We address two bottlenecks for concise QBF encodings of maker-breaker positional games, like Hex and Tic-Tac-Toe. Our baseline is a QBF encoding with explicit variables for board positions and an explicit representation of winning configurations. The first improvement is inspired by lifted planning and avoids variables for explicit board positions, introducing a universal quantifier representing a symbolic board state. The second improvement represents the winning configurations implicitly, exploiting their structure. The paper evaluates the size of several encodings, depending on board size and game depth. It also reports the performance of QBF solvers on these encodings. We evaluate the techniques on Hex instances and also apply them to Harary's Tic-Tac-Toe. In particular, we study scalability to 19$\times$19 boards, played in human Hex tournaments.

Reinforcement learning (RL) has been widely used in text generation to alleviate the exposure bias issue or to utilize non-parallel datasets. The reward function plays an important role in making RL training successful. However, previous reward functions are typically task-specific and sparse, restricting the use of RL. In our work, we propose a task-agnostic approach that derives a step-wise reward function directly from a model trained with teacher forcing. We additionally propose a simple modification to stabilize the RL training on non-parallel datasets with our induced reward function. Empirical results show that our method outperforms self-training and reward regression methods on several text generation tasks, confirming the effectiveness of our reward function.

This paper investigates task-oriented communication for edge inference, where a low-end edge device transmits the extracted feature vector of a local data sample to a powerful edge server for processing. It is critical to encode the data into an informative and compact representation for low-latency inference given the limited bandwidth. We propose a learning-based communication scheme that jointly optimizes feature extraction, source coding, and channel coding in a task-oriented manner, i.e., targeting the downstream inference task rather than data reconstruction. Specifically, we leverage an information bottleneck (IB) framework to formalize a rate-distortion tradeoff between the informativeness of the encoded feature and the inference performance. As the IB optimization is computationally prohibitive for the high-dimensional data, we adopt a variational approximation, namely the variational information bottleneck (VIB), to build a tractable upper bound. To reduce the communication overhead, we leverage a sparsity-inducing distribution as the variational prior for the VIB framework to sparsify the encoded feature vector. Furthermore, considering dynamic channel conditions in practical communication systems, we propose a variable-length feature encoding scheme based on dynamic neural networks to adaptively adjust the activated dimensions of the encoded feature to different channel conditions. Extensive experiments evidence that the proposed task-oriented communication system achieves a better rate-distortion tradeoff than baseline methods and significantly reduces the feature transmission latency in dynamic channel conditions.

As an alcoholic beverage, wine has remained prevalent for thousands of years, and the quality assessment of wines has been significant in wine production and trade. Scholars have proposed various deep learning and machine learning algorithms for wine quality prediction, such as Support vector machine (SVM), Random Forest (RF), K-nearest neighbors (KNN), Deep neural network (DNN), and Logistic regression (LR). However, these methods ignore the inner relationship between the physical and chemical properties of the wine, for example, the correlations between pH values, fixed acidity, citric acid, and so on. To fill the gap, this paper conducts the Pearson correlation analysis, PCA analysis, and Shapiro-Wilk test on those properties and incorporates 1D-CNN architecture to capture the correlations among neighboring features. In addition, it implemented dropout and batch normalization techniques to improve the robustness of the proposed model. Massive experiments have shown that our method can outperform baseline approaches in wine quality prediction. Moreover, ablation experiments also demonstrate the effectiveness of incorporating the 1-D CNN module, Dropout, and normalization techniques.

Many types of data from fields including natural language processing, computer vision, and bioinformatics, are well represented by discrete, compositional structures such as trees, sequences, or matchings. Latent structure models are a powerful tool for learning to extract such representations, offering a way to incorporate structural bias, discover insight about the data, and interpret decisions. However, effective training is challenging, as neural networks are typically designed for continuous computation. This text explores three broad strategies for learning with discrete latent structure: continuous relaxation, surrogate gradients, and probabilistic estimation. Our presentation relies on consistent notations for a wide range of models. As such, we reveal many new connections between latent structure learning strategies, showing how most consist of the same small set of fundamental building blocks, but use them differently, leading to substantially different applicability and properties.

