Word feature vectors have been proven to improve many NLP tasks. With recent advances in unsupervised learning of these feature vectors, it became possible to train it with much more data, which also resulted in better quality of learned features. Since it learns joint probability of latent features of words, it has the advantage that we can train it without any prior knowledge about the goal task we want to solve. We aim to evaluate the universal applicability property of feature vectors, which has been already proven to hold for many standard NLP tasks like part-of-speech tagging or syntactic parsing. In our case, we want to understand the topical focus of text documents and design an efficient representation suitable for discriminating different topics. The discriminativeness can be evaluated adequately on text categorisation task. We propose a novel method to extract discriminative keywords from documents. We utilise word feature vectors to understand the relations between words better and also understand the latent topics which are discussed in the text and not mentioned directly but inferred logically. We also present a simple way to calculate document feature vectors out of extracted discriminative words. We evaluate our method on the four most popular datasets for text categorisation. We show how different discriminative metrics influence the overall results. We demonstrate the effectiveness of our approach by achieving state-of-the-art results on text categorisation task using just a small number of extracted keywords. We prove that word feature vectors can substantially improve the topical inference of documents' meaning. We conclude that distributed representation of words can be used to build higher levels of abstraction as we demonstrate and build feature vectors of documents.

AlphaZero, an approach to reinforcement learning that couples neural networks and Monte Carlo tree search (MCTS), has produced state-of-the-art strategies for traditional board games like chess, Go, shogi, and Hex. While researchers and game commentators have suggested that AlphaZero uses concepts that humans consider important, it is unclear how these concepts are captured in the network. We investigate AlphaZero's internal representations in the game of Hex using two evaluation techniques from natural language processing (NLP): model probing and behavioral tests. In doing so, we introduce new evaluation tools to the RL community, and illustrate how evaluations other than task performance can be used to provide a more complete picture of a model's strengths and weaknesses. Our analyses in the game of Hex reveal interesting patterns and generate some testable hypotheses about how such models learn in general. For example, we find that MCTS discovers concepts before the neural network learns to encode them. We also find that concepts related to short-term end-game planning are best encoded in the final layers of the model, whereas concepts related to long-term planning are encoded in the middle layers of the model.

Dr Jade Leung, an artificial intelligence specialist, talks to Felicity Monk about what we can do to ensure AI is helpful – and not destructive – to humanity.

A world-first report from Australia's science agency, CSIRO, has found that scientists are adopting artificial intelligence (AI) at an unprecedented rate. Analysing the impact of AI on scientific discovery, 'Artificial intelligence for science' draws insight from millions of peer-reviewed scientific papers published over 63 years and identifies key issues ahead for the sector. The report found that artificial intelligence is now implemented in 98 per cent of scientific fields, and by September 2022 approximately 5.7% of all peer-reviewed research worldwide was on the topic. "AI is no longer just the domain of computer scientists or mathematicians; it is now a significant enabling force across all fields of science, which is something we live every day at CSIRO, where digital technologies are accelerating the pace and scale of our research in fields ranging from agriculture to energy to manufacturing and beyond," says CSIRO Chief Scientist Professor Bronwyn Fox. The report uses a bibliometric analysis – statistical methods analysing trends in peer-reviewed research – to determine what percentage of the 333 research fields studied were publishing on artificial intelligence between 1960-2022. Analysing all disciplines of natural science, physical science, social science and the arts and humanities, the report found that only 14% of fields were publishing on artificial intelligence in 1960.

Turkey gets all the attention. Cranberry sauce ruffles feathers. But pumpkin pie is the lovable staple many Americans crave on Thanksgiving. And many don't want to make it themselves. That's why Sam's Club, a retail and grocery warehouse owned by Walmart, is using artificial intelligence to predict how much pie each of its nearly 600 stores needs to make for the holidays.Subscribe to The Post Most newsletter for the most important and interesting stories from The Washington Post. Their model use

Pong: a game so simple a bundle of lab-grown brain cells could play it. This might sound like a low blow, but it's true – last month, Australia-based startup Cortical Labs challenged its creation DishBrain, a biological computer chip that uses a combination of living neurons and silicon, to play the early console classic. The game – a 2D version of table tennis where players control a rectangle "paddle", moving it up and down to rally a ball – ran in the background, wired up to the DishBrain. Electrical stimulations were fed into the cells to represent the placement of the paddle and feedback was pinged when the ball was hit or missed. The scientists then measured the DishBrain's response, observing that it expended more or less energy depending on the position of the ball.

This week, craft beer company Bira landed new funding to expand its geographic reach while Torr FoodTech grabbed $12 million for its unusual and tech-centric approach to snack bars. In agtech, Clarifruit also raised $12 million while more layoffs struck the food delivery sector. Craft beer maker Bira 91 lands $70 million round led by beer company Kirin. Bira will use the funding to build more breweries and expand geographical reach of the Bira line of beverages. Sustainable grocery startup Modern Milkman raises £50 million ($60 million) after Series C close.

Four University of South Australia researchers have been awarded ARC Discovery grants collectively worth $1.8 million, for projects starting in 2023. The project will investigate the ways in which existing Australian induction policies support "precariously employed" early career teachers – those on casual and short-term contracts – to effectively manage student classroom behaviour. "We hope to propose alternative policy and practice recommendations to support the transition of insecure replacement teachers within the profession," Prof Sullivan says. "The benefits of this research include improving teachers' classroom management practices; the retention of new teachers; improving teacher workforce development; and building a healthier education system." Australia's 117,000 km of concrete sewer pipes are currently internally corroding at a depth rate of 1-3 mm per annum.

Combining multi-spectral satellite data and machine learning has been suggested as a method for monitoring plastic pollutants in the ocean environment. Recent studies have made theoretical progress regarding the identification of marine plastic via machine learning. However, no study has assessed the application of these methods for mapping and monitoring marine-plastic density. As such, this paper comprised of three main components: (1) the development of a machine learning model, (2) the construction of the MAP-Mapper, an automated tool for mapping marine-plastic density, and finally (3) an evaluation of the whole system for out-of-distribution test locations. The findings from this paper leverage the fact that machine learning models need to be high-precision to reduce the impact of false positives on results. The developed MAP-Mapper architectures provide users choices to reach high-precision ($\textit{abbv.}$ -HP) or optimum precision-recall ($\textit{abbv.}$ -Opt) values in terms of the training/test data set. Our MAP-Mapper-HP model greatly increased the precision of plastic detection to 95\%, whilst MAP-Mapper-Opt reaches precision-recall pair of 87\%-88\%. The MAP-Mapper contributes to the literature with the first tool to exploit advanced deep/machine learning and multi-spectral imagery to map marine-plastic density in automated software. The proposed data pipeline has taken a novel approach to map plastic density in ocean regions. As such, this enables an initial assessment of the challenges and opportunities of this method to help guide future work and scientific study.

Recent years have witnessed substantial growth in adaptive traffic signal control (ATSC) methodologies that improve transportation network efficiency, especially in branches leveraging artificial intelligence based optimization and control algorithms such as reinforcement learning as well as conventional model predictive control. However, lack of cross-domain analysis and comparison of the effectiveness of applied methods in ATSC research limits our understanding of existing challenges and research directions. This chapter proposes a novel unified view of modern ATSCs to identify common ground as well as differences and shortcomings of existing methodologies with the ultimate goal to facilitate cross-fertilization and advance the state-of-the-art. The unified view applies the mathematical language of the Markov decision process, describes the process of controller design from both the world (problem) and solution modeling perspectives. The unified view also analyses systematic issues commonly ignored in existing studies and suggests future potential directions to resolve these issues.