In 2015, Google's DeepMind AI was tasked with learning to play Atari video games. It was quite successful too, becoming as good at Video Pinball as a human player. But beyond the simple arcade games it began to struggle, notoriously failing to even collect the first key in the legendary 1980s adventure game Montezuma's Revenge, due to the game's complexity. However, a new approach has resulted in an AI algorithm that learnt from mistakes and identified intermediate steps 10 times faster, succeeding where Google failed and successfully autonomously playing Montezuma's Revenge. The work was carried out by Fabio Zambetta and his team from RMIT University in Melbourne, Australia.

The training of stochastic neural network models with binary ($\pm1$) weights and activations via a deterministic and continuous surrogate network is investigated. We derive, using mean field theory, a set of scalar equations describing how input signals propagate through the surrogate network. The equations reveal that these continuous models exhibit an order to chaos transition, and the presence of depth scales that limit the maximum trainable depth. Moreover, we predict theoretically and confirm numerically, that common weight initialization schemes used in standard continuous networks, when applied to the mean values of the stochastic binary weights, yield poor training performance. This study shows that, contrary to common intuition, the means of the stochastic binary weights should be initialised close to $\pm 1$ for deeper networks to be trainable.

Mixed datasets consist of numeric and categorical attributes. Various K-means-based clustering algorithms have been developed to cluster these datasets. Generally, these clustering algorithms use random initial clusters which in turn produce different clustering results in different runs. A few cluster initialisation methods have been developed to compute initial clusters, however, they are either computationally expensive or they do not create the same clustering results in different runs. In this paper, we propose a novel approach to find initial clusters for K-means-based clustering algorithms for mixed datasets. The proposed approach is based on the observation that some data points in datasets remain in the same clusters created by K-means-based clustering algorithm irrespective of the choice of initial clusters. It is proposed that individual attribute information can be used to create initial clusters. A K-means-based clustering algorithm is run many times, in each run one of the attributes is used to create initial clusters. The clustering results of various runs are combined to produce a clustering result. This clustering result is used as initial clusters for a K-means-based clustering algorithm. Experiments with various categorical and mixed datasets showed that the proposed clustering approach produced accurate and consistent results.

Is it possible to predict the motivation of players just by observing their gameplay data? Even if so, how should we measure motivation in the first place? To address the above questions, on the one end, we collect a large dataset of gameplay data from players of the popular game Tom Clancy's The Division (Ubisoft, 2016). On the other end we ask them to report their levels of competence, autonomy, relatedness and presence using the in-house designed Ubisoft Perceived Experience Questionnaire. After processing the survey responses in an ordinal fashion we employ preference learning methods, based on support vector machines, to infer the mapping between gameplay and the four motivation factors. Our key findings suggest that gameplay features are strong predictors of player motivation as the obtained models reach accuracies of near certainty, in particular, from 93% up to 97% on unseen players.

Recently there has been an increasing interest in the multivariate Gaussian process (MGP) which extends the Gaussian process (GP) to deal with multiple outputs. One approach to construct the MGP and account for non-trivial commonalities amongst outputs employs a convolution process (CP). The CP is based on the idea of sharing latent functions across several convolutions. Despite the elegance of the CP construction, it provides new challenges that need yet to be tackled. First, even with a moderate number of outputs, model building is extremely prohibitive due to the huge increase in computational demands and number of parameters to be estimated. Second, the negative transfer of knowledge may occur when some outputs do not share commonalities. In this paper we address these issues. We propose a regularized pairwise modeling approach for the MGP established using CP. The key feature of our approach is to distribute the estimation of the full multivariate model into a group of bivariate GPs which are individually built. Interestingly pairwise modeling turns out to possess unique characteristics, which allows us to tackle the challenge of negative transfer through penalizing the latent function that facilitates information sharing in each bivariate model. Predictions are then made through combining predictions from the bivariate models within a Bayesian framework. The proposed method has excellent scalability when the number of outputs is large and minimizes the negative transfer of knowledge between uncorrelated outputs. Statistical guarantees for the proposed method are studied and its advantageous features are demonstrated through numerical studies.

We derive a family of Monte Carlo estimators for gradients of expectations of univariate distributions, which is related to the log-derivative trick, but involves pairwise interactions between samples. The first of these comes from either a) introducing and approximating an integral representation based on the fundamental theorem of calculus, or b) applying the reparameterisation trick to an implicit parameterisation under infinitesimal perturbation of the parameters. From the former perspective we generalise to a reproducing kernel Hilbert space representation, giving rise to locality parameter in the pairwise interactions mentioned above. The resulting estimators are unbiased and shown to offer an independent component of useful information in comparison with the log-derivative estimator. Promising analytical and numerical examples confirm the intuitions behind the new estimators.

CFS (Correlation-Based Feature Selection) is an FS algorithm that has been successfully applied to classification problems in many domains. We describe Distributed CFS (DiCFS) as a completely redesigned, scalable, parallel and distributed version of the CFS algorithm, capable of dealing with the large volumes of data typical of big data applications. Two versions of the algorithm were implemented and compared using the Apache Spark cluster computing model, currently gaining popularity due to its much faster processing times than Hadoop's MapReduce model. We tested our algorithms on four publicly available datasets, each consisting of a large number of instances and two also consisting of a large number of features. The results show that our algorithms were superior in terms of both time-efficiency and scalability. In leveraging a computer cluster, they were able to handle larger datasets than the non-distributed WEKA version while maintaining the quality of the results, i.e., exactly the same features were returned by our algorithms when compared to the original algorithm available in WEKA.

Sir Winston Churchill's birthplace, Blenheim Palace, is experimenting with a five-foot tall robot tour guide, called Betty. The autonomous robot is the latest in a series of tech advances in the grand stately home. Betty is designed to seek out visitors to provide information and answer their questions. It even takes selfies with visitors and can upload them to social media using the Twitter hashtag #bettyinthepalace. New addition: Blenheim Palace's new robotic tour guide wanders the halls of the stately home.

Working for a living will become obsolete. AI and robots will make the stuff we need and provide the services we need. The path to get there will be rocky. I don't worry about the end game. It's going to be great. But I worry about the path getting there.

Recent years have seen a boom in interest in machine learning systems that can provide a human-understandable rationale for their predictions or decisions. However, exactly what kinds of explanation are truly human-interpretable remains poorly understood. This work advances our understanding of what makes explanations interpretable under three specific tasks that users may perform with machine learning systems: simulation of the response, verification of a suggested response, and determining whether the correctness of a suggested response changes under a change to the inputs. Through carefully controlled human-subject experiments, we identify regularizers that can be used to optimize for the interpretability of machine learning systems. Our results show that the type of complexity matters: cognitive chunks (newly defined concepts) affect performance more than variable repetitions, and these trends are consistent across tasks and domains. This suggests that there may exist some common design principles for explanation systems.