The combinatorial pure exploration of causal bandits is the following online learning task: given a causal graph with unknown causal inference distributions, in each round we choose a subset of variables to intervene or do no intervention, and observe the random outcomes of all random variables, with the goal that using as few rounds as possible, we can output an intervention that gives the best (or almost best) expected outcome on the reward variable $Y$ with probability at least $1-\delta$, where $\delta$ is a given confidence level. We provide the first gap-dependent and fully adaptive pure exploration algorithms on two types of causal models -- the binary generalized linear model (BGLM) and general graphs. For BGLM, our algorithm is the first to be designed specifically for this setting and achieves polynomial sample complexity, while all existing algorithms for general graphs have either sample complexity exponential to the graph size or some unreasonable assumptions. For general graphs, our algorithm provides a significant improvement on sample complexity, and it nearly matches the lower bound we prove. Our algorithms achieve such improvement by a novel integration of prior causal bandit algorithms and prior adaptive pure exploration algorithms, the former of which utilize the rich observational feedback in causal bandits but are not adaptive to reward gaps, while the latter of which have the issue in reverse.

Abstract--In this paper, we propose an explanation of representation for self-attention network (SAN) based neural sequence encoders, which regards the information captured by the model and the encoding of the model as graph structure and the generation of these graph structures respectively. The proposed explanation applies to existing works on SAN-based models and can explain the relationship among the ability to capture the structural or linguistic information, depth of model, and length of sentence, and can also be extended to other models such as recurrent neural network based models. We also propose a revisited multigraph called Multi-order-Graph (MoG) based on our explanation to model the graph structures in the SAN-based model as subgraphs in MoG and convert the encoding of SAN-based model to the generation of MoG. Based on our explanation, we further introduce a Graph-Transformer by enhancing the ability to capture multiple subgraphs of different orders and focusing on subgraphs of high orders. Experimental results on multiple neural machine translation tasks show that the Graph-Transformer can yield effective performance improvement. These works show that SAN-based models can embed structural which the encoder takes a sentence as input and generates the and linguistic information, and the information embedding ability corresponding contextualized representations for the decoder for is related to the model depth and sentence length. So far, although NLP tasks with various we may get intuitions as follows, (1) different layers in SANbased modeling ways, generally, there are mainly three types of encoder models may deliver different sorts of information, (2) architectures, recurrent neural network (RNN) [1], [2], [3], convolutional increasing the depth of the model can improve the performance neural network (CNN), and self-attention network (SAN) while improvement may be tiny when the model is too deep, from Transformer [4].

Infectious diseases remain among the top contributors to human illness and death worldwide, among which many diseases produce epidemic waves of infection. The unavailability of specific drugs and ready-to-use vaccines to prevent most of these epidemics makes the situation worse. These force public health officials and policymakers to rely on early warning systems generated by reliable and accurate forecasts of epidemics. Accurate forecasts of epidemics can assist stakeholders in tailoring countermeasures, such as vaccination campaigns, staff scheduling, and resource allocation, to the situation at hand, which could translate to reductions in the impact of a disease. Unfortunately, most of these past epidemics exhibit nonlinear and non-stationary characteristics due to their spreading fluctuations based on seasonal-dependent variability and the nature of these epidemics. We analyse a wide variety of epidemic time series datasets using a maximal overlap discrete wavelet transform (MODWT) based autoregressive neural network and call it EWNet model. MODWT techniques effectively characterize non-stationary behavior and seasonal dependencies in the epidemic time series and improve the nonlinear forecasting scheme of the autoregressive neural network in the proposed ensemble wavelet network framework. From a nonlinear time series viewpoint, we explore the asymptotic stationarity of the proposed EWNet model to show the asymptotic behavior of the associated Markov Chain. We also theoretically investigate the effect of learning stability and the choice of hidden neurons in the proposal. From a practical perspective, we compare our proposed EWNet framework with several statistical, machine learning, and deep learning models. Experimental results show that the proposed EWNet is highly competitive compared to the state-of-the-art epidemic forecasting methods.

Scientists at a South Australian university are using biology from insects to build robots with a brain – technology that could become a game changer for police, defence and national security. "I'm giving a robot a brain so it can understand its environment," said Flinders University associate professor for autonomous systems, Dr Russell Brinkworth. His biologically-inspired robots have the ability to not just take a picture of the world, but interpret the surrounding environment and adapt accordingly. "Our current robots work well in structured environments that don't change. That sounds complex – but they're all the same," Dr Brinkworth said.

