Articles tagged with Neural Modeling
Researchers created a fiber computer that can be integrated into clothing to track health conditions and physical activity. The technology achieved an average accuracy of 70% when individually operated, but increased to nearly 95% when connected collectively.
This study utilized deep learning models to diagnose and predict the likelihood of malignant transformation in oral potentially malignant disorders. AI-driven approaches offer noninvasive, cost-effective, and objective means to enhance early detection and improve patient outcomes.
An international research team developed a user-friendly software method called Segment Anything for Microscopy, which can precisely segment images of tissues, cells, and similar structures. The new model improved performance for cell segmentation, enabling researchers to automate tasks that previously took weeks of manual effort.
A new AI model measures how fast the brain ages by analyzing MRI scans, providing a more accurate picture of brain health. The tool closely correlates faster brain aging with increased cognitive decline and dementia risk, offering potential for early biomarkers and personalized treatment.
New study finds that limitations on working memory exist due to learning, rather than capacity, and shed light on dopamine-related disorders like Parkinson's, ADHD, and schizophrenia. By understanding this process, clinicians may adopt different treatment options for patients with these conditions.
Researchers at WashU created a new model that uncovers brain mechanisms behind focusing amid distractions, finding people ignore past distractions but stay open to other inputs. The model demonstrates attention control by modulating focus on distractors and target tasks.
Research advances higher-order networks to capture multi-agent interactions, enabling accurate modeling of biological, social, and physical systems. The Dirac-Bianconi operator provides a powerful generalization of the graph Laplacian, encoding local and global interactions across different topological dimensions.
A new AI-based brain signal decoding model has improved how people with ALS use BCIs to predict their thoughts, achieving 74.06% accuracy in classifying left and right hand movement intention. The model's graph attention network design allows it to adapt to each user's unique brain patterns, leading to more consistent and personalized ...
Researchers developed a robust AI model that automates segmenting of MRI images, reducing radiologist workload and improving consistency. The TotalSegmentator MRI model achieved high performance on various anatomical structures, with a Dice score of 0.839.
Researchers used deep learning models to compare gene regulation in different cell types of human and chicken brains, shedding new light on brain evolution and providing tools for studying gene regulation. The study found that while some cell types are highly conserved between birds and mammals, others have evolved differently.
Researchers at Penn State developed a new method to analyze bird songs, revealing context dependence and underlying neurobiology. The study suggests that auditory feedback plays a key role in creating context dependence, and may hold insights into the neural mechanisms of human language.
A study of 153 people between the ages of 60 and 89 suggests a modification to the well-established clinical test for assessing balance in the elderly to make it more efficient, accessible, and predictive. The assessment can predict the risk of falling over a six-month period with accuracy.
A new method allows for accurate measurement of blood-brain barrier permeability, revealing that many CNS drugs penetrate the barrier rapidly. The study found that plasma proteins play a crucial role in maintaining brain delivery of lipophilic agents.
The KAIST research team developed an AI-based technique to accurately predict Hall thruster performance, significantly reducing the time and cost associated with iterative design, fabrication, and testing. The trained neural network ensemble model offers detailed analyses of performance parameters, accounting for key design variables.
A team of researchers has developed a novel model of the Blood-Brain Barrier, which mimics the complex structure of cerebral blood vessels. This breakthrough enables scientists to study neuroinflammation and develop new therapeutic strategies for Alzheimer's disease and other neurodegenerative disorders.
Researchers developed an AI model that analyzes electrocardiogram (ECG) data to predict biological age and potential cognitive decline. The study, based on UK Biobank data, found a link between higher ECG-age and poorer cognitive performance.
Researchers at Mayo Clinic developed patient-derived organoid models to study uveal melanoma, a common type of eye cancer. These 3D models accurately represent the disease's genetic and biological characteristics, enabling better understanding and treatment development.
Researchers used AI to identify genetic factors in Parkinson's disease progression and FDA-approved drugs that can be repurposed for treatment. The study found potential risk genes like SNCA and LRRK2, which are known to cause inflammation, and identified candidate drugs such as simvastatin.
A recent study reveals that rats' visual recognition abilities are extremely efficient and adaptable, even outperforming advances in artificial intelligence. Rats employ more flexible image processing strategies than CNNs, which could inspire new approaches to AI model development.
