A compliant parallel micromanipulator is a mechanism in which the moving platform is connected to the base through a number of flexural components. Utilizing parallel-kinematics configurations and flexure joints, the monolithic micromanipulators can achieve extremely high motion resolution and accuracy. In this work, the focus was towards the experimental evaluation of a 3-DOF ($Z{\theta}_{x}{\theta}_{y}$) monolithic flexure-based piezo-driven micromanipulator for precise out-of-plane micro/nano positioning applications. The monolithic structure avoids the deficiencies of non-monolithic designs such as backlash, wear, friction, and improves the performance of micromanipulator in terms of high resolution, accuracy, and repeatability. A computational study was conducted to investigate and obtain the inverse kinematics of the proposed micromanipulator. As a result of computational analysis, the developed prototype of the micromanipulator is capable of executing large motion range of $\pm$238.5$\mu$m $\times$ $\pm$4830.5$\mu$rad $\times$ $\pm$5486.2$\mu$rad. Finally, a sliding mode control strategy with nonlinear disturbance observer (SMC-NDO) was designed and implemented on the proposed micromanipulator to obtain system behaviors during experiments. The obtained results from different experimental tests validated the fine micromanipulator's positioning ability and the efficiency of the control methodology for precise micro/nano manipulation applications. The proposed micromanipulator achieved very fine spatial and rotational resolutions of $\pm$4nm, $\pm$250nrad, and $\pm$230nrad throughout its workspace.

Sparsity is a common issue in many trajectory datasets, including human mobility data. This issue frequently brings more difficulty to relevant learning tasks, such as trajectory imputation and prediction. Nowadays, little existing work simultaneously deals with imputation and prediction on human trajectories. This work plans to explore whether the learning process of imputation and prediction could benefit from each other to achieve better outcomes. And the question will be answered by studying the coexistence patterns between missing points and observed ones in incomplete trajectories. More specifically, the proposed model develops an imputation component based on the self-attention mechanism to capture the coexistence patterns between observations and missing points among encoder-decoder layers. Meanwhile, a recurrent unit is integrated to extract the sequential embeddings from newly imputed sequences for predicting the following location. Furthermore, a new implementation called Imputation Cycle is introduced to enable gradual imputation with prediction enhancement at multiple levels, which helps to accelerate the speed of convergence. The experimental results on three different real-world mobility datasets show that the proposed approach has significant advantages over the competitive baselines across both imputation and prediction tasks in terms of accuracy and stability.

Detecting abrupt changes in data distribution is one of the most significant tasks in streaming data analysis. Although many unsupervised Change-Point Detection (CPD) methods have been proposed recently to identify those changes, they still suffer from missing subtle changes, poor scalability, or/and sensitive to noise points. To meet these challenges, we are the first to generalise the CPD problem as a special case of the Change-Interval Detection (CID) problem. Then we propose a CID method, named iCID, based on a recent Isolation Distributional Kernel (IDK). iCID identifies the change interval if there is a high dissimilarity score between two non-homogeneous temporal adjacent intervals. The data-dependent property and finite feature map of IDK enabled iCID to efficiently identify various types of change points in data streams with the tolerance of noise points. Moreover, the proposed online and offline versions of iCID have the ability to optimise key parameter settings. The effectiveness and efficiency of iCID have been systematically verified on both synthetic and real-world datasets.

Australian universities have been forced to change the way they run exams and other assessments amid fears students are using emerging artificial intelligence software to write essays. Major institutions have added new rules which state that the use of AI is cheating, with some students already caught using the software. But one AI expert has warned universities are in an "arms race" they can never win. ChatGPT, which generates text on any subject in response to a prompt or query, was launched in November by OpenAI and has already been banned across all devices in New York's public schools due to concerns over its "negative impact on student learning" and potential for plagiarism. In London, one academic tested it against a 2022 exam question and said the AI's answer was "coherent, comprehensive and sticks to the points, something students often fail to do", adding he would have to "set a different kind of exam" or deprive students of internet access for future exams. In Australia, academics have cited concerns over ChatGPT and similar technology's ability to evade anti-plagiarism software while providing quick and credible academic writing.

We develop a fully data-driven model of anisotropic finite viscoelasticity using neural ordinary differential equations as building blocks. We replace the Helmholtz free energy function and the dissipation potential with data-driven functions that a priori satisfy physics-based constraints such as objectivity and the second law of thermodynamics. Our approach enables modeling viscoelastic behavior of materials under arbitrary loads in three-dimensions even with large deformations and large deviations from the thermodynamic equilibrium. The data-driven nature of the governing potentials endows the model with much needed flexibility in modeling the viscoelastic behavior of a wide class of materials. We train the model using stress-strain data from biological and synthetic materials including humain brain tissue, blood clots, natural rubber and human myocardium and show that the data-driven method outperforms traditional, closed-form models of viscoelasticity.

