Articles tagged with Artificial Neural Networks
Comprehensive exploration of living organisms, biological systems, and life processes across all scales from molecules to ecosystems. Encompasses cutting-edge research in biology, genetics, molecular biology, ecology, biochemistry, microbiology, botany, zoology, evolutionary biology, genomics, and biotechnology. Investigates cellular mechanisms, organism development, genetic inheritance, biodiversity conservation, metabolic processes, protein synthesis, DNA sequencing, CRISPR gene editing, stem cell research, and the fundamental principles governing all forms of life on Earth.
Comprehensive medical research, clinical studies, and healthcare sciences focused on disease prevention, diagnosis, and treatment. Encompasses clinical medicine, public health, pharmacology, epidemiology, medical specialties, disease mechanisms, therapeutic interventions, healthcare innovation, precision medicine, telemedicine, medical devices, drug development, clinical trials, patient care, mental health, nutrition science, health policy, and the application of medical science to improve human health, wellbeing, and quality of life across diverse populations.
Comprehensive investigation of human society, behavior, relationships, and social structures through systematic research and analysis. Encompasses psychology, sociology, anthropology, economics, political science, linguistics, education, demography, communications, and social research methodologies. Examines human cognition, social interactions, cultural phenomena, economic systems, political institutions, language and communication, educational processes, population dynamics, and the complex social, cultural, economic, and political forces shaping human societies, communities, and civilizations throughout history and across the contemporary world.
Fundamental study of the non-living natural world, matter, energy, and physical phenomena governing the universe. Encompasses physics, chemistry, earth sciences, atmospheric sciences, oceanography, materials science, and the investigation of physical laws, chemical reactions, geological processes, climate systems, and planetary dynamics. Explores everything from subatomic particles and quantum mechanics to planetary systems and cosmic phenomena, including energy transformations, molecular interactions, elemental properties, weather patterns, tectonic activity, and the fundamental forces and principles underlying the physical nature of reality.
Practical application of scientific knowledge and engineering principles to solve real-world problems and develop innovative technologies. Encompasses all engineering disciplines, technology development, computer science, artificial intelligence, environmental sciences, agriculture, materials applications, energy systems, and industrial innovation. Bridges theoretical research with tangible solutions for infrastructure, manufacturing, computing, communications, transportation, construction, sustainable development, and emerging technologies that advance human capabilities, improve quality of life, and address societal challenges through scientific innovation and technological progress.
Study of the practice, culture, infrastructure, and social dimensions of science itself. Addresses how science is conducted, organized, communicated, and integrated into society. Encompasses research funding mechanisms, scientific publishing systems, peer review processes, academic ethics, science policy, research institutions, scientific collaboration networks, science education, career development, research programs, scientific methods, science communication, and the sociology of scientific discovery. Examines the human, institutional, and cultural aspects of scientific enterprise, knowledge production, and the translation of research into societal benefit.
Comprehensive study of the universe beyond Earth, encompassing celestial objects, cosmic phenomena, and space exploration. Includes astronomy, astrophysics, planetary science, cosmology, space physics, astrobiology, and space technology. Investigates stars, galaxies, planets, moons, asteroids, comets, black holes, nebulae, exoplanets, dark matter, dark energy, cosmic microwave background, stellar evolution, planetary formation, space weather, solar system dynamics, the search for extraterrestrial life, and humanity's efforts to explore, understand, and unlock the mysteries of the cosmos through observation, theory, and space missions.
Comprehensive examination of tools, techniques, methodologies, and approaches used across scientific disciplines to conduct research, collect data, and analyze results. Encompasses experimental procedures, analytical methods, measurement techniques, instrumentation, imaging technologies, spectroscopic methods, laboratory protocols, observational studies, statistical analysis, computational methods, data visualization, quality control, and methodological innovations. Addresses the practical techniques and theoretical frameworks enabling scientists to investigate phenomena, test hypotheses, gather evidence, ensure reproducibility, and generate reliable knowledge through systematic, rigorous investigation across all areas of scientific inquiry.
Study of abstract structures, patterns, quantities, relationships, and logical reasoning through pure and applied mathematical disciplines. Encompasses algebra, calculus, geometry, topology, number theory, analysis, discrete mathematics, mathematical logic, set theory, probability, statistics, and computational mathematics. Investigates mathematical structures, theorems, proofs, algorithms, functions, equations, and the rigorous logical frameworks underlying quantitative reasoning. Provides the foundational language and tools for all scientific fields, enabling precise description of natural phenomena, modeling of complex systems, and the development of technologies across physics, engineering, computer science, economics, and all quantitative sciences.
