This work explores maximum likelihood optimization of neural networks through hypernetworks. A hypernetwork initializes the weights of another network, which in turn can be employed for typical functional tasks such as regression and classification. We optimize hypernetworks to directly maximize the conditional likelihood of target variables given input. Using this approach we obtain competitive empirical results on regression and classification benchmarks.

We focus on wind power modeling using machine learning techniques. We show on real data provided by the wind energy company Ma{\"i}a Eolis, that parametric models, even following closely the physical equation relating wind production to wind speed are outperformed by intelligent learning algorithms. In particular, the CART-Bagging algorithm gives very stable and promising results. Besides, as a step towards forecast, we quantify the impact of using deteriorated wind measures on the performances. We show also on this application that the default methodology to select a subset of predictors provided in the standard random forest package can be refined, especially when there exists among the predictors one variable which has a major impact.

In this work we explore the use of metric index structures, which accelerate nearest neighbor queries, in the scenario where we need to interleave insertions and queries during deployment. This use-case is inspired by a real-life need in malware analysis triage, and is surprisingly understudied. Existing literature tends to either focus on only final query efficiency, often does not support incremental insertion, or does not support arbitrary distance metrics. We modify and improve three algorithms to support our scenario of incremental insertion and querying with arbitrary metrics, and evaluate them on multiple datasets and distance metrics while varying the value of $k$ for the desired number of nearest neighbors. In doing so we determine that our improved Vantage-Point tree of Minimum-Variance performs best for this scenario.

Generative Adversarial Networks (GANs) excel at creating realistic images with complex models for which maximum likelihood is infeasible. However, the convergence of GAN training has still not been proved. We propose a two time-scale update rule (TTUR) for training GANs with stochastic gradient descent on arbitrary GAN loss functions. TTUR has an individual learning rate for both the discriminator and the generator. Using the theory of stochastic approximation, we prove that the TTUR converges under mild assumptions to a stationary local Nash equilibrium. The convergence carries over to the popular Adam optimization, for which we prove that it follows the dynamics of a heavy ball with friction and thus prefers flat minima in the objective landscape. For the evaluation of the performance of GANs at image generation, we introduce the "Fr\'echet Inception Distance" (FID) which captures the similarity of generated images to real ones better than the Inception Score. In experiments, TTUR improves learning for DCGANs and Improved Wasserstein GANs (WGAN-GP) outperforming conventional GAN training on CelebA, CIFAR-10, SVHN, LSUN Bedrooms, and the One Billion Word Benchmark.

Consensus formation is investigated for multi-agent systems in which agents' beliefs are both vague and uncertain. Vagueness is represented by a third truth state meaning \emph{borderline}. This is combined with a probabilistic model of uncertainty. A belief combination operator is then proposed which exploits borderline truth values to enable agents with conflicting beliefs to reach a compromise. A number of simulation experiments are carried out in which agents apply this operator in pairwise interactions, under the bounded confidence restriction that the two agents' beliefs must be sufficiently consistent with each other before agreement can be reached. As well as studying the consensus operator in isolation we also investigate scenarios in which agents are influenced either directly or indirectly by the state of the world. For the former we conduct simulations which combine consensus formation with belief updating based on evidence. For the latter we investigate the effect of assuming that the closer an agent's beliefs are to the truth the more visible they are in the consensus building process. In all cases applying the consensus operators results in the population converging to a single shared belief which is both crisp and certain. Furthermore, simulations which combine consensus formation with evidential updating converge faster to a shared opinion which is closer to the actual state of the world than those in which beliefs are only changed as a result of directly receiving new evidence. Finally, if agent interactions are guided by belief quality measured as similarity to the true state of the world, then applying the consensus operator alone results in the population converging to a high quality shared belief.

A sad cycle has overtaken the gadget business. It starts this week at CES, tech's biggest annual convention, where inventors compete to connect the most random things to the Internet. This year's "smart" stuff includes pillows, air fresheners and even toilets. A few months from now we'll see different headlines: That smart thing you bought is actually spying on you. Sooner or later, the story gets worse: Your smart thing has been hacked.

Drones used to attack two Russian military bases in Syria were so high-tech they were designed to offset jamming technology, were capable of launching precision strikes and could not have been made without foreign assistance, the defence ministry in Moscow has said . The ministry's drone department head Gen Alexander Novikov said the drones used in the weekend's raids differed from the rudimentary craft earlier used by rebels in Syria. The attacks required satellite navigation data that are not available on the internet, complex engineering works and elaborate tests, Gen Novikov said. Analysts say the drones present the biggest military challenge so far to Russia's role in Syria'The creation of drones of such class is impossible in makeshift conditions,' Novikov said. 'Their development and use requires the involvement of experts with special training in the countries that manufacture and use drones.' The ministry said Saturday's raid on the Hemeimeem air base in the province of Lattakia and Russia's naval facility in the port of Tartus involved 13 drones.

Ocado plans to wheel out Star Wars-style C-3PO humanoid robots at its warehouses as early as 2025. The'SecondHands' robots will pass spanners and move ladders to workers using artificial intelligence and speech recognition. Ocado has already built a prototype, marking the latest move from the online grocery specialist to cut its reliance on human workers. Ocado plans to wheel out Star Wars-style C-3PO humanoid robots at its warehouses as early as 2025. The'SecondHands' androids will pass spanners and move ladders to workers using artificial intelligence and speech recognition.

MBN Solutions have been engaged by a world renowned Fortune 500 Consulting client operating across Europe, North America, Asia and the Middle East, to recruit an ambitious and creative (Senior) Data Scientist to help develop and lead on a range of Big Data, Data Science and Advanced Analytical projects. You will be part of a highly reputable Data Science and Machine Learning team within the Analytics and Insight practice, working closely with a range of Blue Chip clients to derive insight and opportunities from their existing systems and to utilize advanced data driven software algorithms and technology to improve and optimize their businesses. For more info send your CV to [email protected] OR press apply!

Following Jeremy Corbyn and Theresa May's heated debate over the state of the NHS during yesterday's PMQs, some experts believe that the use of artificial intelligence could hold the key to saving the UK's NHS. AI, in particular cognitive agents that can hold a human-like conversation with the patients, is the key to rescuing the NHS and giving patients and taxpayers the level of care that they expect. Indeed, David Champeaux, director, Global Cognitive Health Solutions at IPsoft, the digital labour company suggests that AI may be the "miracle pill" for the NHS. See also: British public'would use AI' to relieve NHS pressures "The NHS is at risk of a winter of discontent," said Champeaux. "Our healthcare system is buckling under immense pressure resulting from growing demand and capacity constraints. One way to address the staff shortages is to train digital employees equipped with artificial intelligence (AI) to assist doctors and nurses and relieve them from the high volume of routine and administrative tasks and free up more time for patients."