Annotateddimensionsinclude Valence, Arousal and Emotion label, with annotations gathered using Prolific.

We propose the novel concept of anomaly-free regions (AFR) to improve anomaly detection. An AFR is a region in the data space for which it is known that there are no anomalies inside it, e.g., via domain knowledge. This region can contain any number of normal data points and can be anywhere in the data space. AFRs have the key advantage that they constrain the estimation of the distribution of non-anomalies: The estimated probability mass inside the AFR must be consistent with the number of normal data points inside the AFR. Based on this insight, we provide a solid theoretical foundation and a reference implementation of anomaly detection using AFRs. Our empirical results confirm that anomaly detection constrained via AFRs improves upon unconstrained anomaly detection. Specifically, we show that, when equipped with an estimated AFR, an efficient algorithm based on random guessing becomes a strong baseline that several widely-used methods struggle to overcome. On a dataset with a ground-truth AFR available, the current state of the art is outperformed.

For explainable fault detection and classification (FDC), this paper proposes a unified framework, ABIGX (Adversarial fault reconstruction-Based Integrated Gradient eXplanation). ABIGX is derived from the essentials of previous successful fault diagnosis methods, contribution plots (CP) and reconstruction-based contribution (RBC). It is the first explanation framework that provides variable contributions for the general FDC models. The core part of ABIGX is the adversarial fault reconstruction (AFR) method, which rethinks the FR from the perspective of adversarial attack and generalizes to fault classification models with a new fault index. For fault classification, we put forward a new problem of fault class smearing, which intrinsically hinders the correct explanation. We prove that ABIGX effectively mitigates this problem and outperforms the existing gradient-based explanation methods. For fault detection, we theoretically bridge ABIGX with conventional fault diagnosis methods by proving that CP and RBC are the linear specifications of ABIGX. The experiments evaluate the explanations of FDC by quantitative metrics and intuitive illustrations, the results of which show the general superiority of ABIGX to other advanced explanation methods.

A major challenge to out-of-distribution generalization is reliance on spurious features -- patterns that are predictive of the class label in the training data distribution, but not causally related to the target. Standard methods for reducing the reliance on spurious features typically assume that we know what the spurious feature is, which is rarely true in the real world. Methods that attempt to alleviate this limitation are complex, hard to tune, and lead to a significant computational overhead compared to standard training. In this paper, we propose Automatic Feature Reweighting (AFR), an extremely simple and fast method for updating the model to reduce the reliance on spurious features. AFR retrains the last layer of a standard ERM-trained base model with a weighted loss that emphasizes the examples where the ERM model predicts poorly, automatically upweighting the minority group without group labels. With this simple procedure, we improve upon the best reported results among competing methods trained without spurious attributes on several vision and natural language classification benchmarks, using only a fraction of their compute.

Introduction: 12-lead electrocardiogram (ECG) is recorded during atrial fibrillation (AF) catheter ablation procedure (CAP). It is not easy to determine if CAP was successful without a long follow-up assessing for AF recurrence (AFR). Therefore, an AFR risk prediction algorithm could enable a better management of CAP patients. In this research, we extracted features from 12-lead ECG recorded before and after CAP and train an AFR risk prediction machine learning model. Methods: Pre- and post-CAP segments were extracted from 112 patients. The analysis included a signal quality criterion, heart rate variability and morphological biomarkers engineered from the 12-lead ECG (804 features overall). 43 out of the 112 patients (n) had AFR clinical endpoint available. These were utilized to assess the feasibility of AFR risk prediction, using either pre or post CAP features. A random forest classifier was trained within a nested cross validation framework. Results: 36 features were found statistically significant for distinguishing between the pre and post surgery states (n=112). For the classification, an area under the receiver operating characteristic (AUROC) curve was reported with AUROC_pre=0.64 and AUROC_post=0.74 (n=43). Discussion and conclusions: This preliminary analysis showed the feasibility of AFR risk prediction. Such a model could be used to improve CAP management.

Former Microsoft global AI bigwig Stela Solar says Australia has some of the world's best minds in artificial intelligence, but the country has …

Using artificial intelligence inspired by the human brain, a chip developed by BrainChip Holdings, is winning commercial support from large global …

The Telstra Corporation Ltd (ASX: TLS) share price is currently up as its artificial intelligence play makes headlines. The telco giant is going to work with Woolworths Group Ltd (ASX: WOW) controlled Quantium to help accelerate its use of AI, according to reporting by the Australian Financial Review. The AFR reported that Telstra and Quantium form a joint venture that will start by developing products and services for Telstra's enterprise customers in industries like mining, agribusiness and logistics. Telstra can provide the data, whilst the analytics and AI capabilities will be provided by Quantium. The Telstra CEO, Andy Penn, believes that this partnership will mean that it will be able to attract some of the top data talent.

The UK Court of Appeal has unanimously reached a decision against a face-recognition system used by South Wales Police. The judgment, which called the use of automated face recognition (AFR) "unlawful", could have ramifications for the widespread use of such technology across the UK. But there is disagreement about exactly what the consequences will be. Ed Bridges, who initially launched a case after police cameras digitally analysed his face in the street, had appealed, with the support of personal rights campaign group Liberty, against the use of face recognition by police. The police force claimed in court that the technology was similar to the use of closed-circuit television (CCTV) cameras in cities.

The use of automatic facial recognition (AFR) technology by South Wales Police is unlawful, the Court of Appeal has ruled. It follows a legal challenge brought by civil rights group Liberty and Ed Bridges, 37, from Cardiff. But the court also found its use was proportionate interference with human rights as the benefits outweighed the impact on Mr Bridges. South Wales Police said it would not be appealing the findings. Mr Bridges had said being identified by AFR caused him distress.