Scientists are working on developing an AI system that can analyze your breath and detect diseases. Researcher Dr. Andrea Soltoggio and her team are developing an artificial intelligence system that could save tons of lives down the road: an AI system that could detect diseases, even in its early stages, including terminal illnesses. And it could all be as simple as having the AI system analyze your breath, according to the Smithsonian. A person's breath contains hundreds of volatile organic compounds, some of which can indicate certain diseases in people. Machines called gas-chromatography mass-spectrometers, also known as GC-MS, can be used to detect these compounds. The idea, then, is to use these GC-MS machines to figure out if someone has compounds in their breath that could be indicative of serious illnesses.

Addressing the "memory wall" and pushing for a new architectural solution enabling highly efficient performance computing for rapidly growing artificial intelligence (AI) applications are key areas of focus for Leti, the French technology research institute of CEA Tech. Speaking to EE Times at Leti's annual innovation conference here, Leti CEO Emmanuel Sabonnadière said there needs to be a highly integrated and holistic approach to moving AI from software and the cloud into an embedded chip at the edge. "We really need something at the edge, with a different architecture that is more than just CMOS, but is structurally integrated into the system, and enable autonomy from the cloud -- for example for autonomous vehicles, you need independence of the cloud as much as possible," Sabonnadière said. He commented on the Qualcomm bid for NXP being a key pointer as a driver for more computing at the edge. "Why do you think Qualcomm is buying NXP? It's for the sensing, and to put digital behind the sensing."

From the critical, like law enforcement, healthcare, and humanitarian aid, to the mundane, like dating and shopping, artificial intelligence (AI) seems to be the answer to all our problems. AI is a catch-all phrase for a wide-ranging set of technologies most of which apply learning techniques from statistics to find patterns in large sets of data and make predictions based on those patterns. It seems like there are meetings every other week, organised by representatives from industry, government, academia, and civil society to address the perils of AI and formulate solutions to harness its potential. But who is driving the regulatory agenda and what do they stand to gain? This question needs to be answered because letting industry needs drive the AI agenda presents real risks.

I'm not worried about artificial intelligence, I'm terrified of human stupidity. The debate about technology and its role in society that we need to have is being used to deceive citizens and scare them about the future so they accept to submit to politicians who cannot nor will protect us from the challenges of robotization. However, there are many studies that tell us that in 50 years the vast majority of work will be done by robots. We have lived the fallacies of dystopian estimates for decades. I always explain to my students that, if we believed the fifty-year-forward studies of the past, it has been seventeen years since we have run out of water, oil, and jobs. Fifty-year estimates always suffer from the same mistakes.

The drone makes a conspicuous racket as it lifts off on a mission to capture images of the reservoir below. The sight and sound of this strange device stirs interest among locals as they make their way to and from the town of Kasungu in central Malawi. It takes a matter of minutes for a small crowd to form. A few yards away, Patrick Kalonde is wading through grass and mud. Patrick, an intern at Unicef working on humanitarian uses of drones, is carrying a plastic container and a ladle and is looking for mosquito larvae. The contrast between high-tech drones and low-tech "bucket-and-spade" science, metres apart, could not be starker – yet both are equally important to the success of our new project to map where mosquitoes breed. Kasungu, a small town at the base of the picturesque Kasungu Mountain, is the centre of Africa's first humanitarian drone testing corridor. Set up by Unicef in 2017 with support from the Malawi government, the corridor is an 80km-wide area for flying and testing drones to help the local people. Keen to dispel the reputation that drones are only useful for destruction, the Unicef corridor promotes "drones for good".

The automatic reconstruction of three-dimensional particle tracks from Active Target Time Projection Chambers data can be a challenging task, especially in the presence of noise. In this article, we propose a nonparametric algorithm that is based on the idea of clustering point triplets instead of the original points. We define an appropriate distance measure on point triplets and then apply a single-link hierarchical clustering on the triplets. Compared to parametric approaches like RANSAC or the Hough transform, the new algorithm has the advantage of potentially finding trajectories even of shapes that are not known beforehand. This feature is particularly important in low-energy nuclear physics experiments with AT operating inside a magnetic field. The algorithm has been validated using data from experiments performed with the Active Target Time Projection Chamber (AT-TPC) at the National Superconducting Cyclotron Laboratory (NSCL).The results demonstrate the capability of the algorithm to identify and isolate particle tracks that describe non-analytical trajectories. For curved tracks, the vertex detection recall was 86% and the precision 94%. For straight tracks, the vertex detection recall was 96% and the precision 98%. In the case of a test set containing only straight linear tracks, the algorithm performed better than an iterative Hough transform. Keywords: Time Projection Chambers, Active Target, Pattern Recognition, Clustering 1. Introduction One of the present aims of modern low-energy nuclear physics is to provide a more complete understanding about the behavior of subatomic matter under large isospin (i.e.

In recent years, state-of-the-art methods in computer vision have utilized increasingly deep convolutional neural network architectures (CNNs), with some of the most successful models employing hundreds or even thousands of layers. A variety of pathologies such as vanishing/exploding gradients make training such deep networks challenging. While residual connections and batch normalization do enable training at these depths, it has remained unclear whether such specialized architecture designs are truly necessary to train deep CNNs. In this work, we demonstrate that it is possible to train vanilla CNNs with ten thousand layers or more simply by using an appropriate initialization scheme. We derive this initialization scheme theoretically by developing a mean field theory for signal propagation and by characterizing the conditions for dynamical isometry, the equilibration of singular values of the input-output Jacobian matrix. These conditions require that the convolution operator be an orthogonal transformation in the sense that it is norm-preserving. We present an algorithm for generating such random initial orthogonal convolution kernels and demonstrate empirically that they enable efficient training of extremely deep architectures.

In this paper we study the real time deployment of deep learning algorithms in low resource computational environments. As the use case, we compare the accuracy and speed of neural networks for smile detection using different neural network architectures and their system level implementation on NVidia Jetson embedded platform. We also propose an asynchronous multithreading scheme for parallelizing the pipeline. Within this framework, we experimentally compare thirteen widely used network topologies. The experiments show that low complexity architectures can achieve almost equal performance as larger ones, with a fraction of computation required.

C. Robustness to external noise The sound samples used in all experiments are already recorded under real-world conditions in an office environment. We took care that people in the office are not talking, but background noise like typing on a keyboard and people walking around are clearly identifiable on the sample data. In addition, there is a significant amount of ego noise coming from the robot's servos. Hence, the results depicted in the previous Sections VA and V-B already involve a realistic amount of noise. However, in order to make more precise statements about robustness to noise, we also perform experiments where we simulate an environment with other external sound sources at varying levels. Therefore, we use six randomly selected samples from different background noises including traffic, people speaking, airport, etc.

We present an end-to-end approach that takes unstructured textual input and generates structured output compliant with a given vocabulary. Inspired by recent successes in neural machine translation, we treat the triples within a given knowledge graph as an independent graph language and propose an encoder-decoder framework with an attention mechanism that leverages knowledge graph embeddings. Our model learns the mapping from natural language text to triple representation in the form of subject-predicate-object using the selected knowledge graph vocabulary. Experiments on three different data sets show that we achieve competitive F1-Measures over the baselines using our simple yet effective approach. A demo video is included.