A commonly used strategy for improving optimization algorithms is to restart the algorithm when it is believed to be trapped in an inferior part of the search space. Building on the recent success of Bet-and-Run approaches for restarted local search solvers, we introduce an improved generic Bet-and-Run strategy. The goal is to obtain the best possible results within a given time budget t using a given black-box optimization algorithm. If no prior knowledge about problem features and algorithm behavior is available, the question about how to use the time budget most efficiently arises. We propose to first start k>=1 independent runs of the algorithm during an initialization budget t1=0 time units in doing so), and then continuing these runs for the remaining t3=t-t1-t2 time units. In previous Bet-and-Run strategies, the decision maker D=currentBest would simply select the run with the best- so-far results at negligible time. We propose using more advanced methods to discriminate between "good" and "bad" sample runs, with the goal of increasing the correlation of the chosen run with the a-posteriori best one. We test several different approaches, including neural networks trained or polynomials fitted on the current trace of the algorithm to predict which run may yield the best results if granted the remaining budget. We show with extensive experiments that this approach can yield better results than the previous methods, but also find that the currentBest method is a very reliable and robust baseline approach.

Ibrahim Diallo was fired from his job by the company's AI system, as managers scrambled to figure out the problem and watched him be escorted from the building. In what many are considering a grave warning of the potential consequences of AI in the workplace, a man was fired by his company's AI system. Worst of all, his human managers "stood helpless" throughout the firing process. Nobody had any real answers at first, and no human was able to keep the man from being escorted out of the building by security. Ibrahim Diallo, a programmer for a company in Los Angeles, described his "automated" firing in a viral blog post, described the New Zealand Herald.

In a lagoon in Venice, robotic lily pads float on the surface, with clusters of electronic mussels resting on the bed below. In July, a self-organising team of robots will be released into the murky waters of a lagoon near Venice, Italy. To continue reading this premium article, subscribe for unlimited access. Existing subscribers, please log in with your email address to link your account access.

New technology and new ideas are constantly changing and improving the way we do things. From Skype to Uber and everything in between, the recent years have seen a raft of innovations across just about every industry you can imagine. And there are more big changes on the way for the banking industry. So what does the rise of AI mean for Australian banks and how can consumers benefit from this new technology? Let's take a closer look.

Technologies for amplifying, sequencing and matching DNA have created new opportunities in genomic science. In this series When DNA Talks we look at the ethical and social implications. Everywhere we go we leave behind bits of DNA. We can already use this DNA to predict some traits, such as eye, skin and hair colour. Soon it may be possible to accurately reconstruct your whole face from these traces.

Google has perfected its ability to execute web search results for its users all over the world. In the early days of the Internet, the search engine was primarily suited for displaying search results for English users. Non-English-speaking users have complained that search results are often displayed in the wrong language entirely. However, Google is becoming more proficient at providing search results in other languages as well. A lot of factors can play a role, but one of the biggest is its use of deep learning to understand semantic references--enter semantic indexing. This can now be accomplished in any language that Google serves.

Acute respiratory infections have epidemic and pandemic potential and thus are being studied worldwide, albeit in many different contexts and study formats. Predicting infection from symptom data is critical, though using symptom data from varied studies in aggregate is challenging because the data is collected in different ways. Accordingly, different symptom profiles could be more predictive in certain studies, or even symptoms of the same name could have different meanings in different contexts. We assess state-of-the-art transfer learning methods for improving prediction of infection from symptom data in multiple types of health care data ranging from clinical, to home-visit as well as crowdsourced studies. We show interesting characteristics regarding six different study types and their feature domains. Further, we demonstrate that it is possible to use data collected from one study to predict infection in another, at close to or better than using a single dataset for prediction on itself. We also investigate in which conditions specific transfer learning and domain adaptation methods may perform better on symptom data. This work has the potential for broad applicability as we show how it is possible to transfer learning from one public health study design to another, and data collected from one study may be used for prediction of labels for another, even collected through different study designs, populations and contexts.

Stability is a key aspect of data analysis. In many applications, the natural notion of stability is geometric, as illustrated for example in computer vision. Scattering transforms construct deep convolutional representations which are certified stable to input deformations. This stability to deformations can be interpreted as stability with respect to changes in the metric structure of the domain. In this work, we show that scattering transforms can be generalized to non-Euclidean domains using diffusion wavelets, while preserving a notion of stability with respect to metric changes in the domain, measured with diffusion maps. The resulting representation is stable to metric perturbations of the domain while being able to capture "high-frequency" information, akin to the Euclidean Scattering.

It was recently shown that architectural, regularization and rehearsal strategies can be used to train deep models sequentially on a number of disjoint tasks without forgetting previously acquired knowledge. However, these strategies are still unsatisfactory if the tasks are not disjoint but constitute a single incremental task (e.g., class-incremental learning). In this paper we point out the differences between multi-task and single-incremental-task scenarios and show that well-known approaches such as LWF, EWC and SI are not ideal for incremental task scenarios. A new approach, denoted as AR1, combining architectural and regularization strategies is then specifically proposed. AR1 overhead (in term of memory and computation) is very small thus making it suitable for online learning. When tested on CORe50 and iCIFAR-100, AR1 outperformed existing regularization strategies by a good margin.

There is no strong evidence to support fears that screen time is inherently bad for children, experts have warned, adding that the recognition of so-called gaming disorder by the World Health Organisation is premature. Time spent using devices ranging from computers to smartphones and televisions has been the subject of debate after the UK's culture secretary Matt Hancock called for parents to set boundaries for their children on the use of tech. "Unlimited and unsupervised access to smartphones can be a portal to some very serious risks. And the chief medical officer has highlighted growing concerns around the impact on children's mental health. This backs up every parent's instinct; that children must be protected," he said.