EU lawmakers held their first political debate on the AI Act on Wednesday (5 October) as the discussion moved to more sensitive topics like the highly debated issue of biometric recognition. The AI Act is a landmark EU legislation intended to regulate Artificial Intelligence introducing a series of obligations proportional to the potential harm of the technologies' applications. So far, the co-rapporteurs of the European Parliament, the social democrat Brando Benifei and the liberal Dragoș Tudorache, have limited the discussion to the more technical aspects, hoping to build momentum before addressing the more political hurdles. This approach was not without its successes since the file progressed in several parts. In the meeting, the MEPs formally agreed on the first two batches of compromises on administrative procedures, conformity assessment, standards, and certificates.

NASA's Artemis program aims to send astronauts to the south pole of the Moon, where water in the form of ice has been confirmed, rather than near the equator as with the Apollo mission. The dark areas are likely to contain more ice than the others but also to be dangerous for the astronauts venturing there. A team of researchers studied these areas using deep learning, the study entitled "Cryogeomorphic Characterization of Shadowed Regions in the Artemis Exploration Zone" was published in Geophysical Research Letters. For the first Artemis lunar missions, the selected astronauts (one man and one woman) will fly to the south pole of the moon. This region has a great potential, it is thought to have the greatest abundance of water ice because it has craters where the sun's rays never penetrate, their temperature is estimated at -170 .

Legislation is an inherently human endeavor. But just as organizations across industries are unlocking new capabilities and efficiencies through artificial intelligence (AI), governments also can aid their legislative processes through the application of AI. For the past five years, we've studied the potential impact of AI on government. We've looked at everything from how much time AI could save workers in each US federal agency to the rate of AI adoption in US federal, state, and local governments.2 While AI can help many different areas of the legislative process--from AI assistants answering members' questions about legislation to natural language processing analyzing the US Code for contradictions--two key applications stand out.

Sitting on a mattress in an art gallery turned bunker in Kharkiv, with Russian munitions "howling and thumping" overhead, Dariia Selishcheva began making a video game. Jauntily titled What's Up in a Kharkiv Bomb Shelter, it was an attempt at self-distraction that evolved into a work of journalistic "autofiction". It offers a brief, vivid portrait of life under bombardment in the early months of Russia's unprovoked invasion of Ukraine, based closely on conversations with Selishcheva's neighbours in the shelter and correspondence with friends hiding elsewhere. "My goal was to provide an opportunity for ordinary people's voices to be heard, to capture a fragment of life in a shelter," Selishcheva says. "I wanted everyone to know about their lives and thoughts."

The United States Defense Department (DoD) has added more than a dozen Chinese companies, including the world's largest drone manufacturer, to a blacklist of firms with alleged ties to the Chinese military, clearing the way for restrictions on their business. Shenzhen-based DJI Technology, which is estimated to control more than half of the global market for commercial drones, is among the 13 firms added to the blacklist released by the Pentagon on Wednesday. The blacklist grants the US president authority to impose sanctions against companies deemed to have connections to the Chinese military. The announcement comes after the US Treasury Department last year banned US-based persons from trading shares of DJI and seven other Chinese companies over their alleged involvement in the surveillance of ethnic minority Uighurs in China's far-western region of Xinjiang. BGI Genomics Co, a genetic testing company; CRRC Corp, which manufactures rolling stock; and Zhejiang Dahua Technology, a Hangzhou-based surveillance equipment maker, were also added to the updated list.

A new computational approach will improve understanding of different states of carbon and guide the search for materials yet to be discovered. Materials--we use them, wear them, eat them and create them. Sometimes we invent them by accident, like with Silly Putty. But far more often, making useful materials is a tedious and expensive process of trial and error. Scientists at the U.S. Department of Energy's (DOE) Argonne National Laboratory have recently demonstrated an automated process for identifying and exploring promising new materials by combining machine learning (ML)--a type of artificial intelligence--and high performance computing.

Everyone knows that the Computer--an artificial intelligence (AI)-like entity--on a Star Trek spaceship does everything from brewing tea to compiling complex analyses of flux data. But how are they used at real research facilities? How can AI agents--computer programs that can act based on a perceived environment--help scientists discover next-generation batteries or quantum materials? Three staff members at the National Synchrotron Light Source II (NSLS-II) described how AI agents support scientists using the facility's research tools. As a U.S. Department of Energy's (DOE) Office of Science user facility located at DOE's Brookhaven National Laboratory, NSLS-II offers its experimental capabilities to scientists from all over the world who use it to reveal the mysteries of materials for tomorrow's technology.

Functional data analysis has long been used in modeling time series enabling long term predictions with the ability to We propose a novel group of Gaussian Process based algorithms work with irregularly sampled data [7]. In time series modeling, for fast approximate optimal stopping of time series with specific approaches based on Gaussian Processes (GPs) allow long term applications to financial markets. We show that structural properties forecasting in settings with small quantities of data for calibration commonly exhibited by financial time series (e.g., the tendency and those with a need to estimate the covariance of predictions [30, to mean-revert) allow the use of Gaussian and Deep Gaussian Process 17]. GPs also come up in finance when studying mean reverting models that further enable us to analytically evaluate optimal processes called Ornstein-Uhlenbeck (OU) processes which are GPs stopping value functions and policies. We additionally quantify with an exponential kernel [29].

We consider quantitative analyses of spectral data using laser-induced breakdown spectroscopy. We address the small size of training data available, and the validation of the predictions during inference on unknown data. For the purpose, we build robust calibration models using deep convolutional multitask learning architectures to predict the concentration of the analyte, alongside additional spectral information as auxiliary outputs. These secondary predictions can be used to validate the trustworthiness of the model by taking advantage of the mutual dependencies of the parameters of the multitask neural networks. Due to the experimental lack of training samples, we introduce a simulation-based data augmentation process to synthesise an arbitrary number of spectra, statistically representative of the experimental data. Given the nature of the deep learning model, no dimensionality reduction or data selection processes are required. The procedure is an end-to-end pipeline including the process of synthetic data augmentation, the construction of a suitable robust, homoscedastic, deep learning model, and the validation of its predictions. In the article, we compare the performance of the multitask model with traditional univariate and multivariate analyses, to highlight the separate contributions of each element introduced in the process.

Human visual reasoning allows us to leverage prior visual experience to recognize previously unseen Object-Attribute (O-A) relationships. Predicting such complex relationships of novel O-A compositions - referred to as Composition Zero Shot Learning (CZSL) [17, 19, 21, 22, 25, 28, 33, 36]-is an active area of research. There has been significant progress on CZSL methods in recent years, however, as our experiments demonstrate, their performance degrades in natural cluttered scenes, as illustrated in Fig.1. The main reason in these cases is the interference from the other potential confusing elements. For example, in Figure 1(B.1), the SOTA methods are not able to detect the object of interest given its size relative to image; and while the bird is the object of interest in Figure 1(B.2), the surrounding context dominated by the green leaves results in an incorrect association of the color attribute to the object. The poor performance of the SOTA methods can be attributed to the dominant confounding elements thereby impeding the right O-A composition prediction. This in turn is due to the bias towards seen O-A composition during training time. Generalization to more realistic cases as seen in Figure 1(B) is crucial for the widespread use of CZSL.