Parallel tempering addresses some of the drawbacks of canonical Markov Chain Monte-Carlo methods for Bayesian neural learning with the ability to utilize high performance computing. However, certain challenges remain given the large range of network parameters and big data. Surrogate-assisted optimization considers the estimation of an objective function for models given computational inefficiency or difficulty to obtain clear results. We address the inefficiency of parallel tempering for large-scale problems by combining parallel computing features with surrogate assisted estimation of likelihood function that describes the plausibility of a model parameter value, given specific observed data. In this paper, we present surrogate-assisted parallel tempering for Bayesian neural learning where the surrogates are used to estimate the likelihood. The estimation via the surrogate becomes useful rather than evaluating computationally expensive models that feature large number of parameters and datasets. Our results demonstrate that the methodology significantly lowers the computational cost while maintaining quality in decision making using Bayesian neural learning. The method has applications for a Bayesian inversion and uncertainty quantification for a broad range of numerical models.

Eating food is an experience that tends to be about taste and texture and how the food looks and smells. Our focus goes from what's going on on the plate to what's going on in our mouths, without a lot of concern about what happens in between. Eating as a process doesn't get all that much attention; we tend to treat it as just a chore involving utensils. Which is fine, but are we missing out somehow? The Exertion Games Lab at RMIT University in Australia thinks that the answer to that is yes, and they're using chest-mounted social feeding robots to prove it.

Artificial Intelligence technologies and capabilities are driving digital transformation, growth, and opportunity in nearly every sector. In fact, a report by AlphaBeta urges Australia to double its pace of artificial intelligence and robotics automation to reap a $2.2 trillion market opportunity by 2030. So, why is it that AI can have such a massive impact, and should your organisation jump on the bandwagon? The short answer is that the window of competitive advantage will be small, and if you don't jump through it, one of your competitors will. There's much to be gained by using AI to improve business outcomes.

Eike Germann, Introduction to Reinforcement Learning What is Reinforcement Learning? How is it different from the machine learning we're familiar with? I'll present some foundational ideas (Markov decision processes, policy iteration, value iteration etc) and talk about their limitations. What algorithms are currently used to address those limitations and how do they do it? Based on these, I'll give a short overview of what RL is used currently used for - from training a machine to play space invaders to robotic movement in the real world.

Latent factor models (LFMs) such as matrix factorization achieve the state-of-the-art performance among various Collaborative Filtering (CF) approaches for recommendation. Despite the high recommendation accuracy of LFMs, a critical issue to be resolved is the lack of explainability. Extensive efforts have been made in the literature to incorporate explainability into LFMs. However, they either rely on auxiliary information which may not be available in practice, or fail to provide easy-to-understand explanations. In this paper, we propose a fast influence analysis method named FIA, which successfully enforces explicit neighbor-style explanations to LFMs with the technique of influence functions stemmed from robust statistics. We first describe how to employ influence functions to LFMs to deliver neighbor-style explanations. Then we develop a novel influence computation algorithm for matrix factorization with high efficiency. We further extend it to the more general neural collaborative filtering and introduce an approximation algorithm to accelerate influence analysis over neural network models. Experimental results on real datasets demonstrate the correctness, efficiency and usefulness of our proposed method.

A GPS-denied UAV (Agent B) is localised through INS alignment with the aid of a nearby GPS-equipped UAV (Agent A), which broadcasts its position at several time instants. Agent B measures the signals' direction of arrival with respect to Agent B's inertial navigation frame. Semidefinite programming and the Orthogonal Procrustes algorithm are employed, and accuracy is improved through maximum likelihood estimation. The method is validated using flight data and simulations. A three-agent extension is explored.

Abstract--Automatic recognition of human activities from time-series sensor data (referred to as HAR) is a growing area of research in ubiquitous computing. Most recent research in the field adopts supervised deep learning paradigms to automate extraction of intrinsic features from raw signal inputs and addresses HAR as a multi-class classification problem where detecting a single activity class within the duration of a sensory data segment suffices. However, due to the innate diversity of human activities and their corresponding duration, no data segment is guaranteed to contain sensor recordings of a single activity type. In this paper, we express HAR more naturally as a set prediction problem where the predictions are sets of ongoing activity elements with unfixed and unknown cardinality. For the first time, we address this problem by presenting a novel HAR approach that learns to output activity sets using deep neural networks. Moreover, motivated by the limited availability of annotated HAR datasets as well as the unfortunate immaturity of existing unsupervised systems, we complement our supervised set learning scheme with a prior unsupervised feature learning process that adopts convolutional auto-encoders to exploit unlabeled data.The empirical experiments on two widely adopted HAR datasets demonstrate the substantial improvement of our proposed methodology over the baseline models. I. INTRODUCTION With the proliferation of low-cost sensing technologies as well as the fast advancements in machine learning techniques, automatic human activity recognition (HAR) using wearable sensors has emerged as a key research area in ubiquitous computing [1]-[4].In this problem, high-level activity information is acquired through analyzing low-level sensor recordings with the goal of providing proactive assistance to users.

Computers aren't going to replace creative pros -- but machine learning and artificial intelligence can be powerful tools in the storytelling process. The 60-second spot was directed by Oscar-winner Kevin Macdonald, working from a script that was developed by IBM's Watson AI system. To produce the spot for the Lexus ES executive sedan launching in Europe, the automaker enlisted its creative agency, The&Partnership London, along with technical partner Visual Voice. The agencies collaborated with the IBM Watson team to use AI to analyze 15 years' worth of footage, text and audio for car and luxury brand campaigns that have won Cannes Lions awards for creativity, as well as a range of other external data. Watson identified elements common to award-worthy commercials that were "both emotionally intelligent and entertaining," according to IBM.

Representation learning is a central challenge across a range of machine learning areas. In reinforcement learning, effective and functional representations have the potential to tremendously accelerate learning progress and solve more challenging problems. Most prior work on representation learning has focused on generative approaches, learning representations that capture all underlying factors of variation in the observation space in a more disentangled or well-ordered manner. In this paper, we instead aim to learn functionally salient representations: representations that are not necessarily complete in terms of capturing all factors of variation in the observation space, but rather aim to capture those factors of variation that are important for decision making -- that are "actionable." These representations are aware of the dynamics of the environment, and capture only the elements of the observation that are necessary for decision making rather than all factors of variation, without explicit reconstruction of the observation. We show how these representations can be useful to improve exploration for sparse reward problems, to enable long horizon hierarchical reinforcement learning, and as a state representation for learning policies for downstream tasks. We evaluate our method on a number of simulated environments, and compare it to prior methods for representation learning, exploration, and hierarchical reinforcement learning.

New Zealand, 26 October 2018 – Yesterday at Microsoft's inaugural AI event, Future Now, real-life applications of how AI will help shape New Zealand were brought to life demonstrating that AI is an important driver of new solutions to address some of our biggest societal challenges. Damon Kelly, Enlighten Designs CEO and Microsoft Partner showcased an exciting new initiative with Sustainable Coastlines aiming to make citizen scientists of us all by arming us with right data and insights to help keep our country clean, green and beautiful. Kelly said, "We have partnered with Sustainable Coastlines and Microsoft's Azure platform to develop an AI-powered tool that empowers Kiwis in cleaning up New Zealand's beaches. The tool is the first of its kind in New Zealand and uses Microsoft's Cognitive Services, alongside a United Nations Environment Programme methodology, to help communities around the country capture and categorise what litter is on our beaches." Working alongside the Ministry for the Environment, Department of Conservation and Statistics New Zealand, data collected from Sustainable Coastlines' new tool will be used to help establish a New Zealand-first national litter database.