AI is revolutionizing GRC—automating audits, exposing hidden risks, and redefining compliance faster than regulators can react.
Category: robotics/AI – Page 10
AI Boosts Ocean Forecasting Accuracy and Speed
“The ability to resolve the Gulf Stream and its dynamics properly, has been an open challenge for many years in oceanography,” said Dr. Ashesh Chattopadhyay.
How can AI be used to predict ocean forecasting? This is what a recent study published in the Journal of Geophysical Research Machine Learning and Computation hopes to address as a team of researchers investigated how AI can be used to predict short-and long-term trends in ocean dynamics. This study has the potential to help scientists and the public better understand new methods estimating long-term ocean forecasting, specifically with climate change increasing ocean temperatures.
For the study, the researchers presented a new AI-based modeling tool for predicting ocean dynamics for the Gulf of Mexico, which is a major trade route between the United States and Mexico. The goal of the tool is to build upon longstanding physics-based models that have traditionally been used for predicting ocean dynamics, including temperature and changes in temperature.
In the end, the researchers found that this new model demonstrates improved performance in predicting ocean dynamics, specifically for short-term intervals of 30 days, along with long-term intervals of 10 years. The team aspires to use this new tool for modeling ocean dynamics worldwide.
Inside X0 and XTR-0
XTR-0 is the first way Extropic chips will be integrated with conventional computers. We intend to build more advanced systems around future TSUs that allow them to more easily integrate with conventional AI accelerators like GPUs. This could take the form of something simple like a PCIe card, or could in principle be as complicated as building a single chip that contains both a GPU and a TSU.
X0 houses a family of circuits that generate samples from primitive probability distributions. Our future chips will combine millions of these probabilistic circuits to run EBMs efficiently.
The probabilistic circuits on X0 output random continuous-time voltage signals. Repeatedly observing the signals (waiting sufficiently long between observations) allows a user to generate approximately independent samples from the distribution embodied by the circuit. These circuits are used to generate the random output voltage, making them much more energy efficient than their counterparts on deterministic digital computers.
Ultracompact semiconductor could power next-gen AI and 6G chips
A research team, led by Professor Heein Yoon in the Department of Electrical Engineering at UNIST has unveiled an ultra-small hybrid low-dropout regulator (LDO) that promises to advance power management in advanced semiconductor devices. This innovative chip not only stabilizes voltage more effectively, but also filters out noise—all while taking up less space—opening new doors for high-performance system-on-chips (SoCs) used in AI, 6G communications, and beyond.
The new LDO combines analog and digital circuit strengths in a hybrid design, ensuring stable power delivery even during sudden changes in current demand—like when launching a game on your smartphone—and effectively blocking unwanted noise from the power supply.
What sets this development apart is its use of a cutting-edge digital-to-analog transfer (D2A-TF) method and a local ground generator (LGG), which work together to deliver exceptional voltage stability and noise suppression. In tests, it kept voltage ripple to just 54 millivolts during rapid 99 mA current swings and managed to restore the voltage to its proper level in just 667 nanoseconds. Plus, it achieved a power supply rejection ratio (PSRR) of −53.7 dB at 10 kHz with a 100 mA load, meaning it can effectively filter out nearly all noise at that frequency.
Machine learning enables real-time analysis of iron oxide thin film growth in reactive magnetron sputtering
Researchers at University of Tsukuba have developed a technology for real-time estimation of the valence state and growth rate of iron oxide thin films during their formation. This novel technology was realized by analyzing the full-wavelength data of plasma emission spectra generated during reactive sputtering using machine learning. It is expected to enable high-precision control of the film deposition process.
Metal oxide and nitride thin films are commonly used in electronic devices and energy materials. Reactive sputtering is a versatile technique for depositing thin films by reacting a target metal with gases such as oxygen or nitrogen. A challenge with this process is the transitioning of the target surface between metallic and compound states, causing large fluctuations in film growth rate and composition. At present, there are limited effective methods for real-time monitoring of a material’s chemical state and deposition rate during film formation.
A machine learning technique based on principal component analysis was employed to examine massive emission spectra generated within a reactive sputter plasma. This analysis focused on assessing the state of thin film formation. The results, published in Science and Technology of Advanced Materials: Methods, indicated that the valence state of iron oxide thin films was accurately identified using only the first and second principal components of the spectra. In addition, the film growth rate was predicted with high precision.
Skin-inspired organic biosensors can reliably track health-related signals in real-time
The rapid advancement of sensing and artificial intelligence (AI) systems has paved the way for the introduction of increasingly sophisticated wearable devices, such as fitness trackers and technologies that closely monitor signals associated with specific diseases or medical conditions. Many of these wearable electronics rely on so-called biosensors, devices that can convert biological responses into measurable electrical signals in real-time.
While fitness trackers and other wearable electronics are now widely used, the signals that many existing devices pick up are sometimes inaccurate or distorted. This is because the bending of sensors, moisture and temperature fluctuations sometimes produce inaccurate readings and drifts (i.e., gradual changes that are unrelated to a measured signal).
Researchers at Stanford University have developed new skin-inspired biosensors based on organic field effect transistors (OFETs), devices based on organic semiconductors that control the flow of current in electronics.
