Image super-resolution (SR) is an underdetermined inverse problem, where a large number of plausible high-resolution images can explain the same downsampled image. Most current single image SR methods use empirical risk minimisation, often with a pixel-wise mean squared error (MSE) loss. However, the outputs from such methods tend to be blurry, over-smoothed and generally appear implausible. A more desirable approach would employ Maximum a Posteriori (MAP) inference, preferring solutions that always have a high probability under the image prior, and thus appear more plausible. Direct MAP estimation for SR is non-trivial, as it requires us to build a model for the image prior from samples. Furthermore, MAP inference is often performed via optimisation-based iterative algorithms which don't compare well with the efficiency of neural-network-based alternatives. Here we introduce new methods for amortised MAP inference whereby we calculate the MAP estimate directly using a convolutional neural network. We first introduce a novel neural network architecture that performs a projection to the affine subspace of valid SR solutions ensuring that the high resolution output of the network is always consistent with the low resolution input. We show that, using this architecture, the amortised MAP inference problem reduces to minimising the cross-entropy between two distributions, similar to training generative models. We propose three methods to solve this optimisation problem: (1) Generative Adversarial Networks (GAN) (2) denoiser-guided SR which backpropagates gradient-estimates from denoising to train the network, and (3) a baseline method using a maximum-likelihood-trained image prior. Our experiments show that the GAN based approach performs best on real image data. Lastly, we establish a connection between GANs and amortised variational inference as in e.g. variational autoencoders.

Mobile robots are increasingly being employed for performing complex tasks in dynamic environments. Reinforcement learning (RL) methods are recognized to be promising for specifying such tasks in a relatively simple manner. However, the strong dependency between the learning method and the task to learn is a well-known problem that restricts practical implementations of RL in robotics, often requiring major modifications of parameters and adding other techniques for each particular task. In this paper we present a practical core implementation of RL which enables the learning process for multiple robotic tasks with minimal per-task tuning or none. Based on value iteration methods, this implementation includes a novel approach for action selection, called Q-biased softmax regression (QBIASSR), which avoids poor performance of the learning process when the robot reaches new unexplored states. Our approach takes advantage of the structure of the state space by attending the physical variables involved (e.g., distances to obstacles, X,Y,{\theta} pose, etc.), thus experienced sets of states may favor the decision-making process of unexplored or rarely-explored states. This improvement has a relevant role in reducing the tuning of the algorithm for particular tasks. Experiments with real and simulated robots, performed with the software framework also introduced here, show that our implementation is effectively able to learn different robotic tasks without tuning the learning method. Results also suggest that the combination of true online SARSA({\lambda}) with QBIASSR can outperform the existing RL core algorithms in low-dimensional robotic tasks.

Recently, I did a session at local user group in Ljubljana, Slovenija, where I introduced the new algorithms that are available with MicrosoftML package for Microsoft R Server 9.0.3. For dataset, I have used two from (still currently) running sessions from Kaggle. In the last part, I did image detection and prediction of MNIST dataset and compared the performance and accuracy between. MNIST Handwritten digit database is available here. Starting off with rxNeuralNet, we have to build a NET# model or Neural network to work it's way.

Artificial intelligence "will soon destroy millions of human jobs," warned Gerd Leonhard of The Futures Agency, a speaker at Tata Communications' CEO Summit 2016 earlier this month. "In five years most companies will have armies of very cheap, very powerful machines, connected to a smart cloud, and they will be able to accomplish so many routine processes," the Zurich-based futurist said. "Some 25 years from now machines, through cognitive computing and using vast amounts of data from humans, will do all of that kind of work." A select cluster of 60 business leaders attended the two-day conference at Coworth Park in Ascot, which both educated and provoked. It addressed concerns but also flagged up potential opportunities.

Step counting apps might be not only a waste of time but a dangerous one, according to one expert. The fitness apps might be doing more harm than good because they don't work but force people to focus on ambitious goals that they will never reach, according to a leading computer scientist. "Very few" of the roughly 165,000 healthcare apps are actually based on any scientific evidence, said Dr Greg Hager, from Johns Hopkins University in the US. But they have been downloaded more than a billion times by people looking to improve their health. The giant human-like robot bears a striking resemblance to the military robots starring in the movie'Avatar' and is claimed as a world first by its creators from a South Korean robotic company Waseda University's saxophonist robot WAS-5, developed by professor Atsuo Takanishi and Kaptain Rock playing one string light saber guitar perform jam session A man looks at an exhibit entitled'Mimus' a giant industrial robot which has been reprogrammed to interact with humans during a photocall at the new Design Museum in South Kensington, London Electrification Guru Dr. Wolfgang Ziebart talks about the electric Jaguar I-PACE concept SUV before it was unveiled before the Los Angeles Auto Show in Los Angeles, California, U.S The Jaguar I-PACE Concept car is the start of a new era for Jaguar.

