Image inpainting is a restoration method that reconstructs missing image parts. However, a carefully selected mask of known pixels that yield a high quality inpainting can also act as a sparse image representation. This challenging spatial optimisation problem is essential for practical applications such as compression. So far, it has been almost exclusively adressed by model-based approaches. First attempts with neural networks seem promising, but are tailored towards specific inpainting operators or require postprocessing. To address this issue, we propose the first generative adversarial network (GAN) for spatial inpainting data optimisation. In contrast to previous approaches, it allows joint training of an inpainting generator and a corresponding mask optimisation network. With a Wasserstein distance, we ensure that our inpainting results accurately reflect the statistics of natural images. This yields significant improvements in visual quality and speed over conventional stochastic models. It also outperforms current spatial optimisation networks.

Although machine learning and especially deep learning methods have played an important role in the field of information management, privacy protection is an important and concerning topic in current machine learning models. In information management field, a large number of texts containing personal information are produced by users every day. As the model training on information from users is likely to invade personal privacy, many methods have been proposed to block the learning and memorizing of the sensitive data in raw texts. In this paper, we try to do this more linguistically via distorting the text while preserving the semantics. In practice, we leverage a recently our proposed metric, Neighboring Distribution Divergence, to evaluate the semantic preservation during the distortion. Based on the metric, we propose two frameworks for semantics-preserved distortion, a generative one and a substitutive one. We conduct experiments on named entity recognition, constituency parsing, and machine reading comprehension tasks. Results from our experiments show the plausibility and efficiency of our distortion as a method for personal privacy protection. Moreover, we also evaluate the attribute attack on three privacy-related tasks in the current natural language processing field, and the results show the simplicity and effectiveness of our data-based improvement approach compared to the structural improvement approach. Further, we also investigate the effects of privacy protection in specific medical information management in this work and show that the medical information pre-training model using our approach can effectively reduce the memory of patients and symptoms, which fully demonstrates the practicality of our approach.

Electrocardiography (ECG), an electrical measurement which captures cardiac activities, is the gold standard for diagnosing cardiovascular disease (CVD). However, ECG is infeasible for continuous cardiac monitoring due to its requirement for user participation. By contrast, photoplethysmography (PPG) provides easy-to-collect data, but its limited accuracy constrains its clinical usage. To combine the advantages of both signals, recent studies incorporate various deep learning techniques for the reconstruction of PPG signals to ECG; however, the lack of contextual information as well as the limited abilities to denoise biomedical signals ultimately constrain model performance. In this research, we propose Performer, a novel Transformer-based architecture that reconstructs ECG from PPG and combines the PPG and reconstructed ECG as multiple modalities for CVD detection. This method is the first time that Transformer sequence-to-sequence translation has been performed on biomedical waveform reconstruction, combining the advantages of both PPG and ECG. We also create Shifted Patch-based Attention (SPA), an effective method to encode/decode the biomedical waveforms. Through fetching the various sequence lengths and capturing cross-patch connections, SPA maximizes the signal processing for both local features and global contextual representations. The proposed architecture generates a state-of-the-art performance of 0.29 RMSE for the reconstruction of PPG to ECG on the BIDMC database, surpassing prior studies. We also evaluated this model on the MIMIC-III dataset, achieving a 95.9% accuracy in CVD detection, and on the PPG-BP dataset, achieving 75.9% accuracy in related CVD diabetes detection, indicating its generalizability. As a proof of concept, an earring wearable named PEARL (prototype), was designed to scale up the point-of-care (POC) healthcare system.

The vast potential of Artificial Intelligence has hit a bump in the road following the refusal by several countries to patent inventions generated by an AI machine, says Macquarie Law School's Dr Rita Matulionyte. Macquarie Law School's Dr Rita Matulionyte, an international expert in intellectual property law, says the decisions – which have been challenged in overseas courts – signal a need for reform to ensure current law does not stifle innovation in an'immensely promising' sector. "This is the first case where an applicant is trying to patent AI-generated inventions and indicate AI as the inventor, whereas previously, patents granted over such AI inventions mentioned human beings as the inventors," Matulionyte says. The economic contribution of AI is potentially huge: according to Australia's AI roadmap, digital technologies including AI are potentially worth $A315 billion to Australia's economy by 2028, while AI alone could be worth $A22.17 Used by companies such as Coca-Cola and KFC to protect their secret recipes, trade secrets is another type of intellectual property law that could be available to AI inventions, Matulionyte says.

