Researchers at the Queensland University of Technology (QUT) have applied artificial intelligence (AI) to develop a more accurate and detailed method for analysing images of the back of the eye to help clinicians better detect and track eye diseases. In the study, the group of researchers explored a range of deep learning techniques to analyse Optical Coherence Tomography (OCT) images, said David Alonso-Caneiro, QUT senior research fellow and study lead author. OCT, which takes cross-sectional images of the eye to show different tissue layers, is a common instrument used by optometrists and ophthalmologists. These images are around four microns in size and can help clinicians detect eye diseases such as glaucoma and age-related macular degeneration. The team collected OCT chorio-retinal eye scans from an 18-month longitudinal study of 101 children with good vision and healthy eyes, and used these images to train the AI program to detect patterns and define the choroid boundaries.

Brisbane startup FloodMapp has raised $1.3 million, as it looks to take its flood-prediction tech to the rest of Australia, and into hurricane-prone areas of the US. The funding comes from several VC firms, including Allectus Capital, Transition Level Investments, Jelix Ventures and Mercurian, as well as from a number of individual investors. Founded by Juliette Murphy and Ryan Prosser, FloodMapp combines big data analytics and machine learning techniques with traditional hydrology and hydraulic modelling approaches. The tech measures river height and rainfall data in real-time, and uses underlying elevation and topography to predict how and where water will flow over the land, Murphy tells StartupSmart. This allows the team to "predict a map of the inundated areas" and share that data with third parties.

Companies around the world are expecting to apply artificial intelligence (AI) within their companies in the next few years but are lagging in discussions of the ethics around it, research from Genesys finds. More than half of the employers questioned in a multi-country opinion survey say their companies do not currently have a written policy on the ethical use of AI or bots, although 21% expressed a definite concern that their companies could use AI in an unethical manner. "As a company delivering numerous customer experience solutions enabled by AI, we understand this technology has great potential that also comes with tremendous responsibility," said Steve Leeson, VP UK & Ireland, Genesys. "This research gives us important insight into how businesses and their employees are really thinking about the implications of AI – and where we as a technology community can help them steer an ethical path forward in its use." The research findings stem from opinion surveys sponsored by Genesys (www.genesys.com),

Current cameras are capable of recording high resolution video. While viewing on a mobile device, a user can manually zoom into this high resolution video to get more detailed view of objects and activities. However, manual zooming is not suitable for surveillance and monitoring. It is tiring to continuously keep zooming into various regions of the video. Also, while viewing one region, the operator may miss activities in other regions. In this paper, we propose sZoom, a framework to automatically zoom into a high resolution surveillance video. The proposed framework selectively zooms into the sensitive regions of the video to present details of the scene, while still preserving the overall context required for situation assessment. A multi-variate Gaussian penalty is introduced to ensure full coverage of the scene. The method achieves near real-time performance through a number of timing optimizations. An extensive user study shows that, while watching a full HD video on a mobile device, the system enhances the security operator's efficiency in understanding the details of the scene by 99% on the average compared to a scaled version of the original high resolution video. The produced video achieved 46% higher ratings for usefulness in a surveillance task.

Recurrent Neural Networks (RNN) have become competitive forecasting methods, as most notably shown in the winning method of the recent M4 competition. However, established statistical models such as ETS and ARIMA gain their popularity not only from their high accuracy, but they are also suitable for non-expert users as they are robust, efficient, and automatic. In these areas, RNNs have still a long way to go. We present an extensive empirical study and an open-source software framework of existing RNN architectures for forecasting, that allow us to develop guidelines and best practices for their use. For example, we conclude that RNNs are capable of modelling seasonality directly if the series in the dataset possess homogeneous seasonal patterns, otherwise we recommend a deseasonalization step. Comparisons against ETS and ARIMA demonstrate that the implemented (semi-)automatic RNN models are no silver bullets, but they are competitive alternatives in many situations.

A framework to boost efficiency of Bayesian inference in probabilistic programs is introduced by embedding a sampler inside a variational posterior approximation, which we call the refined variational approximation. Its strength lies both in ease of implementation and in automatically tuning the sampler parameters to speed up mixing time. Several strategies to approximate the \emph{evidence lower bound} (ELBO) computation are introduced, including a rewriting of the ELBO objective. A specialization towards state-space models is proposed. Experimental evidence of its efficient performance is shown by solving an influence diagram in a high-dimensional space using a conditional variational autoencoder (cVAE) as a deep Bayes classifier; an unconditional VAE on density estimation tasks; and state-space models for time-series data.

State of the art algorithms for many pattern recognition problems rely on deep network models. Training these models requires a large labeled dataset and considerable computational resources. Also, it is difficult to understand the working of these learned models, limiting their use in some critical applications. Towards addressing these limitations, our architecture draws inspiration from research in cognitive systems, and integrates the principles of commonsense logical reasoning, inductive learning, and deep learning. In the context of answering explanatory questions about scenes and the underlying classification problems, the architecture uses deep networks for extracting features from images and for generating answers to queries. Between these deep networks, it embeds components for non-monotonic logical reasoning with incomplete commonsense domain knowledge, and for decision tree induction. It also incrementally learns and reasons with previously unknown constraints governing the domain's states. We evaluated the architecture in the context of datasets of simulated and real-world images, and a simulated robot computing, executing, and providing explanatory descriptions of plans. Experimental results indicate that in comparison with an ``end to end'' architecture of deep networks, our architecture provides better accuracy on classification problems when the training dataset is small, comparable accuracy with larger datasets, and more accurate answers to explanatory questions. Furthermore, incremental acquisition of previously unknown constraints improves the ability to answer explanatory questions, and extending non-monotonic logical reasoning to support planning and diagnostics improves the reliability and efficiency of computing and executing plans on a simulated robot.

This work focuses on studying players behaviour in interactive narratives with the aim to simulate their choices. Besides sub-optimal player behaviour due to limited knowledge about the environment, the difference in each player's style and preferences represents a challenge when trying to make an intelligent system mimic their actions. Based on observations from players interactions with an extract from the interactive fiction Anchorhead, we created a player profile to guide the behaviour of a generic player model based on the BDI (Belief-Desire-Intention) model of agency. We evaluated our approach using qualitative and quantitative methods and found that the player profile can improve the performance of the BDI player model. However, we found that players self-assessment did not yield accurate data to populate their player profile under our current approach.

In this paper, we present a new modality for intelligent inte r-active narratives within the theatre domain. We discuss the possibilities of using an intelligent agent that serves as a drama manager a nd as an actor that plays a character within the live theatre exper ience. We pose a set of research challenges that arise from our analysi s towards the implementation of such an agent, as well as potential method ologies as a starting point to bridge the gaps between current literatu re and the proposed modality.

Neural dialogue models have been widely adopted in various chatbot applications because of their good performance in simulating and generalizing human conversations. However, there exists a dark side of these models -- due to the vulnerability of neural networks, a neural dialogue model can be manipulated by users to say what they want, which brings in concerns about the security of practical chatbot services. In this work, we investigate whether we can craft inputs that lead a well-trained black-box neural dialogue model to generate targeted outputs. We formulate this as a reinforcement learning (RL) problem and train a Reverse Dialogue Generator which efficiently finds such inputs for targeted outputs. Experiments conducted on a representative neural dialogue model show that our proposed model is able to discover such desired inputs in a considerable portion of cases. Overall, our work reveals this weakness of neural dialogue models and may prompt further researches of developing corresponding solutions to avoid it.