Everyone has probably heard of machine learning, but how exactly does it work? Does it mean that an intelligent machine makes decisions on behalf of humans? You might want to replace the term "intelligent machine" with "efficient algorithm" and add that this algorithm works with data. In doing so, it delivers a view that captures the essence of the data. Simply put, machine learning focuses on building models that learn from existing data and then uses those models to make logical decisions without requiring human intervention.

You have likely heard of ChatGPT, the artificial intelligence chatbot that can create original college essays that don't get flagged by plagiarism-detection software. Of course, it can do many things beyond confounding educators and delighting students. It can, for instance, write computer code. And, I discovered, give travel planning advice. To see how useful its travel suggestions might be, I began by asking what there is to see in Uturoa, the main town on the French Polynesian island of Raiatea.

Researchers from the University of Amsterdam, together with colleagues at the University of Queensland and the Norwegian Institute for Water Research, have developed a strategy for assessing the toxicity of chemicals using machine learning. The models developed in this study can lead to substantial improvements when compared to conventional'in silico' assessments based on quantitative structure-activity relationship (QSAR) modelling. According to the researchers, the use of machine learning can vastly improve the hazard assessment of molecules, both in the safe-by-design development of new chemicals and in the evaluation of existing chemicals. The importance of the latter is illustrated by the fact that European and US chemical agencies have listed approximately 800,000 chemicals that have been developed over the years but for which there is little to no knowledge about environmental fate or toxicity. Since an experimental assessment of chemical fate and toxicity requires much time, effort, and resources, modelling approaches are already used to predict hazard indicators.

Take a walk down any busy street and the noise can hit like a speaker accidentally left on full volume. The growls of engines accelerating when the traffic light turns green, motorbikes vying for position in the traffic, buses whizzing past and the odd rev-head all compete to be heard. The sound generated by the internal combustion engine has shaped urban life for a century, but that is gradually going to change: by 2050, 90% of cars in Australia will be electric. Australia is developing noise standards for electric cars that may follow similar rules set by the UN or US, industry experts say. But what exactly an electric car, and ultimately our cities, will sound like is under the creative control of carmakers.

Prediction of the electronic structure of functional materials is essential for the engineering of new devices. Conventional electronic structure prediction methods based on density functional theory (DFT) suffer from not only high computational cost, but also limited accuracy arising from the approximations of the exchange-correlation functional. Surrogate methods based on machine learning have garnered much attention as a viable alternative to bypass these limitations, especially in the prediction of solid-state band gaps, which motivated this research study. Herein, we construct a random forest regression model for band gaps of double perovskite materials, using a dataset of 1306 band gaps computed with the GLLBSC (Gritsenko, van Leeuwen, van Lenthe, and Baerends solid correlation) functional. Among the 20 physical features employed, we find that the bulk modulus, superconductivity temperature, and cation electronegativity exhibit the highest importance scores, consistent with the physics of the underlying electronic structure. Using the top 10 features, a model accuracy of 85.6% with a root mean square error of 0.64 eV is obtained, comparable to previous studies. Our results are significant in the sense that they attest to the potential of machine learning regressions for the rapid screening of promising candidate functional materials.

To build trust and confidence in the technology, laws should require organisations and governments to use AI in an ethical, safe and responsible manner that protects peoples' privacy. This means companies and the government must be accountable for the decisions their AI systems make. It means AI systems must be transparent and that an organisation can explain how a person's data is being used by the AI system. It means protections must be put in place to help reduce the risk that AI outputs are not biased or discriminatory. It means individuals are notified when AI is used to make a decision that affects their rights. It means there are boundaries on how high-risk AI systems can be used, and it means individuals have an appropriate legal recourse when those boundaries are broken.

We study the use of parametric building information modeling (BIM) to automatically generate training data for artificial neural networks (ANNs) to recognize building objects in photos. Teaching artificial intelligence (AI) machines to detect building objects in images is the foundation toward AI-assisted semantic 3D reconstruction of existing buildings. However, there exists the challenge of acquiring training data which is typically human-annotated, that is, unless a computer machine can generate high-quality data to train itself for a certain task. In that vein, we trained ANNs solely on realistic computer-generated images of 3D BIM models which were parametrically and automatically generated using the BIMGenE program. The ANN training result demonstrated generalizability and good semantic segmentation on a test case as well as arbitrary photos of buildings that are outside the range of the training data, which is significant for the future of training AI with generated data for solving real-world architectural problems.

