OPINION: Last week about 60 rally teams, close to 500 volunteers and a small organising group staged the Targa Rally of New Zealand. Billed as the ultimate road race, this year's Targa was the 25th running of the iconic event which sees close to 1200 km of public road closed and turned into race-track. Last May my Targa team were doing great until stage three of the second day when some Gentle Annie shingle shredded the Kevlar cambelt on our Type R, rapidly followed by 16 valves and four pistons. So this year we were back with a new top end and a new state of tune. And the good news is that it worked.

OPINION: Last week about 60 rally teams, close to 500 volunteers and a small organising group staged the Targa Rally of New Zealand. Billed as the ultimate road race, this year's Targa was the 25th running of the iconic event which sees close to 1200 km of public road closed and turned into race-track. Last May my Targa team were doing great until stage three of the second day when some Gentle Annie shingle shredded the Kevlar cambelt on our Type R, rapidly followed by 16 valves and four pistons. So this year we were back with a new top end and a new state of tune. And the good news is that it worked.

After decades of study and significant data collection of time-varying swash on sandy beaches, there is no single deterministic prediction scheme for wave runup that eliminates prediction error – even bespoke, locally tuned predictors present scatter when compared to observations. Scatter in runup prediction is meaningful and can be used to create probabilistic predictions of runup for a given wave climate and beach slope. This contribution demonstrates this using a data-driven Gaussian process predictor; a probabilistic machine-learning technique. The runup predictor is developed using 1 year of hourly wave runup data (8328 observations) collected by a fixed lidar at Narrabeen Beach, Sydney, Australia. The Gaussian process predictor accurately predicts hourly wave runup elevation when tested on unseen data with a root-mean-squared error of 0.18 m and bias of 0.02 m.

Ensemble learning is a standard approach to building machine learning systems that capture complex phenomena in real-world data. An important aspect of these systems is the complete and valid quantification of model uncertainty. We introduce a Bayesian nonparametric ensemble (BNE) approach that augments an existing ensemble model to account for different sources of model uncertainty. BNE augments a model's prediction and distribution functions using Bayesian nonparametric machinery. It has a theoretical guarantee in that it robustly estimates the uncertainty patterns in the data distribution, and can decompose its overall predictive uncertainty into distinct components that are due to different sources of noise and error. We show that our method achieves accurate uncertainty estimates under complex observational noise, and illustrate its real-world utility in terms of uncertainty decomposition and model bias detection for an ensemble in predict air pollution exposures in Eastern Massachusetts, USA.

In many practical applications of machine learning and pred ictive modeling, data is produced incrementally in the course of time and observed in the form of a continuous, potentially unbounded stream of observations. Correspond ingly, the problem of learning from data streams has recently received increasing attenti on (Gama, 2012). Algorithms for learning on streams must be able to process the data in a si ngle pass, which implies an incremental mode of learning, and to adapt to changes of the u nderlying data-generating process (Domingos and Hulten, 2003). A popular approach for learning on data streams, both for cla ssification and regression, is rule induction, in the fuzzy logic and computational inte lligence community also known as "evolving fuzzy systems" (Lughofer, 2011). Shaker et al. (2017) proposed a method for regression that builds on a very efficient and effective techniq ue for rule induction, which 1 is inspired by the state-of-the-art machine learning algor ithm AMRules, and combines it with the strengths of fuzzy modeling. Thus, the method induc es a set of fuzzy rules, which, compared to conventional rules with Boolean antecedents, h as the advantage of producing smooth regression functions. The method presented in this p aper, called TSK-Streams, is a revised and improved variant. The main modifications and novel contributions are as follows.

Label switching is a phenomenon arising in mixture model posterior inference that prevents one from meaningfully assessing posterior statistics using standard Monte Carlo procedures. This issue arises due to invariance of the posterior under actions of a group; for example, permuting the ordering of mixture components has no effect on the likelihood. We propose a resolution to label switching that leverages machinery from optimal transport. Our algorithm efficiently computes posterior statistics in the quotient space of the symmetry group. We give conditions under which there is a meaningful solution to label switching and demonstrate advantages over alternative approaches on simulated and real data.

The robots are coming – for jobs. This is the plain, cold, hard fact we now face as we head towards the third decade of the 21st Century. The technology-driven world in which we now live is one filled with promise – cars that drive themselves, algorithms that respond to customer service inquiries, automated business intelligence on tap. Yet, this brave new world is also filled with challenges. For even as AI and automation increase productivity and improve our lives, their widespread adoption means that many work activities humans currently perform will soon be displaced – if they haven't been already. What this doesn't mean, however, is that there will be a shortage of jobs in the future.

By registering, you agree to the AWS Event Terms and Conditions and the AWS Community Codes of Conduct. By completing this form, I agree that I'd like to receive information from Amazon Web Services, Inc. and its affiliates related to AWS services, events and special offers, and my AWS needs by email and post. You may unsubscribe at any time by following the instructions in the communications received. By completing this form, I agree that I'd like to receive information from Amazon Web Services, Inc. and its affiliates related to AWS services, events and special offers, and my AWS needs by email and post. You may unsubscribe at any time by following the instructions in the communications received.

This list of readings about journalism and AI is based on research for the Polis report on AI and Journalism published in November 2018. We will update this list and welcome suggestions for further readings to: c.h.beckett@lse.ac.uk What is machine learning and why should I care? AI is going to save journalism – here's how Is AI and journalism a good mix? First in the world: Yle's smart news assistant Voitto ensures that you don't miss the news you want to read Can science writing be automated?

Car manufacturers know: There's a huge amount of interest in AI-driven cars. Many people would love to automate the task of driving, because they find it tedious or at times impossible. A competent AI driver would have lightning-fast reflexes, would never weave or drift in its lane, and would never drive aggressively. An AI driver would never get tired and could take the wheel for endless hours while we humans nap or party. While AI does need huge volumes of data to program and guide it, that shouldn't be a problem.