Articles tagged with Neural Modeling
EPFL researchers developed detailed computational models of rat hippocampal and somatosensory cortex regions, simulating brain activity and studying the roles of each part. The models' three-dimensional geometry allows for testing with new experimental data and exploring a wide range of phenomena.
Researchers at Rutgers University have uncovered how various brain cell types work together to form large-scale functional networks in the human brain. The study found that certain cell-type distributions align with specific networks in the brain's cortex, highlighting a connection between cellular underpinnings and brain function.
Researchers suggest that starting with smaller neural networks and using curriculum learning can improve performance and reduce the need for massive computing resources. This approach could lead to more resource-efficient and less energy-consuming AI systems.
Researchers observed distinct growth patterns in brain functional networks during the birth transition, with some areas showing minimal changes and others undergoing dramatic reorganization. The subcortical network was found to exhibit significant increases in communication efficiency at birth.
Researchers have developed a deep-learning-powered metalens imaging system that overcomes limitations of traditional metalenses. The system pairs a mass-produced metalens with an image restoration framework driven by AI to achieve aberration-free, full-color images while maintaining compact form factor.
Researchers discovered that NMDA receptors set the baseline level for neural network activity, helping maintain stable brain function. The study's findings suggest potential innovative treatments for diseases linked to disrupted neural stability.
Researchers have developed a simple model system to break down fibrils into their constituent single units or liquid droplets. This discovery has the potential to treat neurodegenerative diseases such as Alzheimer's and Parkinson's by targeting pathological fibrils.
Researchers developed an AI-powered model called FastGlioma that can detect residual tumor tissue with high accuracy in 10 seconds. The technology outperformed conventional methods, reducing the risk of missed tumors by nearly 75%. This innovation could change the field of neurosurgery and minimize reliance on radiographic imaging.
NeuroMechFly v2 simulates how a fruit fly navigates through its environment while reacting to sights, smells, and obstacles. The model can track moving objects visually or navigate towards an odor source, while avoiding obstacles in its path, enabling researchers to study brain-body coordination and animal intelligence.
Researchers developed a novel machine-learning model to identify and measure causal interactions that vary over time. The Temporal Autoencoders for Causal Inference (TACI) model performed well on synthetic and real-world datasets, detecting changes in strength and direction of causal relationships.
Researchers at MD Anderson Cancer Center present promising new treatments, including a gastric cancer therapy using T cell antigen coupler technology. Additionally, COVID-19 mRNA vaccines are shown to improve responses to immune checkpoint inhibitors in patients with non-small cell lung and melanoma cancers.
Researchers at Lehigh University are using advanced algorithms and cross-domain data to help cities predict human movement patterns, enabling better planning and preparedness for events and emergencies. The model will account for variations in data streams from different sources, such as cell towers, GPS, and financial transactions.
Researchers developed a new imaging technique using fluorescence-guided surgery to enhance visibility of tumors and nerves during head and neck cancer surgery. The technique uses two near-infrared fluorophores, one for tumors and another for facial nerves, allowing for clear differentiation between cancerous tissues and nerves.
Researchers at Tel Aviv University demonstrated that bats can navigate great distances in open areas with their eyes closed, using only echolocation. The study found that bats create an acoustic map of their environment, relying on distinct echoes to guide their flight paths.
Despite their ability to provide turn-by-turn driving directions in New York City with near-perfect accuracy, generative AI models do not form a coherent internal map of the city. The researchers developed new metrics to test a transformer's world model and found that only one generated a coherent world model for Othello moves.
Researchers at Barrow Neurological Institute collected and displayed Vesalius' anatomical manikins for the first time, showcasing their enduring influence on modern anatomic teaching. The display highlights the significance of these works in revolutionizing anatomical education and training.
A team of MIT engineers developed an algorithm to identify causal links in complex systems, taking data from various sources and analyzing interactions between variables. The method generates a causality map linking variables with likely cause-and-effect relationships, including synergistic and redundant links.
Researchers developed a novel neural network model to reconstruct 3D digital images of relief-type cultural heritage objects from old photos. The model improves the accuracy of depth estimation and soft-edge detection, enhancing the preservation of cultural heritage.
Yihao Zheng and his team are developing a fiber-optic probe that analyzes artery blockages in the brain and guides procedures for blockage removal. The technology uses light and advanced calculations to determine the properties of blood clots, enabling doctors to make informed decisions about how to remove them.
A machine learning model predicts soil behavior during earthquakes, identifying areas vulnerable to liquefaction and providing contour maps for safer construction sites. The study uses geological data to create detailed 3D maps of soil layers, improving prediction accuracy by 20%.