ChatGPT has answers for almost everything, but there's one answer we may not know for a while: will this tool turn out to be the genie its creators regret taking out of the bottle over unintended consequences in cybersecurity? BlackBerry surveyed 1,500 IT decision makers across North America, UK, and Australia and half (51 percent) predicted we're less than a year away from a cyberattack credited to ChatGPT. Three-quarters of respondents believe foreign states are already using ChatGPT for malicious purposes against other nations. The survey also exposed a perception that, while respondents see ChatGPT as being used for'good' purposes, 73 percent acknowledge its potential threat to cybersecurity and are either very or fairly concerned, proving Artificial Intelligence (AI) is a double-edged sword. The emergence of chatbots and AI-powered tools presents new challenges in cybersecurity, especially when they end up in the wrong hands.

Convolutional neural networks (CNNs) are a representative class of deep learning algorithms including convolutional computation that perform translation-invariant classification of input data based on their hierarchical architecture. However, classical convolutional neural network learning methods use the steepest descent algorithm for training, and the learning performance is greatly influenced by the initial weight settings of the convolutional and fully connected layers, requiring re-tuning to achieve better performance under different model structures and data. Combining the strengths of the simulated annealing algorithm in global search, we propose applying it to the hyperparameter search process in order to increase the effectiveness of convolutional neural networks (CNNs). In this paper, we introduce SA-CNN neural networks for text classification tasks based on Text-CNN neural networks and implement the simulated annealing algorithm for hyperparameter search. Experiments demonstrate that we can achieve greater classification accuracy than earlier models with manual tuning, and the improvement in time and space for exploration relative to human tuning is substantial.

Humans possess the extraordinary capability of learning a new concept even after minimal observation. To a greater extent, a child can distinguish a dog from a cat through a single picture [1]. This critical characteristic of human intelligence lies in the humans' ability to leverage obtained knowledge of prior experiences to unforeseen circumstances with small observation. Unlike the human learning paradigm, traditional machine learning (ML) and deep learning (DL) models train a specific task from scratch through: (a) the training phase in which a model is initiated randomly and then updated, and (b) the test phase in which the model evaluates. While ML and DL have obtained remarkable success in a wide range of applications, they are notorious for requiring a huge number of samples to generalize. In many real-world problems, collecting more data is costly, time-consuming, and even might not feasible due to physical system constraints [2]. Moreover, most ML and DL models presume that training and testing datasets have the same distribution [3]. Thus, their performance suffers under data distribution shifts [4].

Label distribution learning (LDL) is an effective method to predict the label description degree (a.k.a. label distribution) of a sample. However, annotating label distribution (LD) for training samples is extremely costly. So recent studies often first use label enhancement (LE) to generate the estimated label distribution from the logical label and then apply external LDL algorithms on the recovered label distribution to predict the label distribution for unseen samples. But this step-wise manner overlooks the possible connections between LE and LDL. Moreover, the existing LE approaches may assign some description degrees to invalid labels. To solve the above problems, we propose a novel method to learn an LDL model directly from the logical label, which unifies LE and LDL into a joint model, and avoids the drawbacks of the previous LE methods. Extensive experiments on various datasets prove that the proposed approach can construct a reliable LDL model directly from the logical label, and produce more accurate label distribution than the state-of-the-art LE methods.

Deep learning (DL) algorithms have been widely applied to short-term voltage stability (STVS) assessment in power systems. However, transferring the knowledge learned in one power grid to other power grids with topology changes is still a challenging task. This paper proposed a transferable DL-based model for STVS assessment by constructing the topology-aware voltage dynamic features from raw PMU data. Since the reactive power flow and grid topology are essential to voltage stability, the topology-aware and physics-informed voltage dynamic features are utilized to effectively represent the topological and temporal patterns from post-disturbance system dynamic trajectories. The proposed DL-based STVS assessment model is tested under random operating conditions on the New England 39-bus system. It has 99.99\% classification accuracy of the short-term voltage stability status using the topology-aware and physics-informed voltage dynamic features. In addition to high accuracy, the experiments show good adaptability to PMU errors. Moreover, The proposed STVS assessment method has outstanding performance on new grid topologies after fine-tuning. In particular, the highest accuracy reaches 99.68\% in evaluation, which demonstrates a good knowledge transfer ability of the proposed model for power grid topology change.

We conducted a human subject study of named entity recognition on a noisy corpus of conversational music recommendation queries, with many irregular and novel named entities. We evaluated the human NER linguistic behaviour in these challenging conditions and compared it with the most common NER systems nowadays, fine-tuned transformers. Our goal was to learn about the task to guide the design of better evaluation methods and NER algorithms. The results showed that NER in our context was quite hard for both human and algorithms under a strict evaluation schema; humans had higher precision, while the model higher recall because of entity exposure especially during pre-training; and entity types had different error patterns (e.g. frequent typing errors for artists). The released corpus goes beyond predefined frames of interaction and can support future work in conversational music recommendation.