Researchers have developed a passive, solar-powered orbital data center that can scale AI computing and reduce environmental impact. The system leverages decades of research on 'tethers' and could host thousands of computing nodes to replicate terrestrial data centers.
Researchers have developed a method called PropMolFlow that can generate molecular candidates roughly 10 times faster than existing methods while maintaining accuracy. The breakthrough could lead to faster creation of pharmaceuticals, materials, and new technologies by specifying properties first and then finding structures.
The Global Brain Economy Initiative aims to establish brain capital as an essential asset for the 21st century, connecting neuroscience with economic policy. The initiative's mission is to address disparities in support for brain capital across various sectors and promote long-term growth, workforce resilience, and social well-being.
Researchers created a computational model that combines physiological signals, sensory input, and word information to construct human emotions. The model achieved an agreement rate of about 75% when compared to participants' self-reported emotional evaluations.
Engineers at the University of Pennsylvania have discovered that foams exhibit internal motion resembling deep learning in AI systems. The study suggests a common mathematical principle underlying both foams and AI training, with implications for designing adaptive materials and understanding biological structures.
The new program focuses on advancing foundational research in AI, including innovation in language models and algorithmic efficiency. Google will support research grants, scholarships for students, and educational initiatives at the TAU Center.
A new AI framework uncovers simple, understandable rules governing complex dynamics in nature and technology. The AI generates equations that accurately describe complex systems, revealing hidden variables that govern their behavior. This approach offers scientists a new way to leverage AI for understanding complex systems.
Dr. Tom McClelland from the University of Cambridge believes that our current evidence is insufficient to determine whether artificial intelligence has achieved consciousness. He suggests that sentience, which involves positive and negative feelings, is a more critical factor in making AI ethically significant.
Researchers used AI to study covert attention and found emergent properties in artificial neural networks, including new neuron types with response properties never highlighted before. The findings have implications for our understanding of the human brain and its ability to process information.
The University of Texas at Dallas has partnered with Tech Mahindra to facilitate collaboration on artificial intelligence (AI) innovation, skill development, and research. The partnership will provide opportunities for students and faculty to advance AI technologies, data science, and cybersecurity.
The EBRAINS Summit 2025 will bring together experts to assess how neuroscience can drive medical progress, digital innovation, and responsible data use. Preliminary results from the EPINOV clinical trial, integrating virtual brain technology for epilepsy surgery planning, will be presented.
Researchers from Johns Hopkins University found that selecting the right blueprint can accelerate learning in visual AI systems, rivalling conventional methods. By modifying convolutional neural networks, they generated brain-like activity patterns, suggesting that architectural design plays a crucial role in AI development.
Researchers aim to understand and overcome the limitations of current large language models, which make mistakes despite extensive training. The Emmy Noether Research Group will focus on developing new architectures with predictable capabilities.
Security researchers have developed a defense mechanism that protects against cryptanalytic parameter extraction attacks on AI systems. By making neurons in the same layer similar to each other, the defense creates a barrier of similarity that makes it difficult for attacks to proceed.
This book offers a comprehensive exploration of AI-driven analytics in finance, addressing market prediction, fraud detection, and risk assessment. It also discusses AI applications in healthcare and cybersecurity, including disease classification and biometric identification systems.
The new statistical method adapts to data structure, resisting outliers and providing greater stability on non-Euclidean spaces. This improves the reliability of analysis in areas like medical imaging, computer vision, and machine learning.
Researchers developed a novel topology-aware multiscale feature fusion network to enhance EEG-based motor imagery decoding. The TA-MFF network achieves excellent classification performance, outperforming state-of-the-art methods by leveraging spectral-topological data analysis-processing and inter-spectral recursive attention.
Researchers at University of Würzburg successfully tested an AI-based attitude controller for satellites directly in orbit, using Deep Reinforcement Learning. The test demonstrated the speed and flexibility of the DRL approach, which can automate control strategies and adapt to differences between expected and actual conditions.
Researchers Prof Axel Cleeremans, Prof Anil Seth, and Prof Liad Mudrik warn that advances in AI and neurotechnology are outpacing our understanding of consciousness. They emphasize the need for theory-driven research and innovative methods to advance consciousness science.