According to information published by the US DoD on November 23, 2022, U.S. 5th Fleet began a three-week unmanned and artificial intelligence integration event in Bahrain that will involve employing new platforms in the region for the first time. Various unmanned systems sit on display in Manama, Bahrain. The event, called Digital Horizon, will advance the command's efforts to integrate new unmanned technologies while establishing the world's first unmanned surface vessel fleet by end of next summer. U.S. 5th Fleet's efforts are focused on improving what U.S. and regional navies are able to see above, on and below the water. Digital Horizon will include 17 industry partners bringing 15 different types of systems, 10 of which will operate with U.S. 5th Fleet for the first time.

While artificial intelligence (AI) promises faster and smarter decision making, the Actuaries Institute and the Australian Human Rights Commission (AHRC) worry about potential discrimination and highlight the need to prevent this. To address the issue, they created a Guidance Resource designed to help insurers and actuaries to comply with the federal anti-discrimination legislation when AI is used in pricing or underwriting insurance products. The guidance was developed after a 2021 report by the AHRC that looked at the human rights impacts of new and emerging technologies, including AI-informed decision making. The Actuaries Institute strongly supported the report's recommendations to develop a set guidelines for use by the government and non-government organisations on complying with federal antidiscrimination laws when AI has been used in decision making. It approached the AHRC with a collaboration offer and together they developed these guidelines.

We consider the problem of learning Stochastic Differential Equations of the form $dX_t = f(X_t)dt+\sigma(X_t)dW_t $ from one sample trajectory. This problem is more challenging than learning deterministic dynamical systems because one sample trajectory only provides indirect information on the unknown functions $f$, $\sigma$, and stochastic process $dW_t$ representing the drift, the diffusion, and the stochastic forcing terms, respectively. We propose a method that combines Computational Graph Completion and data adapted kernels learned via a new variant of cross validation. Our approach can be decomposed as follows: (1) Represent the time-increment map $X_t \rightarrow X_{t+dt}$ as a Computational Graph in which $f$, $\sigma$ and $dW_t$ appear as unknown functions and random variables. (2) Complete the graph (approximate unknown functions and random variables) via Maximum a Posteriori Estimation (given the data) with Gaussian Process (GP) priors on the unknown functions. (3) Learn the covariance functions (kernels) of the GP priors from data with randomized cross-validation. Numerical experiments illustrate the efficacy, robustness, and scope of our method.

We propose AstroSLAM, a standalone vision-based solution for autonomous online navigation around an unknown target small celestial body. AstroSLAM is predicated on the formulation of the SLAM problem as an incrementally growing factor graph, facilitated by the use of the GTSAM library and the iSAM2 engine. By combining sensor fusion with orbital motion priors, we achieve improved performance over a baseline SLAM solution. We incorporate orbital motion constraints into the factor graph by devising a novel relative dynamics factor, which links the relative pose of the spacecraft to the problem of predicting trajectories stemming from the motion of the spacecraft in the vicinity of the small body. We demonstrate the excellent performance of AstroSLAM using both real legacy mission imagery and trajectory data courtesy of NASA's Planetary Data System, as well as real in-lab imagery data generated on a 3 degree-of-freedom spacecraft simulator test-bed.

We present Charles University submissions to the WMT22 General Translation Shared Task on Czech-Ukrainian and Ukrainian-Czech machine translation. We present two constrained submissions based on block back-translation and tagged back-translation and experiment with rule-based romanization of Ukrainian. Our results show that the romanization only has a minor effect on the translation quality. Further, we describe Charles Translator, a system that was developed in March 2022 as a response to the migration from Ukraine to the Czech Republic. Compared to our constrained systems, it did not use the romanization and used some proprietary data sources.

We present a non-autoregressive system submission to the WMT 22 Efficient Translation Shared Task. Our system was used by Helcl et al. (2022) in an attempt to provide fair comparison between non-autoregressive and autoregressive models. This submission is an effort to establish solid baselines along with sound evaluation methodology, particularly in terms of measuring the decoding speed. The model itself is a 12-layer Transformer model trained with connectionist temporal classification on knowledge-distilled dataset by a strong autoregressive teacher model.