If autonomous AI systems are to be reliably safe in novel situations, they will need to incorporate general principles guiding them to recognize and avoid harmful behaviours. Such principles may need to be supported by a binding system of regulation, which would need the underlying principles to be widely accepted. They should also be specific enough for technical implementation. Drawing inspiration from law, this article explains how negative human rights could fulfil the role of such principles and serve as a foundation both for an international regulatory system and for building technical safety constraints for future AI systems.

This paper proposes a generalised and robust multi-factor Gated Recurrent Unit (GRU) based Deep Learning (DL) model to forecast electricity load in distribution networks during wildfire seasons. The flexible modelling methods consider data input structure, calendar effects and correlation-based leading temperature conditions. Compared to the regular use of instantaneous temperature, the Mean Absolute Percentage Error (MAPE) is decreased by 30.73% by using the proposed input feature selection and leading temperature relationships. Our model is generalised and applied to eight real distribution networks in Victoria, Australia, during the wildfire seasons of 2015-2020. We demonstrate that the GRU-based model consistently outperforms another DL model, Long Short-Term Memory (LSTM), at every step, giving average improvements in Mean Squared Error (MSE) and MAPE of 10.06% and 12.86%, respectively. The sensitivity to large-scale climate variability in training data sets, e.g. El Ni\~no or La Ni\~na years, is considered to understand the possible consequences for load forecasting performance stability, showing minimal impact. Other factors such as regional poverty rate and large-scale off-peak electricity use are potential factors to further improve forecast performance. The proposed method achieves an average forecast MAPE of around 3%, giving a potential annual energy saving of AU\$80.46 million for the state of Victoria.

Satellite Image Time Series (SITS) of the Earth's surface provide detailed land cover maps, with their quality in the spatial and temporal dimensions consistently improving. These image time series are integral for developing systems that aim to produce accurate, up-to-date land cover maps of the Earth's surface. Applications are wide-ranging, with notable examples including ecosystem mapping, vegetation process monitoring and anthropogenic land-use change tracking. Recently proposed methods for SITS classification have demonstrated respectable merit, but these methods tend to lack native mechanisms that exploit the temporal dimension of the data; commonly resulting in extensive data pre-processing contributing to prohibitively long training times. To overcome these shortcomings, Temporal CNNs have recently been employed for SITS classification tasks with encouraging results. This paper seeks to survey this method against a plethora of other contemporary methods for SITS classification to validate the existing findings in recent literature. Comprehensive experiments are carried out on two benchmark SITS datasets with the results demonstrating that Temporal CNNs display a superior performance to the comparative benchmark algorithms across both studied datasets, achieving accuracies of 95.0\% and 87.3\% respectively. Investigations into the Temporal CNN architecture also highlighted the non-trivial task of optimising the model for a new dataset.

Deaf individuals confront significant communication obstacles on a daily basis. Their inability to hear makes it difficult for them to communicate with those who do not understand sign language. Moreover, it presents difficulties in educational, occupational, and social contexts. By providing alternative communication channels, technology can play a crucial role in overcoming these obstacles. One such technology that can facilitate communication between deaf and hearing individuals is sign language recognition. We will create a robust system for sign language recognition in order to convert Indian Sign Language to text or speech. We will evaluate the proposed system and compare CNN and LSTM models. Since there are both static and gesture sign languages, a robust model is required to distinguish between them. In this study, we discovered that a CNN model captures letters and characters for recognition of static sign language better than an LSTM model, but it outperforms CNN by monitoring hands, faces, and pose in gesture sign language phrases and sentences. The creation of a text-to-sign language paradigm is essential since it will enhance the sign language-dependent deaf and hard-of-hearing population's communication skills. Even though the sign-to-text translation is just one side of communication, not all deaf or hard-of-hearing people are proficient in reading or writing text. Some may have difficulty comprehending written language due to educational or literacy issues. Therefore, a text-to-sign language paradigm would allow them to comprehend text-based information and participate in a variety of social, educational, and professional settings. Keywords: deaf and hard-of-hearing, DHH, Indian sign language, CNN, LSTM, static and gesture sign languages, text-to-sign language model, MediaPipe Holistic, sign language recognition, SLR, SLT

Deep reinforcement learning algorithms that learn policies by trial-and-error must learn from limited amounts of data collected by actively interacting with the environment. While many prior works have shown that proper regularization techniques are crucial for enabling data-efficient RL, a general understanding of the bottlenecks in data-efficient RL has remained unclear. Consequently, it has been difficult to devise a universal technique that works well across all domains. In this paper, we attempt to understand the primary bottleneck in sample-efficient deep RL by examining several potential hypotheses such as non-stationarity, excessive action distribution shift, and overfitting. We perform thorough empirical analysis on state-based DeepMind control suite (DMC) tasks in a controlled and systematic way to show that high temporal-difference (TD) error on the validation set of transitions is the main culprit that severely affects the performance of deep RL algorithms, and prior methods that lead to good performance do in fact, control the validation TD error to be low. This observation gives us a robust principle for making deep RL efficient: we can hill-climb on the validation TD error by utilizing any form of regularization techniques from supervised learning. We show that a simple online model selection method that targets the validation TD error is effective across state-based DMC and Gym tasks. Reinforcement learning (RL) methods, when combined with high-capacity deep neural net function approximators, have shown promise in domains such as robot manipulation (Andrychowicz et al., 2020), chip placement (Mirhoseini et al., 2020), games (Silver et al., 2016), and data-center cooling (Lazic et al., 2018). Since every unit of active online data collection comes at an expense (e.g., running real robots, chip evaluation using simulation), it is important to develop sample-efficient deep RL algorithms, that can learn efficiently even with limited amount of experience. Devising such efficient RL algorithm has been an important thread of research in recent years (Janner et al., 2019; Chen et al., 2021; Hiraoka et al., 2021). In principle, off-policy RL methods (e.g., SAC (Haarnoja et al., 2018), TD3 (Fujimoto et al., 2018), Rainbow (Hessel et al., 2018)) should provide good sample efficiency, because they make it possible to improve the policy and value functions for many gradient steps per step of data collection. However, this benefit does not appear to be realizable in practice, as taking too many training steps per each collected transition actually harms performance in many environments.

