Many complex natural and cultural phenomena are well modelled by systems of simple interactions between particles. A number of architectures have been developed to articulate this kind of structure, both implicitly and explicitly. We consider an unsupervised explicit model, the NRI model, and make a series of representational adaptations and physically motivated changes. Most notably we factorise the inferred latent interaction graph into a multiplex graph, allowing each layer to encode for a different interaction-type. This fNRI model is smaller in size and significantly outperforms the original in both edge and trajectory prediction, establishing a new state-of-the-art. We also present a simplified variant of our model, which demonstrates the NRI's formulation as a variational auto-encoder is not necessary for good performance, and make an adaptation to the NRI's training routine, significantly improving its ability to model complex physical dynamical systems.

The learning of predictive models for data-driven decision support has been a prevalent topic in many fields. However, construction of models that would capture interactions among input variables is a challenging task. In this paper, we present a new preference learning approach for multiple criteria sorting with potentially interacting criteria. It employs an additive piecewise-linear value function as the basic preference model, which is augmented with components for handling the interactions. To construct such a model from a given set of assignment examples concerning reference alternatives, we develop a convex quadratic programming model. Since its complexity does not depend on the number of training samples, the proposed approach is capable for dealing with data-intensive tasks. To improve the generalization of the constructed model on new instances and to overcome the problem of over-fitting, we employ the regularization techniques. We also propose a few novel methods for classifying non-reference alternatives in order to enhance the applicability of our approach to different datasets. The practical usefulness of the proposed method is demonstrated on a problem of parametric evaluation of research units, whereas its predictive performance is studied on several monotone learning datasets. The experimental results indicate that our approach compares favourably with the classical UTADIS method and the Choquet integral-based sorting model.

We analyze a new robust method for the reconstruction of probability distributions of observed data in the presence of output outliers. It is based on a so-called gradient conjugate prior (GCP) network which outputs the parameters of a prior. By rigorously studying the dynamics of the GCP learning process, we derive an explicit formula for correcting the obtained variance of the marginal distribution and removing the bias caused by outliers in the training set. Assuming a Gaussian (input-dependent) ground truth distribution contaminated with a proportion $\varepsilon$ of outliers, we show that the fitted mean is in a $c e^{-1/\varepsilon}$-neighborhood of the ground truth mean and the corrected variance is in a $b\varepsilon$-neighborhood of the ground truth variance, whereas the uncorrected variance of the marginal distribution can even be infinite. We explicitly find $b$ as a function of the output of the GCP network, without a priori knowledge of the outliers (possibly input-dependent) distribution. Experiments with synthetic and real-world data sets indicate that the GCP network fitted with a standard optimizer outperforms other robust methods for regression.

Lake and Baroni (2018) introduced the SCAN dataset probing the ability of seq2seq models to capture compositional generalizations, such as inferring the meaning of "jump around" 0-shot from the component words. Recurrent networks (RNNs) were found to completely fail the most challenging generalization cases. We test here a convolutional network (CNN) on these tasks, reporting hugely improved performance with respect to RNNs. Despite the big improvement, the CNN has however not induced systematic rules, suggesting that the difference between compositional and non-compositional behaviour is not clear-cut.

When concept drift is detected during classification in a data stream, a common remedy is to retrain a framework's classifier. However, this loses useful information if the classifier has learnt the current concept well, and this concept will recur again in the future. Some frameworks retain and reuse classifiers, but it can be time-consuming to select an appropriate classifier to reuse. These frameworks rarely match the accuracy of state-of-the-art ensemble approaches. For many data stream tasks, speed is important: fast, accurate frameworks are needed for time-dependent applications. We propose the Enhanced Concept Profiling Framework (ECPF), which aims to recognise recurring concepts and reuse a classifier trained previously, enabling accurate classification immediately following a drift. The novelty of ECPF is in how it uses similarity of classifications on new data, between a new classifier and existing classifiers, to quickly identify the best classifier to reuse. It always trains both a new classifier and a reused classifier, and retains the more accurate classifier when concept drift occurs. Finally, it creates a copy of reused classifiers, so a classifier well-suited for a recurring concept will not be impacted by being trained on a different concept. In our experiments, ECPF classifies significantly more accurately than a state-of-the-art classifier reuse framework (Diversity Pool) and a state-of-the-art ensemble technique (Adaptive Random Forest) on synthetic datasets with recurring concepts. It classifies real-world datasets five times faster than Diversity Pool, and six times faster than Adaptive Random Forest and is not significantly less accurate than either.

It was on the motorway near Phoenix, Arizona, that I realised fully driverless cars might be quite a distant dream. And that was because our Google Waymo robo-taxi seemed incapable of leaving that motorway. We were in Arizona to record a radio documentary for the BBC World Service about the progress towards creating autonomous vehicles that would make our roads safer and replace human drivers with robots. Google leads this race at the moment and for the past six months has been offering a robo-taxi service, Waymo One, to a select few early adopters in and around the Phoenix suburb of Chandler. Our first ride with Waymo took us through the quiet suburban streets, where traffic is sparse and drivers well mannered.

ABBYY, a global leader in Content IQ technologies and solutions, today announced it has signed an agreement to acquire Philadelphia, Pennsylvania-based TimelinePI. TimelinePI provides a comprehensive process intelligence platform designed to empower users to understand, monitor and optimize any business process. The global process analytics market size is expected to grow to USD 1,421.7 million by 2023 according to Research and Markets. The acquisition of TimelinePI is a strategic investment by ABBYY into the emerging process intelligence market which is critical to truly understanding the impact and effectiveness of business processes and opportunities for productivity gains from digital transformation investments. TimelinePI's vision of combining the most versatile process mining and operational monitoring with cutting-edge, process-centric AI and machine learning will serve as a critical cornerstone to ABBYY's Digital IQ strategy.

We have come to the fifth month of the year, and technology especially the disruptive one that includes Artificial Intelligence (AI) is gaining strong-hold more than ever. Understanding its disruptive factors is important as it enables more accurate forecasting and better planning for civil society, policymakers and businesses. Identifying the main levers that drive the growth of AI applications can help to expedite the many positive use cases in the pipeline; like optimised renewable energy distribution at scale and Machine Learning disease diagnosis systems in healthcare. So how are the disruptive technologies redefining businesses sphere? Over the years, it is been seen that AI adaptability is increasing.

I recently was a guest speaker at the Stanford AI Salon on the topic of accessiblity in AI, which included a free-ranging discussion among assembled members of the Stanford AI Lab. There were a number of interesting questions and topics, so I thought I would share a few of my answers here. Q: What 3 things would you most like the general public to know about AI? AI is easier to use than the hype would lead you to believe. In my recent talk at the MIT Technology Review conference, I debunked several common myths that you must have a PhD, a giant data set, or expensive computational power to use AI. Most AI researchers are not working on getting computers to achieve human consciousness.

Over the next year, the recipients will work on things like a nerve-sensing wearable wristband. Another project seeks to develop a wearable cap that reads a person's EEG data and communicates it to the cloud to provide seizure warnings and alerts. Other tools will rely on speech recognition, AI-powered chatbots and apps for people with vision impairment. This year's grantees include the University of California, Berkeley; Massachusetts Eye and Ear, a teaching hospital of Harvard Medical School; Voiceitt in Israel; Birmingham City University in the United Kingdom; University of Sydney in Australia; Pison Technology of Boston; and Our Ability, of Glenmont, New York. "What stands out the most about this round of grantees is how so many of them are taking standard AI capabilities, like a chatbot or data collection, and truly revolutionizing the value of technology," Microsoft's Senior Accessibility Architect Mary Bellard said in a blog post.