Word representations are created using analogy context-based statistics and lexical relations on words. Word representations are inputs for the learning models in Natural Language Understanding (NLU) tasks. However, to understand language, knowing only the context is not sufficient. Reading between the lines is a key component of NLU. Embedding deeper word relationships which are not represented in the context enhances the word representation. This paper presents a word embedding which combines an analogy, context-based statistics using Word2Vec, and deeper word relationships using Conceptnet, to create an expanded word representation. In order to fine-tune the word representation, Self-Organizing Map is used to optimize it. The proposed word representation is compared with semantic word representations using Simlex 999. Furthermore, the use of 3D visual representations has shown to be capable of representing the similarity and association between words. The proposed word representation shows a Spearman correlation score of 0.886 and provided the best results when compared to the current state-of-the-art methods, and exceed the human performance of 0.78.

Modelling long-term dependencies is a challenge for recurrent neural networks. This is primarily due to the fact that gradients vanish during training, as the sequence length increases. Gradients can be attenuated by transition operators and are attenuated or dropped by activation functions. Canonical architectures like LSTM alleviate this issue by skipping information through a memory mechanism. We propose a new recurrent architecture (Non-saturating Recurrent Unit; NRU) that relies on a memory mechanism but forgoes both saturating activation functions and saturating gates, in order to further alleviate vanishing gradients. In a series of synthetic and real world tasks, we demonstrate that the proposed model is the only model that performs among the top 2 models across all tasks with and without long-term dependencies, when compared against a range of other architectures.

Symbolic regression has been shown to be quite useful in many domains from discovering scientific laws to industrial empirical modeling. Existing methods focus on numerically fitting the given data. However, in many domains, symbolically derivable properties of the desired expressions are known. We illustrate these "semantic priors" with leading powers (the polynomial behavior as the input approaches 0 and $\infty$). We introduce an expression generating neural network that significantly favors the generation of expressions with desired leading powers, even generalizing to powers not in the training set. We then describe our Neural-Guided Monte Carlo Tree Search (NG-MCTS) algorithm for symbolic regression. We extensively evaluate our method on thousands of symbolic regression tasks and desired expressions to show that it significantly outperforms baseline algorithms and exhibits discovery of novel expressions outside of the training set.

In this work, we propose a composition/decomposition framework for adversarially training generative models on composed data - data where each sample can be thought of as being constructed from a fixed number of components. In our framework, samples are generated by sampling components from component generators and feeding these components to a composition function which combines them into a "composed sample". This compositional training approach improves the modularity, extensibility and interpretability of Generative Adversarial Networks (GANs) - providing a principled way to incrementally construct complex models out of simpler component models, and allowing for explicit "division of responsibility" between these components. Using this framework, we define a family of learning tasks and evaluate their feasibility on two datasets in two different data modalities (image and text). Lastly, we derive sufficient conditions such that these compositional generative models are identifiable. Our work provides a principled approach to building on pre-trained generative models or for exploiting the compositional nature of data distributions to train extensible and interpretable models.

An important part of many machine learning workflows on graphs is vertex representation learning, i.e., learning a low-dimensional vector representation for each vertex in the graph. Recently, several powerful techniques for unsupervised representation learning have been demonstrated to give the state-of-the-art performance in downstream tasks such as vertex classification and edge prediction. These techniques rely on random walks performed on the graph in order to capture its structural properties. These structural properties are then encoded in the vector representation space. However, most contemporary representation learning methods only apply to static graphs while real-world graphs are often dynamic and change over time. Static representation learning methods are not able to update the vector representations when the graph changes; therefore, they must re-generate the vector representations on an updated static snapshot of the graph regardless of the extent of the change in the graph. In this work, we propose computationally efficient algorithms for vertex representation learning that extend random walk based methods to dynamic graphs. The computation complexity of our algorithms depends upon the extent and rate of changes (the number of edges changed per update) and on the density of the graph. We empirically evaluate our algorithms on real world datasets for downstream machine learning tasks of multi-class and multi-label vertex classification. The results show that our algorithms can achieve competitive results to the state-of-the-art methods while being computationally efficient.

