My father, Richard Zobel, who has died aged 81, was a pioneering computer scientist at the University of Manchester, birthplace of "Baby", the world's first stored-program computer. He rode the wave of the information technology revolution, starting in the early 1960s on military flight simulators for the electronics and equipment company Sperry's – the valve analog computers they used ran so hot that he had to work in the cool of the night – and in later years recommending improvements to the distant early warning system (Dews) protecting Indian Ocean coastlines from tsunami, but it was his 40-year academic career that defined his professional life. Richard was born in Lewisham, south London, the son of Joan, a dressmaker, and Norman Zobel, a car mechanic, just before the outbreak of the second world war, and narrowly escaped early tragedy when a water tank came through the ceiling and landed on his bed during the blitz. He went to Colfe's school (then a grammar school) on a scholarship, and graduated in 1963 in electrical engineering from London University, sponsored on his sandwich course by Sperry Gyroscope, a UK arm of the US company, which had headquarters in Bracknell. He met Lesley Winks at Peggy Spencer's ballroom dancehall in Penge, and they married in 1964.

An asteroid has flown past Earth closer than any seen before. The tiny object, known as asteroid 2020 QG, came just 1,830 miles over the southern Indian Ocean on Sunday, the space agency said. As it did so, it was spotted by the Zwicky Transient Facility, a robotic camera that scans the sky in search of a variety of objects, from the smallest asteroids to the largest supernova. The asteroid 2020 QG is particularly small. It is about three to six meters across, scientists said, roughly the size of a large car.

Artificial intelligence has been vital in controlling the spread of the coronavirus in the Arabian Gulf, a health conference has been told. Technology has forecast the pandemic's development and informed residents when they have been in contact with infected individuals, the Riyadh Global Digital Health Summit heard. The summit was also told that the rapid growth in telemedicine – such as video or telephone consultations – is not likely to be reversed when the pandemic is over. However, experts cautioned that organisations were not doing enough to share vital data that could save lives and certain ethical concerns about the use of data had not been resolved. Dr Esam Al Wagait, director of Saudi Arabia's National Information Centre, said the Kingdom's artificial intelligence (AI) based Covid-19 Index had been crucial in forecasting the virus's spread locally, including which areas would be most heavily affected and how many people would fall ill.

This paper investigates the impact of changes in agents' beliefs coupled with dynamics in agents' meta-roles on the evolution of institutions. The study embeds agents' meta-roles in the BDI architecture. In this context, the study scrutinises the impact of cognitive dissonance in agents due to unfairness of institutions. To showcase our model, two historical long-distance trading societies, namely Armenian merchants of New-Julfa and the English East India Company are simulated. Results show how change in roles of agents coupled with specific institutional characteristics leads to changes of the rules in the system.

All famous machine learning algorithms that comprise both supervised and semi-supervised learning work well only under a common assumption: the training and test data follow the same distribution. When the distribution changes, most statistical models must be reconstructed from newly collected data, which for some applications can be costly or impossible to obtain. Therefore, it has become necessary to develop approaches that reduce the need and the effort to obtain new labeled samples by exploiting data that are available in related areas, and using these further across similar fields. This has given rise to a new machine learning framework known as transfer learning: a learning setting inspired by the capability of a human being to extrapolate knowledge across tasks to learn more efficiently. Despite a large amount of different transfer learning scenarios, the main objective of this survey is to provide an overview of the state-of-the-art theoretical results in a specific, and arguably the most popular, sub-field of transfer learning, called domain adaptation. In this sub-field, the data distribution is assumed to change across the training and the test data, while the learning task remains the same. We provide a first up-to-date description of existing results related to domain adaptation problem that cover learning bounds based on different statistical learning frameworks.