We introduce CPDL+, a family of expressive logics rooted in Propositional Dynamic Logic (PDL). In terms of expressive power, CPDL+ strictly contains PDL extended with intersection and converse (a.k.a. ICPDL) as well as Conjunctive Queries (CQ), Conjunctive Regular Path Queries (CRPQ), or some known extensions thereof (Regular Queries and CQPDL). We investigate the expressive power, characterization of bisimulation, satisfiability, and model checking for CPDL+. We argue that natural subclasses of CPDL+ can be defined in terms of the tree-width of the underlying graphs of the formulas. We show that the class of CPDL+ formulas of tree-width 2 is equivalent to ICPDL, and that it also coincides with CPDL+ formulas of tree-width 1. However, beyond tree-width 2, incrementing the tree-width strictly increases the expressive power. We characterize the expressive power for every class of fixed tree-width formulas in terms of a bisimulation game with pebbles. Based on this characterization, we show that CPDL+ has a tree-like model property. We prove that the satisfiability problem is decidable in 2ExpTime on fixed tree-width formulas, coinciding with the complexity of ICPDL. We also exhibit classes for which satisfiability is reduced to ExpTime. Finally, we establish that the model checking problem for fixed tree-width formulas is in \ptime, contrary to the full class CPDL+.

Public attention towards explainability of artificial intelligence (AI) systems has been rising in recent years to offer methodologies for human oversight. This has translated into the proliferation of research outputs, such as from Explainable AI, to enhance transparency and control for system debugging and monitoring, and intelligibility of system process and output for user services. Yet, such outputs are difficult to adopt on a practical level due to a lack of a common regulatory baseline, and the contextual nature of explanations. Governmental policies are now attempting to tackle such exigence, however it remains unclear to what extent published communications, regulations, and standards adopt an informed perspective to support research, industry, and civil interests. In this study, we perform the first thematic and gap analysis of this plethora of policies and standards on explainability in the EU, US, and UK. Through a rigorous survey of policy documents, we first contribute an overview of governmental regulatory trajectories within AI explainability and its sociotechnical impacts. We find that policies are often informed by coarse notions and requirements for explanations. This might be due to the willingness to conciliate explanations foremost as a risk management tool for AI oversight, but also due to the lack of a consensus on what constitutes a valid algorithmic explanation, and how feasible the implementation and deployment of such explanations are across stakeholders of an organization. Informed by AI explainability research, we conduct a gap analysis of existing policies, leading us to formulate a set of recommendations on how to address explainability in regulations for AI systems, especially discussing the definition, feasibility, and usability of explanations, as well as allocating accountability to explanation providers.

The computational power of contemporary quantum processors is limited by hardware errors that cause computations to fail. In principle, each quantum processor's computational capabilities can be described with a capability function that quantifies how well a processor can run each possible quantum circuit (i.e., program), as a map from circuits to the processor's success rates on those circuits. However, capability functions are typically unknown and challenging to model, as the particular errors afflicting a specific quantum processor are a priori unknown and difficult to completely characterize. In this work, we investigate using artificial neural networks to learn an approximation to a processor's capability function. We explore how to define the capability function, and we explain how data for training neural networks can be efficiently obtained for a capability function defined using process fidelity. We then investigate using convolutional neural networks to model a quantum computer's capability. Using simulations, we show that convolutional neural networks can accurately model a processor's capability when that processor experiences gate-dependent, time-dependent, and context-dependent stochastic errors. We then discuss some challenges to creating useful neural network capability models for experimental processors, such as generalizing beyond training distributions and modelling the effects of coherent errors. Lastly, we apply our neural networks to model the capabilities of cloud-access quantum computing systems, obtaining moderate prediction accuracy (average absolute error around 2-5%).

The societal impact of pre-trained language models has prompted researchers to probe them for strong associations between protected attributes and value-loaded terms, from slur to prestigious job titles. Such work is said to probe models for bias or fairness-or such probes 'into representational biases' are said to be 'motivated by fairness'-suggesting an intimate connection between bias and fairness. We provide conceptual clarity by distinguishing between association biases (Caliskan et al., 2022) and empirical fairness (Shen et al., 2022) and show the two can be independent. Our main contribution, however, is showing why this should not come as a surprise. To this end, we first provide a thought experiment, showing how association bias and empirical fairness can be completely orthogonal. Next, we provide empirical evidence that there is no correlation between bias metrics and fairness metrics across the most widely used language models. Finally, we survey the sociological and psychological literature and show how this literature provides ample support for expecting these metrics to be uncorrelated.

Researchers have used artificial intelligence to create'ideal' pageant queen candidates as part of a study to explore the beauty standards of Miss United Kingdom and other global contests. The experts at Great Green Wall used online image generator Midjourney to do this, which gave a surprising variety of results for each country. While Miss United Kingdom was thought to have been influenced by Princess Diana, other nations were inspired by athletes, Bollywood and even Marilyn Monroe. Yet these images often included'highly unobtainable body proportions', researchers said, with'supermodel-like facial structures that can only be achieved through cosmetic surgery or genetics'. Founder of Great Green Wall, Sam Phoenix, wrote: 'Beauty standards can vary drastically from country to country, so it was fascinating to see how well the AI was able to recreate those unique beauty standards within a "pageant" setting.