In audio processing applications, the generation of expressive sounds based on high-level representations demonstrates a high demand. These representations can be used to manipulate the timbre and influence the synthesis of creative instrumental notes. Modern algorithms, such as neural networks, have inspired the development of expressive synthesizers based on musical instrument timbre compression. Unsupervised deep learning methods can achieve audio compression by training the network to learn a mapping from waveforms or spectrograms to low-dimensional representations. This study investigates the use of stacked convolutional autoencoders for the compression of time-frequency audio representations for a variety of instruments for a single pitch. Further exploration of hyper-parameters and regularization techniques is demonstrated to enhance the performance of the initial design. In an unsupervised manner, the network is able to reconstruct a monophonic and harmonic sound based on latent representations. In addition, we introduce an evaluation metric to measure the similarity between the original and reconstructed samples. Evaluating a deep generative model for the synthesis of sound is a challenging task. Our approach is based on the accuracy of the generated frequencies as it presents a significant metric for the perception of harmonic sounds. This work is expected to accelerate future experiments on audio compression using neural autoencoders.

Cicada Innovations has acquired custodianship of Australia's longest-running annual deep technology conference Tech23 as the capital raised by their deep tech companies eclipses $5.7 billion. Tech23 and Cicada Innovations have always been united by a shared mission to celebrate and support Australian deep tech innovators, with both organisations boasting a lengthy track record of nurturing some of Australia's most successful companies: For 13 years, Tech23 has showcased and championed over 300 of Australia's most promising high-growth deep tech companies, while providing a mechanism for venture capital, other investors, media, advisors, policy makers, and potential local and global customers to learn about and connect with these companies. The event, planned for July 2023, will ask big questions about how we build the future – from sustainable cities to game-changing climate solutions and completely new paradigms of human health. Creating a space to connect and spark meaningful conversations about the ideas, technology, and innovators that can propel humanity into a better tomorrow. Cicada will take a proactive approach to finding the next 23 startups, setting out on a national road show in early 2023 to engage with local ecosystems and unearth emerging deep tech voices and give them national platform and vital exposure and support.

The SKA pulsar search pipeline will be used for real time detection of pulsars. Modern radio telescopes such as SKA will be generating petabytes of data in their full scale of operation. Hence experience-based and datadriven algorithms are being investigated for applications such as candidate detection. Here we describe our findings from testing a state of the art object detection algorithm called Mask R-CNN to detect candidate signatures in the SKA pulsar search pipeline. We have trained the Mask R-CNN model to detect candidate images. A custom semi-auto annotation tool was developed and investigated to rapidly mark the regions of interest in large datasets. We have used a simulation dataset to train and build the candidate detection algorithm. A more detailed analysis is planned. The paper presents details of this initial investigation highlighting the future prospects.

Construction of dictionaries using nonnegative matrix factorisation (NMF) has extensive applications in signal processing and machine learning. With the advances in deep learning, training compact and robust dictionaries using deep neural networks, i.e., dictionaries of deep features, has been proposed. In this study, we propose a probabilistic generative model which employs a variational autoencoder (VAE) to perform nonnegative dictionary learning. In contrast to the existing VAE models, we cast the model under a statistical framework with latent variables obeying a Gamma distribution and design a new loss function to guarantee the nonnegative dictionaries. We adopt an acceptance-rejection sampling reparameterization trick to update the latent variables iteratively. We apply the dictionaries learned from VAE-NMF to two signal processing tasks, i.e., enhancement of speech and extraction of muscle synergies. Experimental results demonstrate that VAE-NMF performs better in learning the latent nonnegative dictionaries in comparison with state-of-the-art methods.

Image-text contrastive learning models such as CLIP have demonstrated strong task transfer ability. The high generality and usability of these visual models is achieved via a web-scale data collection process to ensure broad concept coverage, followed by expensive pre-training to feed all the knowledge into model weights. Alternatively, we propose REACT, REtrieval-Augmented CusTomization, a framework to acquire the relevant web knowledge to build customized visual models for target domains. We retrieve the most relevant image-text pairs (~3% of CLIP pre-training data) from the web-scale database as external knowledge, and propose to customize the model by only training new modualized blocks while freezing all the original weights. The effectiveness of REACT is demonstrated via extensive experiments on classification, retrieval, detection and segmentation tasks, including zero, few, and full-shot settings. Particularly, on the zero-shot classification task, compared with CLIP, it achieves up to 5.4% improvement on ImageNet and 3.7% on the ELEVATER benchmark (20 datasets).