An artificial intelligence system is capable of being an "inventor" under Australian patent law, the federal court has ruled, in a decision that could have wider intellectual property implications. University of Surrey professor Ryan Abbott has launched more than a dozen patent applications across the globe, including in the UK, US, New Zealand and Australia, on behalf of US-based Dr Stephen Thaler. They seek to have Thaler's artificial intelligence device known as Dabus (a device for the autonomous bootstrapping of unified sentience) listed as the inventor. The applications claimed Dabus, which is made up of artificial neural networks, invented an emergency warning light and a type of food container, among other inventions. Several countries, including Australia, had rejected the applications, stating a human must be named the inventor.

With digital marketing, good, clean, and insightful data is a key pillar which a business stands to drive growth and profits. Having clear and precise data-driven outcomes should be a priority for all marketers. When used in tandem with well-defined marketing and sales goals, and various marketing tools and techniques, companies will discover that their lead to sale conversion process can be far less cumbersome and more rewarding. Possessing clean data will help marketers identify detailed segments based on user attributes, past behaviours, interactions, and other necessary data points. Data can be leveraged for highly targeted campaigns which will drive marketing return on investment (ROI).

We investigate active learning in Gaussian Process state-space models (GPSSM). Our problem is to actively steer the system through latent states by determining its inputs such that the underlying dynamics can be optimally learned by a GPSSM. In order that the most informative inputs are selected, we employ mutual information as our active learning criterion. In particular, we present two approaches for the approximation of mutual information for the GPSSM given latent states. The proposed approaches are evaluated in several physical systems where we actively learn the underlying non-linear dynamics represented by the state-space model.

Neural language models (LM) trained on diverse corpora are known to work well on previously seen entities, however, updating these models with dynamically changing entities such as place names, song titles and shopping items requires re-training from scratch and collecting full sentences containing these entities. We aim to address this issue, by introducing entity-aware language models (EALM), where we integrate entity models trained on catalogues of entities into the pre-trained LMs. Our combined language model adaptively adds information from the entity models into the pre-trained LM depending on the sentence context. Our entity models can be updated independently of the pre-trained LM, enabling us to influence the distribution of entities output by the final LM, without any further training of the pre-trained LM. We show significant perplexity improvements on task-oriented dialogue datasets, especially on long-tailed utterances, with an ability to continually adapt to new entities (to an extent).

This thesis introduces the "method of structural refinement", which serves as a means of transforming the relational semantics of a modal and/or constructive logic into an 'economical' proof system by connecting two proof-theoretic paradigms: labelled and nested sequent calculi. The formalism of labelled sequents has been successful in that cut-free calculi in possession of desirable proof-theoretic properties can be automatically generated for large classes of logics. Despite these qualities, labelled systems make use of a complicated syntax that explicitly incorporates the semantics of the associated logic, and such systems typically violate the subformula property to a high degree. By contrast, nested sequent calculi employ a simpler syntax and adhere to a strict reading of the subformula property, making such systems useful in the design of automated reasoning algorithms. However, the downside of the nested sequent paradigm is that a general theory concerning the automated construction of such calculi (as in the labelled setting) is essentially absent, meaning that the construction of nested systems and the confirmation of their properties is usually done on a case-by-case basis. The refinement method connects both paradigms in a fruitful way, by transforming labelled systems into nested (or, refined labelled) systems with the properties of the former preserved throughout the transformation process. To demonstrate the method of refinement and some of its applications, we consider grammar logics, first-order intuitionistic logics, and deontic STIT logics. The introduced refined labelled calculi will be used to provide the first proof-search algorithms for deontic STIT logics. Furthermore, we employ our refined labelled calculi for grammar logics to show that every logic in the class possesses the effective Lyndon interpolation property.

