Machine learning
Deep reinforcement learning (DRL) has become a crucial aspect of artificial intelligence (AI), enabling machines to learn from trial and error. However, one of the significant challenges in DRL is learning the optimal state representation, which affects the learning speed and efficiency of the model. Researchers from the Tianjin University
Machine learning
Researchers from the Karlsruhe Institute of Technology (KIT) have made significant advancements in black-box optimization, a crucial aspect of machine learning, by developing a new algorithm that outperforms traditional methods in noisy and complex scenarios. The Model-based Relative Entropy Stochastic Search (MORE) algorithm, improved by decoupling the update of the
Machine learning
Artificial intelligence has become an integral part of our daily lives, but few know about its rich history that dates back to the 14th century. From automated chat devices to poetry-generating machines, the concept of AI has undergone significant transformations over the years. Dennis Yi Tenen, a scholar and software
Drug discovery
Researchers at the University of Massachusetts have identified the potential of Artificial Intelligence (AI), Machine Learning (ML), and Deep Learning (DL) models to revolutionize the pharmaceutical industry. According to a new study, these innovative methods can significantly assist in the development of new pharmaceutical compounds, which is a lengthy, costly,
Machine learning
Scientists at Schlumberger-Doll Research have developed a novel machine learning approach that enables cost-effective monitoring of methane leaks in the oil and gas industry. The researchers state that methane leaks are a significant component of greenhouse gas emissions, and it is crucial to frequently monitor these releases throughout the production
Machine learning
The COVID-19 pandemic has highlighted the inefficiencies in the global food supply chain, with close to a third of global food production being wasted, while millions of people struggle with food insecurity. With the population explosion and climate change adding pressure on the food system, reducing food waste has become
Machine learning
As technological advancements continue to drive innovation, the need for skilled professionals in cybersecurity has never been greater. With the growth of artificial intelligence, machine learning, and quantum computing, companies are facing unprecedented security threats that require experts with up-to-date knowledge and skills. According to the Bureau of Labor Statistics,
Machine learning
Researchers from Yonsei University have shed light on the significance of artificial intelligence in managing groundwater quality. The study, conducted between 2017 and 2020, employed a comprehensive Groundwater Quality Index (GQI) to evaluate potable groundwater quality across South Korea. The investigation highlighted the pressing need for policy revision, as over
Machine learning
Researchers at Suzhou University of Science and Technology have made a significant contribution to the field of machine learning by developing an accurate modeling and optimization technique for predicting the total energy consumption of air conditioning water systems. The study found that artificial neural networks (ANNs) outperformed other machine learning
Machine learning
Researchers from Nankai University have developed a self-training approach that leverages unlabeled data to address the problem of catastrophic forgetting in class-incremental semantic segmentation. This approach, titled "Self-training for Class-incremental Semantic Segmentation," has yielded state-of-the-art results on benchmark datasets, including a relative gain of up to 114% on
Machine learning
The latest patent disclosure describes a technical field related to a robot system used for delivering items, including a control method thereof. The present disclosure discloses a robot system and a method for controlling the robot system, with a first robot and a second robot performing smooth and efficient delivery
Machine learning
Recent research out of Boulder, Colorado, at the University of Colorado has made groundbreaking findings in the field of robotics. The study focuses on developing dense, high-resolution radar data from frequency modulated continuous wave radar sensors, along with sparse radar pointclouds produced by one of the radar sensors. The research
