Random forests remain among the most popular off-the-shelf supervised machine learning tools with a well-established track record of predictive accuracy in both regression and classification settings. Despite their empirical success as well as a bevy of recent work investigating their statistical properties, a full and satisfying explanation for their success has yet to be put forth. Here we aim to take a step forward in this direction by demonstrating that the additional randomness injected into individual trees serves as a form of implicit regularization, making random forests an ideal model in low signal-to-noise ratio (SNR) settings. Specifically, from a model-complexity perspective, we show that the mtry parameter in random forests serves much the same purpose as the shrinkage penalty in explicitly regularized regression procedures like lasso and ridge regression. To highlight this point, we design a randomized linear-model-based forward selection procedure intended as an analogue to tree-based random forests and demonstrate its surprisingly strong empirical performance. Numerous demonstrations on both real and synthetic data are provided.

--Spectral Clustering is a popular technique to split data points into groups, especially for complex datasets. The algorithms in the Spectral Clustering family typically consist of multiple separate stages (such as similarity matrix construction, low-dimensional embedding, and K-Means clustering as post-processing), which may lead to sub-optimal results because of the possible mismatch between different stages. In this paper, we propose an end-to-end single-stage learning method to clustering called Regularized Nonnegative Spectral Embedding (RNSE) which extends Spectral Clustering with the adaptive learning of similarity matrix and meanwhile utilizes nonnegative constraints to facilitate one-step clustering (directly from data points to clustering labels). Two well-founded methods, successive alternating projection and strategic multiplicative update, are employed to work out the quite challenging optimization problems in RNSE. Extensive experiments on both synthetic and real-world datasets demonstrate RNSE's superior clustering performance to some state-of-the-art competitors. I NTRODUCTION Clustering is an important unsupervised learning task which aims to group a set of data objects into clusters in such a way that objects in the same cluster are more similar to each other than those in different clusters. For complex datasets, Spectral Clustering [1] and its many variants [2]- [4] are particularly popular due to their ability of discovering highly non-convex clusters.

Exploration in environments with continuous control and sparse rewards remains a key challenge in reinforcement learning (RL). Recently, surprise has been used as an intrinsic reward that encourages systematic and efficient exploration. We introduce a new definition of surprise and its RL implementation named Variational Assorted Surprise Exploration (VASE). VASE uses a Bayesian neural network as a model of the environment dynamics and is trained using variational inference, alternately updating the accuracy of the agent's model and policy. Our experiments show that in continuous control sparse reward environments VASE outperforms other surprise-based exploration techniques.

Imagine flying from Europe to Australia in just 90 minutes. This is fantasy for now, but the stratosphere is the next frontier in aviation, with supersonic flights using that high-altitude space. And one of the keys to making it happen will be the use of Artificial Intelligence (AI) to cope with the increased complexity the sector will face. "Aviation is being reshaped by a number of powerful forces that are fundamentally impacting the Air Traffic Management sector," says Beatrice Pesquet-Popescu, Research and Business Innovation Director for Air Traffic Management (ATM) at Thales. "In addition to the growth expected in traditional aircraft, we will have to cope with new vehicles such as drones and stratospheric balloons, circulating in low or high altitude airspace."

'Independently I had started to do my research on how we can apply artificial intelligence to investigate some of the challenges that beset major programmes,' said Quang. 'What stood out for me from the course, is how we can use artificial intelligence to tackle both complexity and behavioural decision making. This is now the basis of a multi-year research programme I have the privilege of conducting with Saïd Business School as an Associate Scholar.' The pair leveraged the Oxford network to build the business. Throughout their programme they regularly discussed and refined their ideas with academics and classmates, several of whom are now shareholders.

German sports car maker Porsche and US aircraft manufacturer Boeing are teaming up to assess whether they can bring the dream, or nightmare, of a flying car to reality. The two companies announced this week that they're planning to make a concept vehicle with a "fully electric" vertical takeoff and landing (EVTOL) capability. The companies have created a mockup of a vehicle that looks like a sleeker version of the Batmobile from The Dark Knight Rises – exactly what you might expect from Porsche designers. The project will involve engineers from Boeing, Porsche, and Boeing subsidiary Aurora Flight Sciences, which makes unmanned aerial vehicles. The companies are exploring whether there's a market for premium vehicles.

The use of neural networks to predict airport passenger activity choices inside the terminal is presented in this paper. Three network architectures are proposed: Feedforward Neural Networks (FNN), Long Short-Term Memory (LSTM) networks, and a combination of the two. Inputs to these models are both static (passenger and trip characteristics) and dynamic (real-time passenger tracking). A real-world case study exemplifies the application of these models, using anonymous WiFi traces collected at Bologna Airport to train the networks. The performance of the models were evaluated according to the misclassification rate of passenger activity choices. In the LSTM approach, two different multi-step forecasting strategies are tested. According to our findings, the direct LSTM approach provides better results than the FNN, especially when the prediction horizon is relatively short (20 minutes or less).

Bayesian inference in state-space models is challenging due to high-dimensional state trajectories. A viable approach is particle Markov chain Monte Carlo, combining MCMC and sequential Monte Carlo to form "exact approximations" to otherwise intractable MCMC methods. The performance of the approximation is limited to that of the exact method. We focus on particle Gibbs and particle Gibbs with ancestor sampling, improving their performance beyond that of the underlying Gibbs sampler (which they approximate) by marginalizing out one or more parameters. This is possible when the parameter prior is conjugate to the complete data likelihood. Marginalization yields a non-Markovian model for inference, but we show that, in contrast to the general case, this method still scales linearly in time. While marginalization can be cumbersome to implement, recent advances in probabilistic programming have enabled its automation. We demonstrate how the marginalized methods are viable as efficient inference backends in probabilistic programming, and demonstrate with examples in ecology and epidemiology.

Clustering is one of the most fundamental and wide-spread techniques in exploratory data analysis. Yet, the basic approach to clustering has not really changed: a practitioner hand-picks a task-specific clustering loss to optimize and fit the given data to reveal the underlying cluster structure. Some types of losses---such as k-means, or its non-linear version: kernelized k-means (centroid based), and DBSCAN (density based)---are popular choices due to their good empirical performance on a range of applications. Although every so often the clustering output using these standard losses fails to reveal the underlying structure, and the practitioner has to custom-design their own variation. In this work we take an intrinsically different approach to clustering: rather than fitting a dataset to a specific clustering loss, we train a recurrent model that learns how to cluster. The model uses as training pairs examples of datasets (as input) and its corresponding cluster identities (as output). By providing multiple types of training datasets as inputs, our model has the ability to generalize well on unseen datasets (new clustering tasks). Our experiments reveal that by training on simple synthetically generated datasets or on existing real datasets, we can achieve better clustering performance on unseen real-world datasets when compared with standard benchmark clustering techniques. Our meta clustering model works well even for small datasets where the usual deep learning models tend to perform worse.

Artificial intelligence allows us to program our lives on command, while offering the promise of solving some of the world's most challenging problems. But countries around the world, including Australia, are grappling with how to build ethical frameworks around AI.