The government is wary of over-regulating new technologies such as artificial intelligence and will resist making ethics standards and codes mandatory for Australian businesses, Digital Economy minister Jane Hume says. In an address to the Committee for Economic Development of Australia (CEDA), Senator Hume said the federal government would play an enabling role in accelerating the growth of artificial intelligence, along with setting standards in terms of ethics. "AI, along with other digital technologies, will play an increasingly important role in our economy and society over the next decade and beyond," Senator Hume said. "As we continue to vault forward in this space, government has a pivotal role to play as an enabler, and as a standard setter – particularly in regards to ethics. "The government has a significant responsibility … to ensure that AI, as an industry as well as a technology, has every chance to flourish, making sure we have the right settings, skills and expertise in place to ensure Australia is a global forerunner." The May budget allocated $124 million to artificial intelligence initiatives, including $50 million for a National AI Intelligence Centre within CSIRO and $34 million in grants for AI projects addressing national challenges. The Coalition has also unveiled AI ethics principles, with eight guiding principles "designed to help achieve safer and more reliable outcomes for all Australians". These principles and other standards around AI are currently entirely voluntary for Australian businesses, and Senator Hume said the government will avoid making them mandatory. "I obviously would rather have a voluntary code where industry has the input to what's in the code.

As the discipline has evolved, research in machine learning has been focused more and more on creating more powerful neural networks, without regard for the interpretability of these networks. Such "black-box models" yield state-of-the-art results, but we cannot understand why they make a particular decision or prediction. Sometimes this is acceptable, but often it is not. We propose a novel architecture, Regression Networks, which combines the power of neural networks with the understandability of regression analysis. While some methods for combining these exist in the literature, our architecture generalizes these approaches by taking interactions into account, offering the power of a dense neural network without forsaking interpretability. We demonstrate that the models exceed the state-of-the-art performance of interpretable models on several benchmark datasets, matching the power of a dense neural network. Finally, we discuss how these techniques can be generalized to other neural architectures, such as convolutional and recurrent neural networks.

Electricity load forecasting is crucial for the power systems' planning and maintenance. However, its un-stationary and non-linear characteristics impose significant difficulties in anticipating future demand. This paper proposes a novel ensemble deep Random Vector Functional Link (edRVFL) network for electricity load forecasting. The weights of hidden layers are randomly initialized and kept fixed during the training process. The hidden layers are stacked to enforce deep representation learning. Then, the model generates the forecasts by ensembling the outputs of each layer. Moreover, we also propose to augment the random enhancement features by empirical wavelet transformation (EWT). The raw load data is decomposed by EWT in a walk-forward fashion, not introducing future data leakage problems in the decomposition process. Finally, all the sub-series generated by the EWT, including raw data, are fed into the edRVFL for forecasting purposes. The proposed model is evaluated on twenty publicly available time series from the Australian Energy Market Operator of the year 2020. The simulation results demonstrate the proposed model's superior performance over eleven forecasting methods in three error metrics and statistical tests on electricity load forecasting tasks.

We introduce a new class of non-linear function-on-function regression models for functional data using neural networks. We propose a framework using a hidden layer consisting of continuous neurons, called a continuous hidden layer, for functional response modeling and give two model fitting strategies, Functional Direct Neural Network (FDNN) and Functional Basis Neural Network (FBNN). Both are designed explicitly to exploit the structure inherent in functional data and capture the complex relations existing between the functional predictors and the functional response. We fit these models by deriving functional gradients and implement regularization techniques for more parsimonious results. We demonstrate the power and flexibility of our proposed method in handling complex functional models through extensive simulation studies as well as real data examples.

The transformer has recently achieved impressive results on various tasks. To further improve the effectiveness and efficiency of the transformer, there are two trains of thought among existing works: (1) going wider by scaling to more trainable parameters; (2) going shallower by parameter sharing or model compressing along with the depth. However, larger models usually do not scale well when fewer tokens are available to train, and advanced parallelisms are required when the model is extremely large. Smaller models usually achieve inferior performance compared to the original transformer model due to the loss of representation power. In this paper, to achieve better performance with fewer trainable parameters, we propose a framework to deploy trainable parameters efficiently, by going wider instead of deeper. Specially, we scale along model width by replacing feed-forward network (FFN) with mixture-of-experts (MoE). We then share the MoE layers across transformer blocks using individual layer normalization. Such deployment plays the role to transform various semantic representations, which makes the model more parameter-efficient and effective. To evaluate our framework, we design WideNet and evaluate it on ImageNet-1K. Our best model outperforms Vision Transformer (ViT) by $1.46\%$ with $0.72 \times$ trainable parameters. Using $0.46 \times$ and $0.13 \times$ parameters, our WideNet can still surpass ViT and ViT-MoE by $0.83\%$ and $2.08\%$, respectively.