Researchers at the University of Surrey have developed a brain-inspired approach to improve artificial neural networks' performance without sacrificing accuracy. The method, called Topographical Sparse Mapping (TSM), rethinks how AI systems are wired by connecting each neuron only to nearby or related ones.
Researchers warn that advances in AI and neurotechnology are outpacing our understanding of consciousness, with potential serious ethical consequences. A better understanding of consciousness could have major implications for AI, prenatal policy, animal welfare, medicine, mental health, law, and emerging neurotechnologies.
Researchers at USC Viterbi School of Engineering have developed artificial neurons that physically embody the analog dynamics of biological brain cells. These innovations will allow for significant reduction in chip size and energy consumption, potentially advancing artificial general intelligence.
The Stowers Institute has appointed its first AI Fellow, Sumner Magruder, to harness the potential of artificial intelligence in biological research. He will collaborate with researchers to design new algorithms and unlock insights from large datasets.
Engineers at Duke University have constructed an 'agentic system' of AI bots that can solve complex design problems nearly as well as a fully trained scientist. The researchers created large language model (LLM) AI agents to complete all the legwork, allowing them to automate straightforward but niche design problems.
A team of researchers at the University of Waterloo developed a framework that uses mathematical tools and machine learning to rigorously check and verify the safety of AI-driven systems. The framework has been tested on challenging control problems and matched or exceeded traditional approaches.
MetaSeg achieves the same segmentation performance as U-Nets but requires 90% fewer parameters, making medical image segmentation more cost-effective. The new approach leverages implicit neural representations to quickly adjust to new images and decode accurate labels.
A team of researchers developed a computational method that can design intrinsically disordered proteins with desired properties. The work uses automatic differentiation to optimize protein sequences and leverages molecular dynamics simulations for precision. This breakthrough has the potential to reveal new insights into diseases like...
Researchers at Institute of Science Tokyo developed a new framework for generative diffusion models by reinterpreting Schrödinger bridge models as variational autoencoders. This approach reduces computational costs and prevents overfitting, enabling more efficient generative AI models with broad applicability.
Scientists at Seoul National University have developed a framework to manipulate emergent behavior in animal groups and robot swarms. The approach uses physics-informed AI to learn local interaction rules, enabling the control of collective patterns such as rings, clumps, and flocks.
Researchers assessed the effectiveness of a single session with 'Amanda,' a ChatGPT-4o-based chatbot, versus a brief journaling task in addressing non-abusive relationship conflict. The study found that both interventions improved participants' specific relationship problems, overall relationships, and well-being.
Researchers at Politecnico di Milano developed photonic chips for training physical neural networks, eliminating digitisation requirements. This allows for faster, more robust, and efficient network training using light signals.
Researchers have developed a new light-based chip that cuts power consumption for image recognition tasks by up to 100 times, using lasers and microscopic lenses fabricated onto circuit boards. This breakthrough enables faster performance and potentially strain-free AI systems.
Researchers have developed a silicon chip that uses light to perform convolution operations for AI, reducing energy consumption and increasing speed. The chip achieves near zero energy performance, leap forward for future AI systems.
A global study surveyed 14,000 patients across 43 countries, finding that those in poorer health were more likely to reject AI. Patients preferred explainable AI and wanted clinicians to make final decisions.
The Wits MIND Institute has received a $1 million boost from Google.org, enabling it to drive next-generation breakthroughs in natural and artificial intelligence. The partnership aims to advance the scientific understanding of both natural and artificial intelligence, foster breakthrough research and technological innovation.
A former diplomat warns that algorithms lack empathy and intuition, which are essential for successful negotiations. However, AI can streamline diplomacy and amplify human aspirations when used carefully. Diplomats need training in AI ethics and global cooperation to ensure equal access and deployment.
Researchers developed AI models that can identify signs of heart failure in patients from Appalachia using low-tech electrocardiogram results. The models achieved high accuracy and could potentially provide clinicians with an edge in protecting patients' cardiac health.
Researchers at the University of Vaasa developed smart packaging that can detect subtle color changes in printed packages, enabling cost-effective solutions for industries like food and beverage, healthcare, and logistics. This technology provides a human-eye accurate and environmentally friendly alternative to electronic sensors, pavi...
A team of computer scientists created 2,300 original sudoku puzzles and asked AI tools like OpenAI's ChatGPT to solve them. The results showed that while some AI models could solve easy sudokus, most struggled to provide accurate explanations, raising questions about the trustworthiness of AI-generated information.