We present a new pre-training method, Multimodal Inverse Cloze Task, for Knowledge-based Visual Question Answering about named Entities (KVQAE). KVQAE is a recently introduced task that consists in answering questions about named entities grounded in a visual context using a Knowledge Base. Therefore, the interaction between the modalities is paramount to retrieve information and must be captured with complex fusion models. As these models require a lot of training data, we design this pre-training task from existing work in textual Question Answering. It consists in considering a sentence as a pseudo-question and its context as a pseudo-relevant passage and is extended by considering images near texts in multimodal documents. Our method is applicable to different neural network architectures and leads to a 9% relative-MRR and 15% relative-F1 gain for retrieval and reading comprehension, respectively, over a no-pre-training baseline.

Representation learning is important for solving sequence-to-sequence problems in natural language processing. Representation learning transforms raw data into vector-form representations while preserving their features. However, data with significantly different features leads to heterogeneity in their representations, which may increase the difficulty of convergence. We design a multi-filter encoder-decoder model to resolve the heterogeneity problem in sequence-to-sequence tasks. The multi-filter model divides the latent space into subspaces using a clustering algorithm and trains a set of decoders (filters) in which each decoder only concentrates on the features from its corresponding subspace. As for the main contribution, we design a self-enhancing mechanism that uses a reinforcement learning algorithm to optimize the clustering algorithm without additional training data. We run semantic parsing and machine translation experiments to indicate that the proposed model can outperform most benchmarks by at least 5\%. We also empirically show the self-enhancing mechanism can improve performance by over 10\% and provide evidence to demonstrate the positive correlation between the model's performance and the latent space clustering.

Adding interpretability to word embeddings represents an area of active research in text representation. Recent work has explored thepotential of embedding words via so-called polar dimensions (e.g. good vs. bad, correct vs. wrong). Examples of such recent approaches include SemAxis, POLAR, FrameAxis, and BiImp. Although these approaches provide interpretable dimensions for words, they have not been designed to deal with polysemy, i.e. they can not easily distinguish between different senses of words. To address this limitation, we present SensePOLAR, an extension of the original POLAR framework that enables word-sense aware interpretability for pre-trained contextual word embeddings. The resulting interpretable word embeddings achieve a level of performance that is comparable to original contextual word embeddings across a variety of natural language processing tasks including the GLUE and SQuAD benchmarks. Our work removes a fundamental limitation of existing approaches by offering users sense aware interpretations for contextual word embeddings.

A faithful and interpretable explanation of an AI model's behavior and internal structure is a high-level explanation that is human-intelligible but also consistent with the known, but often opaque low-level causal details of the model. We argue that the theory of causal abstraction provides the mathematical foundations for the desired kinds of model explanations. In causal abstraction analysis, we use interventions on model-internal states to rigorously assess whether an interpretable high-level causal model is a faithful description of an AI model. Our contributions in this area are: (1) We generalize causal abstraction to cyclic causal structures and typed high-level variables.

Entity and relation extraction is a key task in information extraction, where the output can be used for downstream NLP tasks. Existing approaches for entity and relation extraction tasks mainly focus on the English corpora and ignore other languages. Thus, it is critical to improving performance in a multilingual setting. Meanwhile, multilingual training is usually used to boost cross-lingual performance by transferring knowledge from languages (e.g., high-resource) to other (e.g., low-resource) languages. However, language interference usually exists in multilingual tasks as the model parameters are shared among all languages. In this paper, we propose a two-stage multilingual training method and a joint model called Multilingual Entity and Relation Extraction framework (mERE) to mitigate language interference across languages. Specifically, we randomly concatenate sentences in different languages to train a Language-universal Aggregator (LA), which narrows the distance of embedding representations by obtaining the unified language representation. Then, we separate parameters to mitigate interference via tuning a Language-specific Switcher (LS), which includes several independent sub-modules to refine the language-specific feature representation. After that, to enhance the relational triple extraction, the sentence representations concatenated with the relation feature are used to recognize the entities. Extensive experimental results show that our method outperforms both the monolingual and multilingual baseline methods. Besides, we also perform detailed analysis to show that mERE is lightweight but effective on relational triple extraction and mERE{} is easy to transfer to other backbone models of multi-field tasks, which further demonstrates the effectiveness of our method.