Neural networks achieve outstanding accuracy in classification and regression tasks. However, understanding their behavior still remains an open challenge that requires questions to be addressed on the robustness, explainability and reliability of predictions. We answer these questions by computing reachable sets of neural networks, i.e. sets of outputs resulting from continuous sets of inputs. We provide two efficient approaches that lead to over- and under-approximations of the reachable set. This principle is highly versatile, as we show. First, we analyze and enhance the robustness properties of both classifiers and regression models. This is in contrast to existing works, which only handle classification. Specifically, we verify (non-)robustness, propose a robust training procedure, and show that our approach outperforms adversarial attacks as well as state-of-the-art methods of verifying classifiers for non-norm bound perturbations. We also provide a technique of distinguishing between reliable and non-reliable predictions for unlabeled inputs, quantify the influence of each feature on a prediction, and compute a feature ranking.

We study two practically important cases of model based clustering using Gaussian Mixture Models: (1) when there is misspecification and (2) on high dimensional data, in the light of recent advances in Gradient Descent (GD) based optimization using Automatic Differentiation (AD). Our simulation studies show that EM has better clustering performance, measured by Adjusted Rand Index, compared to GD in cases of misspecification, whereas on high dimensional data GD outperforms EM. We observe that both with EM and GD there are many solutions with high likelihood but poor cluster interpretation. To address this problem we design a new penalty term for the likelihood based on the Kullback Leibler divergence between pairs of fitted components. Closed form expressions for the gradients of this penalized likelihood are difficult to derive but AD can be done effortlessly, illustrating the advantage of AD-based optimization. Extensions of this penalty for high dimensional data and for model selection are discussed. Numerical experiments on synthetic and real datasets demonstrate the efficacy of clustering using the proposed penalized likelihood approach.

Gradient-only and probabilistic line searches have recently reintroduced the ability to adaptively determine learning rates in dynamic mini-batch sub-sampled neural network training. However, stochastic line searches are still in their infancy and thus call for an ongoing investigation. We study the application of the Gradient-Only Line Search that is Inexact (GOLS-I) to automatically determine the learning rate schedule for a selection of popular neural network training algorithms, including NAG, Adagrad, Adadelta, Adam and LBFGS, with numerous shallow, deep and convolutional neural network architectures trained on different datasets with various loss functions. We find that GOLS-I's learning rate schedules are competitive with manually tuned learning rates, over seven optimization algorithms, three types of neural network architecture, 23 datasets and two loss functions. We demonstrate that algorithms, which include dominant momentum characteristics, are not well suited to be used with GOLS-I. However, we find GOLS-I to be effective in automatically determining learning rate schedules over 15 orders of magnitude, for most popular neural network training algorithms, effectively removing the need to tune the sensitive hyperparameters of learning rate schedules in neural network training.

Learn Computer Vision. Introduction course to Computer Vision with Python. Make Computer Vision Apps? Learn Computer Vision theory? Build a strong portfolio with Computer Vision & Image Processing Projects? Looking to add Computer Vision algorithms in your current software project ? Whatever be your motivation to learn Computer Vision, I can assure you that you’ve come to the right course. You get. Complete course with 1 hour of video tutorials, Source code for all examples in the course. What you'll learn. Use basic Computer Vision techniques. Do image processing. Build: Image Similarity app, Face Detection app and Object Detection app! Master Computer Vision! .

An important issue in clustering concerns the avoidance of false positives while searching for clusters. This work addressed this problem considering agglomerative methods, namely single, average, median, complete, centroid and Ward's approaches applied to unimodal and bimodal datasets obeying uniform, gaussian, exponential and power-law distributions. A model of clusters was also adopted, involving a higher density nucleus surrounded by a transition, followed by outliers. This paved the way to defining an objective means for identifying the clusters from dendrograms. The adopted model also allowed the relevance of the clusters to be quantified in terms of the height of their subtrees. The obtained results include the verification that many methods detect two clusters in unimodal data. The single-linkage method was found to be more resilient to false positives. Also, several methods detected clusters not corresponding directly to the nucleus. The possibility of identifying the type of distribution was also investigated.