Researchers at the University of Rochester are developing biologically inspired predictive coding networks for digital image recognition using analog circuits, which could lead to more efficient drones. The team aims to approach the performance of existing digital approaches and translate it to complex perception tasks needed by self-d...
Researchers highlight the potential of solvent-based recycling and AI-assisted sorting to recycle complex plastics. However, the study emphasizes that replacing fossil-based plastics with biobased alternatives poses significant challenges, requiring comprehensive approaches and life cycle assessments.
A new study by Cornell University reveals Amazon's AI shopping assistant Rufus gives vague or incorrect responses to users writing in some English dialects like AAE. The researchers propose a framework for evaluating chatbots that can better serve users from diverse linguistic backgrounds.
Researchers found that LLMs are better at representing non-sensorimotor concepts but struggle with sensory and motor concepts. Incorporating sensory input improves LLM performance and leads to more human-like representation, consistent with previous human studies on multimodal learning.
A novel method predicts the working status of high-formwork support systems using a combination of finite element model simulations, deep learning, and large language models. The framework achieves superior performance over existing methods and demonstrates potential applications in complex structures.
A new study reveals that AI systems transition from relying on word positions to meaning-based understanding as they receive enough data for training. The transition occurs abruptly, similar to a phase transition in physical systems, and is driven by the amount of data available.
Researchers developed an AI-powered microscope system to measure soil fungi presence and quantity, providing insights into soil health and fertility. The low-cost optical microscopy with machine learning technology can be used by farmers and land managers worldwide.
A new study in Nature Communications found that AI models exhibit a geometric property called convexity, which helps humans form and share concepts. Convexity is also linked to the performance of AI models on specific tasks.
Researchers pioneer a new AI method to uncover cognitive strategies in decision-making, revealing suboptimal behavioral patterns. The study uses small neural networks to predict animal choices with accuracy comparable to larger neural networks.
Researchers developed a simplified model to explain visual processing in the primary visual cortex, achieving 75% accuracy with fewer layers. The 'minimodels' for individual neurons are just as powerful as large models, providing an accurate and interpretable way to study visual computation.
Researchers used machine learning to simulate galaxy evolution and supernova explosions, achieving speeds four times faster than supercomputers. This breakthrough enables the study of galaxy origins, including the creation of the Milky Way's elements essential for life.
An interdisciplinary team at TU Wien has developed a method that allows for the exact calculation of how reliably a neural network operates within a defined input domain. This enables mathematical guarantees for the safe use of AI in sensitive applications.
A new diagnostic tool uses AI to analyze handwriting signals, detecting subtle motor symptoms associated with Parkinson's disease. The device has shown an average accuracy of 96.22% in distinguishing patients from healthy individuals.
The AI for Good Global Summit 2025 will showcase AI innovations delivering better healthcare and education, reducing disaster risks, ensuring water and food security, and bolstering economic resilience. The event, organized by the International Telecommunication Union (ITU), features talks from AI leaders and 100+ demos.
Computer scientist Zeynep Akata has developed innovative methods to combine visual, linguistic, and conceptual elements in AI to increase user trust. Her research on explainable AI aims to make image classification decisions more transparent.
Researchers developed an AI tool called AAnet to characterize cancer cell diversity, identifying five distinct cell groups with different gene expression profiles. This could lead to more targeted therapies and improved patient outcomes.
An AI model developed by Ehsan Ghane at the University of Gothenburg can predict the durability and strength of woven composite materials, reducing development time. The model integrates material laws to make extrapolations outside training data, enabling better understanding of material behavior.
Researchers found that brain's dopamine neurons encode a map of possible future rewards across time and magnitude, guiding adaptive behavior in uncertain environments. This biological insight aligns with recent advances in AI, particularly distributional RL algorithms, which learn from reward distributions rather than averages.
Dr. Deanna Kaplan's innovative voice-capture app, Fabla, captures unstructured voice narratives to study how clinical interventions influence daily life. The platform has found applications across diverse health domains, including veteran experiences and healthcare provider burnout.
A new study by UChicago scientists found that AI-powered weather prediction models are remarkable but not magical, struggling to predict unprecedented weather events. The model can achieve impressive accuracy for short-term forecasts but fails to extrapolate beyond existing training data, leading to false negatives and potential mispre...
A team of researchers developed a machine learning model called Aurora that accurately forecasts various Earth systems, including air quality and tropical cyclone tracks. The model outperforms traditional systems at a fraction of the cost, enabling better preparedness for extreme weather events.