatment decisions based upon analysis of real-world clinical data and use of strong science. The promise of AI is that medicine becomes more of a science than an artform. Guidelines promulgated by specialty societies for physicians' use in daily practice are often based upon flimsy evidence and flawed studies. In a 2009 study, Duke University researchers found that only 11 percent of the recommendations from the American College of Cardiology and American Heart Association were based upon evidence from multiple randomized trials or meta-analyses – the gold standards for study design .

BigML is bringing the third edition of our Summer School in Machine Learning to Valencia, Spain. We will hold a two-day course for advanced undergraduates as well as graduate students, and industry practitioners seeking a quick, practical, and hands-on introduction to Machine Learning.

A huge batch of letters penned by visionary British cryptographer Alan Turning has been found at the University of Manchester. Professor Jim Miles was tidying a storeroom when he discovered the correspondence in an old filing cabinet. At first he assumed the orange folder, which had Turing's name on the front, had simply been re-used by another member of staff. But a closer look revealed 148 documents, including a letter sent by GCHQ, a draft version of a BBC radio programme about artificial intelligence, and invitations to lecture at some top universities in America. Turing worked at the University of Manchester from 1948, first as a Reader in the mathematics department and later as the Deputy Director of the Computing Laboratory.

In Texas, a child asks an Amazon Echo to "play dollhouse with me and get me a dollhouse?" In England, the words "OK Google, what is the Whopper burger?" in a Burger King advertisement trigger Google Home smart speakers to start spouting descriptions of the burgers. And sometime soon, your car may choose the best price for maintenance or an electric charge, as well as driving itself to the appointment. Welcome to the new world where intelligent machines, rather than people, make more and more decisions about what to buy, at what price, and complete the transactions without a middleman over a blockchain distributed ledger. This will mean massive new markets for everything from home supplies ordered via "smart speakers" such as Amazon Echo to electricity ordered by smart thermostats to replacement parts and raw materials purchased by manufacturing robots or optimisation algorithms for cyber physical systems of machines.

Robots are taking our jobs. Almost everything you can learn in our current education system will be automated soon. Supply chains are in upheaval as production moves closer to the consumer and products are made by individual robots rather than rows of underpaid workers. Artificial intelligence and machine learning are threatening thousands of white-collar jobs. As manufacturing shifts away from the traditional Asian hubs, shipping lines now suffer from massive overcapacity that will probably stay for a long time. We are aware of all of these trends.

A reliable, accurate, and affordable positioning service is highly required in wireless networks. In this paper, the novel Message Passing Hybrid Localization (MPHL) algorithm is proposed to solve the problem of cooperative distributed localization using distance and direction estimates. This hybrid approach combines two sensing modalities to reduce the uncertainty in localizing the network nodes. A statistical model is formulated for the problem, and approximate minimum mean square error (MMSE) estimates of the node locations are computed. The proposed MPHL is a distributed algorithm based on belief propagation (BP) and Markov chain Monte Carlo (MCMC) sampling. It improves the identifiability of the localization problem and reduces its sensitivity to the anchor node geometry, compared to distance-only or direction-only localization techniques. For example, the unknown location of a node can be found if it has only a single neighbor; and a whole network can be localized using only a single anchor node. Numerical results are presented showing that the average localization error is significantly reduced in almost every simulation scenario, about 50% in most cases, compared to the competing algorithms.

Compressed sensing (CS) is a sampling theory that allows reconstruction of sparse (or compressible) signals from an incomplete number of measurements, using of a sensing mechanism implemented by an appropriate projection matrix. The CS theory is based on random Gaussian projection matrices, which satisfy recovery guarantees with high probability; however, sparse ternary {0, -1, +1} projections are more suitable for hardware implementation. In this paper, we present a deep learning approach to obtain very sparse ternary projections for compressed sensing. Our deep learning architecture jointly learns a pair of a projection matrix and a reconstruction operator in an end-to-end fashion. The experimental results on real images demonstrate the effectiveness of the proposed approach compared to state-of-the-art methods, with significant advantage in terms of complexity.

With the availability of large databases and recent improvements in deep learning methodology, the performance of AI systems is reaching or even exceeding the human level on an increasing number of complex tasks. Impressive examples of this development can be found in domains such as image classification, sentiment analysis, speech understanding or strategic game playing. However, because of their nested non-linear structure, these highly successful machine learning and artificial intelligence models are usually applied in a black box manner, i.e., no information is provided about what exactly makes them arrive at their predictions. Since this lack of transparency can be a major drawback, e.g., in medical applications, the development of methods for visualizing, explaining and interpreting deep learning models has recently attracted increasing attention. This paper summarizes recent developments in this field and makes a plea for more interpretability in artificial intelligence. Furthermore, it presents two approaches to explaining predictions of deep learning models, one method which computes the sensitivity of the prediction with respect to changes in the input and one approach which meaningfully decomposes the decision in terms of the input variables. These methods are evaluated on three classification tasks.

We discuss memory models which are based on tensor decompositions using latent representations of entities and events. We show how episodic memory and semantic memory can be realized and discuss how new memory traces can be generated from sensory input: Existing memories are the basis for perception and new memories are generated via perception. We relate our mathematical approach to the hippocam-pal memory indexing theory. We describe the first detailed mathematical models for the complete processing pipeline from sensory input and its semantic decoding, i.e., perception, to the formation of episodic and semantic memories and their declarative semantic decodings. Our main hypothesis is that perception includes an active semantic decoding process, which relies on latent representations of entities and predicates, and that episodic and semantic memories depend on the same decoding process. We contribute to the debate between the leading memory consolidation theories, i.e., the standard consolidation theory (SCT) and the multiple trace theory (MTT). The latter is closely related to the complementary learning systems (CLS) framework. In particular, we show explicitly how episodic memory can teach the neocortex to form a semantic memory, which is a core issue in MTT and CLS.

Humans take advantage of real world symmetries for various tasks, yet capturing their superb symmetry perception mechanism with a computational model remains elusive. Motivated by a new study demonstrating the extremely high inter-person accuracy of human perceived symmetries in the wild, we have constructed the first deep-learning neural network for reflection and rotation symmetry detection (Sym-NET), trained on photos from MS-COCO (Microsoft-Common Object in COntext) dataset with nearly 11K consistent symmetry-labels from more than 400 human observers. We employ novel methods to convert discrete human labels into symmetry heatmaps, capture symmetry densely in an image and quantitatively evaluate Sym-NET against multiple existing computer vision algorithms. On CVPR 2013 symmetry competition testsets and unseen MS-COCO photos, Sym-NET significantly outperforms all other competitors. Beyond mathematically well-defined symmetries on a plane, Sym-NET demonstrates abilities to identify viewpoint-varied 3D symmetries, partially occluded symmetrical objects, and symmetries at a semantic level.