Researchers at Weill Cornell Medicine have identified a specific brain circuit that appears to reduce anxiety without side effects. The study suggests a new target for treating anxiety disorders and demonstrates a general strategy for mapping drug effects on the brain.
Researchers at McGill University discovered a novel brain mechanism that explains why bipolar patients alternate between mania and depression. A dopamine-based 'second brain clock' controls mood shifts, operating in tandem with the body's natural sleep-wake cycle.
The collaboration aims to develop advanced 3D mini-brain models for replicating human brain architecture, enabling researchers to explore neurological diseases and screen drug candidates. The platform offers a high-throughput screening method for rapid testing of potential drug candidates.
Researchers developed a system to detect and decode fiducial markers in challenging lighting conditions using neural networks. The system, DeepArUco++, overcomes the limitations of classic machine vision techniques and can be applied today thanks to open availability of its code.
Researchers found AI-based imaging technology improves disease diagnosis accuracy, particularly in cardiology, oncology, neurology, and ophthalmology. The technology also enhances diagnostic efficiency and reduces healthcare disparities by delivering high-quality diagnostics to underserved areas.
Researchers identify key brain signals prediction error and expected value to predict recovery potential in depression. They found unique brain activity patterns that could inform tailored therapy strategies, targeting specific symptoms of depression.
The new model, based on a PV-RNN framework, achieves compositionality by combining language with vision, proprioception, working memory, and attention. It requires less computing power than large language models (LLMs) and makes mistakes similar to humans.
A study by Professor Jan Peters at the University of Cologne explores how virtual slot machines' design features trigger dopaminergic effects in the brain's reward system, leading to erroneous beliefs and expectations about control over outcomes and chances of winning. This can lead to continued gambling despite high losses.
The Advanced Research + Invention Agency has awarded $84.2 million to Rice researchers to explore and unlock new methods for interfacing with the human brain at the circuit level. The project involves developing a distributed network of minimally invasive implants to stimulate neural circuits with cell-type precision.
Neuroscientists at WashU develop a novel method to create personalized brain models, shedding light on individual variations in brain dynamics and their impact on cognition and behavior. The study reveals new insights into the mechanisms underlying person-specific differences in brain electrophysiology.
The study utilizes infrared spectroscopy and a machine-learned protocol to map spectroscopic fingerprints to atomistic structures. The authors demonstrate the accuracy of their network in predicting local atomistic structures and energetic variations, enabling the tracking of dynamic C–C coupling on Cu surfaces.
Researchers introduced a novel approach to enhance reservoir computing, incorporating a generalized readout that offers improved accuracy and robustness compared to conventional methods. The new method uses a nonlinear combination of reservoir variables to uncover deeper patterns in input data.
Researchers at UTEP aim to understand how drugs impact decision-making processes and drive costly behaviors. The study will use animal models and computational neurobiology to simulate neural activity and test hypotheses about the relationship between drug use, decision-making, and brain activity.
A new computational model reveals how place cells in the hippocampus can store episodic memories, including those of events without a spatial component. The model proposes that grid cells form a scaffold that anchors memories and drives recall by connecting to sensory cortex.
Researchers developed an explainable deep learning model to predict and analyze HABs in Chinese lakes and reservoirs, achieving significant improvement over conventional machine learning methods. The model identified water temperature as the most influential factor driving algal bloom dynamics.
Researchers developed an AI model to detect brain cancer spread in surrounding tissue using MRI scans, showing 85-per-cent accuracy. This non-surgical method offers insights into patients' cancer without aggressive surgery, potentially improving treatment and survival.
Researchers developed a cutting-edge method leveraging Graph Neural Networks (GNNs) to predict mesozooplankton community dynamics and visualize their interactions. The study achieved remarkable improvements in forecasting accuracy by integrating inter-series relationships and temporal dependencies among input-variables.
This review highlights the transformative capabilities of single-cell and spatial genomics, providing critical insights into disease mechanisms and developing innovative therapies. The technologies enable comprehensive cell atlases, tracing the evolution of sequencing methods and incorporating multi-omics approaches, which significantl...
Scientists discovered that aphasia patients struggle with both forming concept of time and selecting correct verb tense. The severity of these issues varied depending on the language and individual, with some facing challenges primarily during encoding or retrieval.
The one-core-neuron system (OCNS) minimizes model size while maintaining high performance in deep learning. OCNS employs a single neuron to encode high-dimensional data into a one-dimensional time-series representation, reducing parameters by an average of 0.035%.