A study led by Graciela Pineyro and Tomas Paus found that cannabis use in adolescence can lead to thinning of the cerebral cortex, affecting communication between neurons. The researchers used a combination of methods to demonstrate THC's impact on brain cells and identified genes associated with cortical thinning.
Researchers from Amsterdam UMC have developed a way to predict which patients are at risk of epilepsy after a cerebral venous sinus thrombosis (CVT), a rare type of stroke. The prediction model, known as the DIAS3 score, is based on six indicators and can be accessed online for healthcare providers worldwide.
Researchers at EPFL have developed the e-Flower, a flower-shaped 3D microelectrode array that enables real-time recording of neural activity from 3D neural spheroids. This breakthrough technology allows for more accurate and gentle monitoring of brain cells, paving the way for further research on brain organoids.
Researchers emphasize the need for updating offshore turbine designs to reflect the complexity of storms. Advanced modeling techniques and data-driven models are being developed to address this issue.
Mayo Clinic scientists created mini brain models in a dish that closely match key features seen in the brains of patients with Lewy body dementia. The team identified four potential drug compounds that may offer approaches to treating the disease.
Researchers developed a new AI model that predicts optical properties across a wide range of light frequencies using only a material's crystal structure as input. This enables highly precise predictions, making it suitable for screening materials for high-performance solar cells and detecting quantum materials.
Researchers have created the largest and most complete map of the fruit fly brain, detailing over 50 million connections between neurons. The study provides critical information about brain wiring and underlying signals, paving the way for future studies on larger-brained animals.
A study by Osaka Metropolitan University found that ChatGPT's diagnostic performance for brain tumors was comparable to that of neuroradiologists, with an accuracy rate of 73%. The model's performance varied depending on the type of clinical report written, with higher accuracy when using reports from neuroradiologist writers.
Researchers developed an AI-driven approach to model complex hand movements, overcoming current limitations in neuroscience and biomedical engineering. The model achieved a 100% success rate in controlling virtual Baoding balls, showcasing its strength in various challenging situations.
Researchers report significant strides in enhancing early diagnosis of bipolar disorder in adolescents by combining multimodal MRI with behavioral assessments. This approach reveals specific changes in brain networks signaling early-stage bipolar disorder, potentially leading to better and more personalized treatments. The study's find...
A Concordia-led team developed a framework that enables crowdsourced deep reinforcement learning as a service, using blockchain technology. This allows smaller organizations to access complex AI tasks previously out of reach, reducing costs and risk.
Researchers at WVU are working on a project to inhibit the myeloperoxidase enzyme, which feeds pancreatic cancer growth. By targeting this enzyme, they hope to boost the body's immune system to fight cancer, showing promise in mouse models and potential for future clinical trials.
A deep-learning algorithm developed by astronomer David Harvey can untangle the complex signals of self-interacting dark matter and AGN feedback in galaxy cluster images. The Inception model achieved an accuracy of 80% under ideal conditions, showcasing its potential for analyzing vast amounts of space data.
A novel approach to overcome limitations of traditional methods, NeuPh uses local conditional neural fields to reconstruct high-resolution phase information from low-resolution measurements. It provides robust resolution enhancement and outperforms existing models in accuracy.
A new study mapped genes linked to schizophrenia and uncovered a mechanism disrupting synaptic plasticity in affected individuals. The researchers identified three proteins mediating impairments of plasticity, holding promise for new treatments.
Researchers found that exposure to PFAS triggers altered activity of the ppar gene group, leading to changes in swimming behaviour and startle response in zebrafish larvae. The study suggests that PFAS may also have effects on human brain development and behavior.
Researchers have found evidence for place cells in zebrafish brains, allowing them to create internal maps of their environment. The brain region, telencephalon, is also thought to be analogous to the mammalian hippocampus and plays a key role in spatial orientation, social networks, and memory.
A new study using manifold learning and signal processing techniques identifies a significant correlation between adolescent brain activity and mental health symptoms. The approach, called exogenous PHATE, combines brain activation data with environmental variables to improve detection of existing symptoms and predict future ones.
Researchers at Duke University have developed a computer model that simulates nerve responses to electrical stimulation, enabling the efficient design of more effective and targeted neuromodulation therapies. The new tool, called S-MF, runs thousands of times faster than current industry standards without sacrificing accuracy or detail.
A Chinese Medical Journal study developed an AI-based system to automate embryo selection and eliminate subjectivity in IVF. The system improved human embryo assessment and selection, achieving higher accuracy in embryo aneuploidy screening than experienced embryologists.
Researchers develop an unsupervised deep learning-based method to reconstruct particle distribution in Tomographic PIV, achieving superior performance over traditional methods. The new technique demonstrates potential for practical applications in high-density particle fields and high-velocity flow fields.
