Robert Jones was driving home through the pretty town of Todmorden, in West Yorkshire, when he noticed the fuel light flashing on the dashboard of his car. He had just a few miles to find a petrol station, which was cutting things rather fine, but thankfully his GPS seemed to have found a short cut – sending him on a narrow winding path up the side of the valley. Robert followed the machine's instructions, but as he drove, the road got steeper and narrower. After a couple of miles, it turned into a dirt track, but Robert wasn't fazed. After all, he thought, he had "no reason not to trust the satnav".

The aim of this project is to detect the rooftop of buildings to determine the available area at different locations and to identify the most suitable ones for solar energy application such as solar PV using Neural Networks and satellite imagery. The Inria Aerial Image Labeling addresses a core topic in remote sensing: the automatic pixelwise labeling of aerial imagery. The first approach to organize the data was to make MX files, one per image, each file contain the 100 images with their respective mask. In order to do that a function mxFileCreator was build. The net selected for this project was at Wolfram Neural Net Repository for Semantic Segmentation.

Until a few years ago the work of data scientists was isolated and mattered primarily for research and/or R&D purposes. The industry has been extremely thankful for the contributions of these clever individuals but we need them now in the mainstream! This need is creating a huge demand in the industry and it's radically transforming the hunt for big data and machine learning talent. Fast forward 2018 and today every CEO, CIO, CDO, CMO is seeking answers to questions that don't exist yet. Typical questions in the minds of the leaders could be...

A fleet of robotic jellyfish has been designed to monitor delicate ecosystems, including coral reefs. The underwater drones were invented by engineers at Florida Atlantic University and are driven by rings of hydraulic tentacles. The robots can squeeze through tight holes without causing damage. One expert praised the design but warned that the man-made jellyfish might be eaten by turtles. The flexible, 20cm-wide bots are modelled on the appearance of the moon jellyfish during its larval stage.

From smartphone assistants to image recognition and translation, machine learning already helps us in our everyday lives. But it can also help us to tackle some of the world's most challenging physical problems -- such as energy consumption. Large-scale commercial and industrial systems like data centres consume a lot of energy, and while much has been done to stem the growth of energy use, there remains a lot more to do given the world's increasing need for computing power. Reducing energy usage has been a major focus for us over the past 10 years: we have built our own super-efficient servers at Google, invented more efficient ways to cool our data centres and invested heavily in green energy sources, with the goal of being powered 100 percent by renewable energy. Compared to five years ago, we now get around 3.5 times the computing power out of the same amount of energy, and we continue to make many improvements each year.

Elon Musk is one of the world's most prominent business figures. His latest headline-grabber is the announcement of the first paying passenger his SpaceX venture plans to fly around the Moon. There are also his extraordinary pioneering achievements include creating online payment platform PayPal, running electric car maker Tesla, as well as SpaceX. His innovative and wide-ranging interests include solar energy and artificial intelligence, and he has promised the Hyperloop, a super-high speed magnetic train travel, in an underground tube and he has designs on Mars. But this year, things seem to have turned sour for the tech entrepreneur.

We introduce a dynamic artificial neural network-based (ANN) adaptive inference process, which learns temporal predictive models of dynamical systems. We term the process REPRISE, a REtrospective and PRospective Inference SchEme. REPRISE infers the unobservable contextual state that best explains its recently encountered sensorimotor experiences as well as accompanying, context-dependent temporal predictive models retrospectively. Meanwhile, it executes prospective inference, optimizing upcoming motor activities in a goal-directed manner. In a first implementation, a recurrent neural network (RNN) is trained to learn a temporal forward model, which predicts the sensorimotor contingencies of different simulated dynamic vehicles. The RNN is augmented with contextual neurons, which enable the compact encoding of distinct, but related sensorimotor dynamics. We show that REPRISE is able to concurrently learn to separate and approximate the encountered sensorimotor dynamics. Moreover, we show that REPRISE can exploit the learned model to induce goal-directed, model-predictive control, that is, approximate active inference: Given a goal state, the system imagines a motor command sequence optimizing it with the prospective objective to minimize the distance to a given goal. Meanwhile, the system evaluates the encountered sensorimotor contingencies retrospectively, adapting its neural hidden states for maintaining model coherence. The RNN activities thus continuously imagine the upcoming future and reflect on the recent past, optimizing both, hidden state and motor activities. In conclusion, the combination of temporal predictive structures with modulatory, generative encodings offers a way to develop compact event codes, which selectively activate particular types of sensorimotor event-specific dynamics.

In this work, a new approach for Sun tracking systems is presented. Due to the current system limitations regarding costs and operational problems, a new approach based on low cost, computer vision open hardware and deep learning has been developed. The preliminary tests carried out successfully in Plataforma solar de Almeria (PSA), reveal the great potential and show the new approach as a good alternative to traditional systems. The proposed approach can provide key variables for the Sun tracking system control like cloud movements prediction, block and shadow detection, atmospheric attenuation or measures of concentrated solar radiation, which can improve the control strategies of the system and therefore the system performance.

The U.S. solar revolution has been a terrific boon to customer choice, the economy and climate policy planning. But solar panels alone can't achieve the full value of solar generation or the aggressive goals of greenhouse gas reductions. Moreover, solar developers face a wave of changes that is challenging their continued growth. Energy markets are shifting, supply chains are becoming more competitive, electric and solar rates are changing and customers' interest in controlling their energy destiny is increasing. As a result, the economics of distributed solar projects are getting skinnier and riskier for the solar developer.

A futuristic, solar-powered yacht which can cruise the globe without stopping to refuel has been unveiled by its Swiss designers. The electric SolarImpact yacht is longer than a blue whale and topped with enough solar panels to cover a regulation-size tennis court. The boat sleeps ten people, on top of accommodation for the small crew, and is loaded with artificial intelligence that allows it to be driven by a single person. Pictured is an artist's impression of the all-electric SolarImpact yacht. The yacht is the result of five years of research by Zurich firm SolarImpact Yacht AG, which has not revealed an expected price or release date for its design.