A new tool shows just how much of people's personal information is made public on Facebook for anyone to see. The utility, which calls itself Stalkscan, claims to offer all the "'public' info Facebook doesn't let you see". It combs through everything that has been made public by a person – which will probably have happened involuntarily – and collects all of it in one place. It does that using only the unique identifier that each profile has. That means that it's possible to do it for yourself, and see what parts of your online life you may have left exposed, but also that anyone in the world can do it to you, too.

Imagine a pill that knew if you were ill enough to need drugs, and wouldn't release chemicals if it thought you didn't need it. That's the breakthrough that's been made at Eindhoven University in the Netherlands by a team of researchers ld by Maarten Merkx. The team has harnessed the power of DNA itself to form an organic computer that performs crude calculations on the state of your health. When you get ill, or suffer from a chronic condition, doctors normally prescribe drugs to help you get better, but this is based on a set of generic guidelines. The idea is that a smart pill will be able to offer specific doses, tailored to your needs, reducing the risk of side effects and waste.

Google has launched its Fact Check tag in three more countries, as it steps up its efforts to combat fake news. The label will now appear in the expand story box in Google News search results and the Google News and Weather app in Argentina, Brazil and Mexico. The feature first launched in the US last October, ahead of the Presidential election, and has since been rolled out in France and Germany. The giant human-like robot bears a striking resemblance to the military robots starring in the movie'Avatar' and is claimed as a world first by its creators from a South Korean robotic company Waseda University's saxophonist robot WAS-5, developed by professor Atsuo Takanishi and Kaptain Rock playing one string light saber guitar perform jam session A man looks at an exhibit entitled'Mimus' a giant industrial robot which has been reprogrammed to interact with humans during a photocall at the new Design Museum in South Kensington, London Electrification Guru Dr. Wolfgang Ziebart talks about the electric Jaguar I-PACE concept SUV before it was unveiled before the Los Angeles Auto Show in Los Angeles, California, U.S The Jaguar I-PACE Concept car is the start of a new era for Jaguar. Japan's On-Art Corp's CEO Kazuya Kanemaru poses with his company's eight metre tall dinosaur-shaped mechanical suit robot'TRX03' and other robots during a demonstration in Tokyo, Japan Japan's On-Art Corp's eight metre tall dinosaur-shaped mechanical suit robot'TRX03' performs during its unveiling in Tokyo, Japan Singulato Motors co-founder and CEO Shen Haiyin poses in his company's concept car Tigercar P0 at a workshop in Beijing, China A picture shows Singulato Motors' concept car Tigercar P0 at a workshop in Beijing, China Connected company president Shigeki Tomoyama addresses a press briefing as he elaborates on Toyota's "connected strategy" in Tokyo.

King's College Hospital has created a free virtual reality app designed to ease patients' fears ahead of MRI machine scans. My MRI at King's, which has primarily been built for children, is essentially a simple audiovisual guide that walks patients through the events that will happen on the day. It can be used at home ahead of a scan, and is viewable on a virtual reality headset, such as Google Cardboard. However, users can also explore it on a phone or tablet. The giant human-like robot bears a striking resemblance to the military robots starring in the movie'Avatar' and is claimed as a world first by its creators from a South Korean robotic company Waseda University's saxophonist robot WAS-5, developed by professor Atsuo Takanishi and Kaptain Rock playing one string light saber guitar perform jam session A man looks at an exhibit entitled'Mimus' a giant industrial robot which has been reprogrammed to interact with humans during a photocall at the new Design Museum in South Kensington, London Electrification Guru Dr. Wolfgang Ziebart talks about the electric Jaguar I-PACE concept SUV before it was unveiled before the Los Angeles Auto Show in Los Angeles, California, U.S The Jaguar I-PACE Concept car is the start of a new era for Jaguar.

It is about to become much harder to find streams of football matches and downloads of music, under new rules. Search giant Google and Bing will hide illegally pirated content and instead show them links to places to get that same video or music legally, by paying. That is after the two companies launched a crackdown on piracy websites and signed up to a new code that is intended to protect users safety by stopping them from visiting disreputable sites. Keeping people from visiting illegal sites will keep them safe from the kind of spam, advertising and malware that is often served alongside the streams or downloads, according to those backing the code. The giant human-like robot bears a striking resemblance to the military robots starring in the movie'Avatar' and is claimed as a world first by its creators from a South Korean robotic company Waseda University's saxophonist robot WAS-5, developed by professor Atsuo Takanishi and Kaptain Rock playing one string light saber guitar perform jam session A man looks at an exhibit entitled'Mimus' a giant industrial robot which has been reprogrammed to interact with humans during a photocall at the new Design Museum in South Kensington, London Electrification Guru Dr. Wolfgang Ziebart talks about the electric Jaguar I-PACE concept SUV before it was unveiled before the Los Angeles Auto Show in Los Angeles, California, U.S The Jaguar I-PACE Concept car is the start of a new era for Jaguar.