ABSTRACT The TESS mission produces a large amount of time series data, only a small fraction of which contain detectable exoplanetary transit signals. Deep learning techniques such as neural networks have proved effective at differentiating promising astrophysical eclipsing candidates from other phenomena such as stellar variability and systematic instrumental effects in an efficient, unbiased and sustainable manner. This paper presents a high quality dataset containing light curves from the Primary Mission and 1st Extended Mission full frame images and periodic signals detected via Box Least Squares (Kovács et al. 2002; Hartman 2012). The dataset was curated using a thorough manual review process then used to train a neural network called Astronet-Triage-v2. On our test set, for transiting/eclipsing events we achieve a 99.6% recall (true positives over all data with positive labels) at a precision of 75.7% (true positives over all predicted positives). Since 90% of our training data is from the Primary Mission, we also test our ability to generalize on held-out 1st Extended Mission data. Here, we find an area under the precision-recall curve of 0.965, a 4% improvement over Astronet-Triage (Yu et al. 2019). On the TESS Object of Interest (TOI) Catalog through April 2022, a shortlist of planets and planet candidates, Astronet-Triage-v2 is able to recover 3577 out of 4140 TOIs, while Astronet-Triage only recovers 3349 targets at an equal level of precision. In other words, upgrading to Astronet-Triage-v2 helps save at least 200 planet candidates from being lost. The new model is currently used for planet candidate triage in the Quick-Look Pipeline (Huang et al. 2020a,b; Kunimoto et al. 2021). INTRODUCTION ally requires extremely precise observations.

Diabetic Retinopathy (DR) is considered one of the primary concerns due to its effect on vision loss among most people with diabetes globally. The severity of DR is mostly comprehended manually by ophthalmologists from fundus photography-based retina images. This paper deals with an automated understanding of the severity stages of DR. In the literature, researchers have focused on this automation using traditional machine learning-based algorithms and convolutional architectures. However, the past works hardly focused on essential parts of the retinal image to improve the model performance. In this paper, we adopt transformer-based learning models to capture the crucial features of retinal images to understand DR severity better. We work with ensembling image transformers, where we adopt four models, namely ViT (Vision Transformer), BEiT (Bidirectional Encoder representation for image Transformer), CaiT (Class-Attention in Image Transformers), and DeiT (Data efficient image Transformers), to infer the degree of DR severity from fundus photographs. For experiments, we used the publicly available APTOS-2019 blindness detection dataset, where the performances of the transformer-based models were quite encouraging.

Spear Phishing is a harmful cyber-attack facing business and individuals worldwide. Considerable research has been conducted recently into the use of Machine Learning (ML) techniques to detect spear-phishing emails. ML-based solutions may suffer from zero-day attacks; unseen attacks unaccounted for in the training data. As new attacks emerge, classifiers trained on older data are unable to detect these new varieties of attacks resulting in increasingly inaccurate predictions. Spear Phishing detection also faces scalability challenges due to the growth of the required features which is proportional to the number of the senders within a receiver mailbox. This differs from traditional phishing attacks which typically perform only a binary classification between phishing and benign emails. Therefore, we devise a possible solution to these problems, named RAIDER: Reinforcement AIded Spear Phishing DEtectoR. A reinforcement-learning based feature evaluation system that can automatically find the optimum features for detecting different types of attacks. By leveraging a reward and penalty system, RAIDER allows for autonomous features selection. RAIDER also keeps the number of features to a minimum by selecting only the significant features to represent phishing emails and detect spear-phishing attacks. After extensive evaluation of RAIDER over 11,000 emails and across 3 attack scenarios, our results suggest that using reinforcement learning to automatically identify the significant features could reduce the dimensions of the required features by 55% in comparison to existing ML-based systems. It also improves the accuracy of detecting spoofing attacks by 4% from 90% to 94%. In addition, RAIDER demonstrates reasonable detection accuracy even against a sophisticated attack named Known Sender in which spear-phishing emails greatly resemble those of the impersonated sender.