The study reveals that directional connections propagate signals in a downstream flow, leading to more complex activity patterns. Mathematical models also suggest that modularity and connectivity interact to foster dynamical complexity.
A study published in Chinese Medical Journal explores the use of artificial intelligence to identify potential medications for treating glaucoma. Researchers used AI models to predict the effectiveness of small-molecule compounds targeting RIPK3, a key signaling molecule involved in programmed cell death.
A recent study demonstrates how DNNs can predict fragrance profiles from essential oil chemical compositions, validating sensory evaluations. The model achieved high accuracy in predicting floral scents and showed promise for generating new and unique combinations.
The US Department of Energy is investing $179 million in three Microelectronics Science Research Centers to develop next-generation microelectronics designed for extreme environments. PNNL will lead projects on neuromorphic computing, EUV lithography, and heterogeneous computing.
A comprehensive analysis of medical AI technologies highlights their potential in improving diagnostic accuracy and customizing treatments. However, challenges such as data collection and analysis, biases, and patient privacy concerns need to be addressed through standardized evaluation protocols and effective collaborations.
A new method has been developed to create motor neurons from stem cells taken directly from ALS patients, allowing for fast and individualized drug testing. The cultured ALS motor neurons had increased susceptibility to cell death, underscoring the utility of this system to identify potential drugs.
Researchers found that neural stem cells have a rejuvenating effect on nearby brain cells, while T cells promote stress and damage. The study opens new avenues for research into slowing or reversing brain aging.
Researchers developed a new benchmark for health care using reinforcement learning, which shows promise in managing chronic or psychiatric diseases. However, current methods are data-hungry and fail to perform accurately when tested on real-world data.
Researchers at Tohoku University developed lab-grown neurons that form complex networks resembling animal nervous systems. These networks exhibit diverse neuronal ensembles and can be reconfigured through repetitive stimulation, mimicking neural plasticity.
A research team led by USC aims to create comprehensive maps of retinal nerve connections to understand and combat retinitis pigmentosa, a progressive eye disease affecting 2 million people globally.
Researchers uncover human hippocampal CA3 region's unique neural connectivity and synaptic properties. The team found that the human CA3 network codes information efficiently to maximize associations and memory storage, with sparser connections and more reliable synapses compared to mouse models.
A new technique identifies and removes specific points in a training dataset that contribute most to a model's failures on minority subgroups. This approach maintains the overall accuracy of the model while improving its performance regarding underrepresented groups.
Researchers found that weakly spatial cells gradually correlate their activity with other neurons to form a mental map, stitching together individual locations. Sleep aids in this process, refining neural network activity and consolidating memories.
Researchers used machine learning to predict multiple types of intelligence from brain connections, with general intelligence performing best. The model's accuracy improved when trained on theory-driven connections, suggesting there are still unknown aspects of intelligence to discover.
Researchers at Pusan National University developed a hybrid model to predict metal wear in magnesium alloys, enabling safer, lighter designs. The model combines machine learning and physics to improve fatigue life prediction, offering greater predictive reliability for enhanced safety and longevity.
Researchers identified the critical role of TIMM50 protein in mitochondrial energy production and its link to a severe and rare neurological disease. The study's findings suggest potential targets for future drug treatments and advance research on protein import into mitochondria in brain cells.
Researchers developed an interactive screening model called RITA-T, which improved early identification of high-risk toddlers from underserved areas. The study found that toddlers screened via RITA-T had shorter wait times and more accessible diagnostic services compared to those not using the model.
Researchers at Tokyo University of Science have developed a new method called black-box forgetting, which enables selective removal of unnecessary information from large pre-trained AI models. This approach enhances model efficiency and improves privacy by reducing computational resources and information leakage.
A new brain mapping technique has revealed fresh insights into how higher-order functions like language, thought, and attention are organised. Researchers used data from fMRI scans to create accurate models of brain activity and interactions between regions.
Scientists at MIT developed a fully integrated photonic processor that can perform all key computations of a deep neural network optically on the chip. The device completed machine-learning classification tasks in under half a nanosecond while achieving over 92% accuracy, similar to traditional hardware.
A new study found that brain stimulation effectiveness is linked to individual learning abilities, not age. The study used atDCS on participants with optimal and suboptimal learning strategies, revealing accelerated accuracy improvement in suboptimal learners.