In this tutorial a small introduction of machine learning focused on development will be done with one of the most used Java libraries for this purpose, Weka. The machine learning is a subfield of data science . If data science covers the entire process of obtaining knowledge, cleaning, analysis, visualization and data deployment, machine learning are the algorithms and techniques used in the analysis and modeling phase of this process. Within these, we will focus on supervised learning, which is often used for classification and regression problems. The classification can be applied when dealing with a discrete class, where the objective is to predict one of the mutually exclusive values in the target variable.

In a world first, an undersea robot has dispersed microscopic baby corals (coral larvae) to help scientists working to repopulate parts of the Great Barrier Reef during this year's mass coral spawning event. Professor Dunbabin engineered QUT's reef protector RangerBot into LarvalBot specifically for the coral restoration project led by Professor Harrison. The project builds on Professor Harrison's successful larval reseeding technique piloted on the southern Great Barrier Reef in 2016 and 2017 in collaboration with the Great Barrier Reef Foundation, the Great Barrier Reef Marine Park Authority (GBRMPA) and Queensland Parks & Wildlife Service (QPWS), following successful small scale trials in the Philippines funded by the Australian Centre for International Agricultural Research. "This year represents a big step up for our larval restoration research and the first time we've been able to capture coral spawn on a bigger scale using large floating spawn catchers then rearing them into tiny coral larvae in our specially constructed larval pools and settling them on damaged reef areas," Professor Harrison said. "Winning the GBRF's Reef Innovation Challenge meant that we could increase the scale of the work planned for this year using mega-sized spawn catchers and fast track an initial trial of LarvalBot as a novel method of dispersing the coral larvae out on to the Reef. "With further research and refinement, this technique has enormous potential to operate across large areas of reef and multiple sites in a way that hasn't previously been possible.

Pauline Pounds, Associate Professor at the University of Queensland, speaks about building robots that can endure children. She discusses the tradeoffs of designing a robot that can survive children and cannot harm the children. Pounds talks about how the robot has performed with children so far, the hardware design, and her future direction with this work.

QUT researchers have developed an algorithm that can predict where a tennis player will hit the next ball by analysing Australian Open data of thousands of shots by the top male tennis players. Dr Simon Denman, a Senior Research Fellow with the Speech, Audio, Image and Video Technology Laboratory, said the research into the match play of Novak Djokovic, Rafael Nadal and Roger Federer could lead to new ways for professional tennis players to predict their opponent's moves or virtual reality games offering the chance to go head-to-head with world's best players in an accurate but artificial grand slam. Dr Denman is part of a team of QUT researchers, including PhD student Tharindu Fernando, Professor Sridha Sridharan and Professor Clinton Fookes, all from the Vision and Signal Processing Discipline at QUT, who created the algorithm for predicting the next shot in tennis using Hawk-Eye data from the 2012 Australian Tennis Open, provided by Tennis Australia. The researchers narrowed their focus to study just the shot selection of Djokovic, Nadal and Federer because they had the complete data to input into the system on how the players' shot selection changed as the tournament progressed. The researchers analysed more than 3400 shots for Djokovic, nearly 3500 shots for Nadal and almost 1900 shots by Federer, adding context for each shot such as whether it was a return, a winner or an error.

Victoria has sanctioned a trial of driverless cars on rural roads in a bid to improve the dramatically more dangerous conditions outside urban areas. People are five times more likely to be killed on a Victorian country road than in the city. The automated vehicle technology is being developed by Bosch as part of a $2.3m state government grant and will be tested on high-speed rural roads later this year. "This trial is an exciting step towards driverless vehicles hitting the road," the acting premier, Jacinta Allan, said. Bosch has been granted the state's first permit to allow automated vehicles for on-road testing, with other successful applicants to be announced soon.