Researchers at Washington University in St. Louis have found that serotonin increases the amplitude of neural responses to food-related odors in locusts, while ignoring non-food smells. This discovery sheds light on how sensory signals are processed and could inspire solutions for odor detection in toxic environments.
Researchers at Osaka Metropolitan University found that Ecklonia cava polyphenols can protect against neurodegeneration and improve motor function in Parkinson's disease model mice. The antioxidants activate the AMPK enzyme and inhibit reactive oxygen species production, reducing neuronal cell death.
Researchers at Brigham and Women's Hospital developed a 'Parkinson's in a dish' model that rapidly converts stem cells to brain cells with protein structures characteristic of the disease. The study enables the study of Parkinson's disease pathology in a petri dish, paving the way for personalized diagnostic and treatment methods.
Researchers from Osaka Metropolitan University developed a new scoring model using prehospital resuscitation data to predict neurological outcomes of patients with OHCA. The R-EDByUS score achieved high precision, enabling healthcare providers to make quick and accurate decisions upon hospital arrival.
A new study from the University of Washington suggests that cortical implants like Blindsight, developed by Neuralink, will not provide high-resolution vision. Instead, researchers found that a single electrode stimulates only one neuron, and image sharpness is determined by thousands of neurons in the brain.
A new study published in the journal Brain Connectivity reveals how psychological resilience can aid children's recovery from concussions. The research found that building resilience through supportive family environments and effective coping strategies may help young patients heal faster.
A novel, fast and high-quality neural text-to-speech model was successfully developed using a Transformer encoder + ConvNeXt decoder and MS-FC-HiFi-GAN. The model can synthesize one second of speech at high speed in just 0.1 seconds using a single CPU core, achieving eight times faster synthesis than conventional methods.
Researchers introduce ghost channels and cycles to understand transient behaviors in complex systems like climate processes or neuronal networks. This new approach challenges traditional concepts based on stable or unstable equilibria, potentially helping predict tipping cascades and ecosystem degradation.
The study demonstrates significant advancements in stability and functionality of ssDNA-SWCNT complexes, with high-affinity sequences showing superior binding strength. The findings also reveal notable improvements in resistance to enzymatic degradation, making these complexes suitable for long-term biological applications.
A new AI model can identify certain stages of ductal carcinoma in situ (DCIS), a type of pre-invasive breast cancer, that are likely to progress to invasive cancer. The model uses imaging and machine learning to analyze tissue samples and determine the stage of DCIS based on cell arrangement and organization.
Researchers at Duke University have broken through the performance wall of adaptive radar systems using convolutional neural networks, paralleling computer vision. They've released a large open-source dataset for other AI researchers to build upon their work, aiming to tackle industry needs like object detection and tracking.
Researchers at Georgia Tech developed a neural network that makes decisions similar to humans, using Bayesian neural networks and evidence accumulation processes. The model outperformed rival deterministic models and showed improved performance in high-speed scenarios, demonstrating its potential for more accurate decision-making.
Researchers discovered that propofol, a commonly used anesthesia drug, induces unconsciousness by causing the brain to become increasingly unstable. This instability leads to chaotic brain activity, resulting in loss of consciousness. The study's findings could help develop better tools for monitoring patients during general anesthesia.
Atomic Force Microscopy (AFM) offers groundbreaking insights into brain cells and tissues, enabling early detection and monitoring of neurodegenerative diseases. The review highlights the potential of AFM in characterizing biomarkers in cerebrospinal fluid and blood to enhance diagnosis and treatment.
Researchers have developed a multi-component hydrogel scaffold to mimic the amyloid-beta containing microenvironment associated with AD. The study found elevated levels of neuroinflammation and apoptosis markers in healthy neuronal progenitor cells cultured within this environment.
Researchers at Amsterdam UMC have developed a prediction model that can forecast cognitive decline in Alzheimer's patients with mild cognitive impairment or dementia. The model provides an indication of the disease course over 5 years and has potential for use in a user-friendly app, aiding doctors in discussing prognosis with patients.
A new study advances our understanding of how the brain responds to emotionally charged objects and scenes. The research identified how the brain represents different categories of emotional stimuli in a way that allows for more than a simple 'approach avoid' dichotomy when guiding behavioral responses.
A new dual-branch network combining CNNs and visual transformers achieves state-of-the-art recognition accuracies for plant disease identification, enhancing disease sensing capabilities and offering potential for efficient models crucial for improving agricultural production.
Researchers at the University of Houston have introduced a new method for sleep stage classification that can be performed at home and uses only two leads. This approach achieves expert-level agreement with the gold-standard polysomnography without expensive equipment, paving the way for more accessible and cost-effective sleep studies.