AI model predicts adult ADHD using virtual reality and eye movement data 🧠👀. Study found that their machine learning model could distinguish adults with ADHD from those without the condition 81% of the time when tested on an independent sample.

Read Full Article

#AIPredictsADHD #VirtualReality #EyeMovementData #MachineLearning #ADHDAwareness

How individuals grasp an object may offer simpler diagnosis for autism spectrum disorder. 🤲🧩 Machine learning analysis is able to classify autism with around 85% accuracy based on how young adults use their thumbs and index fingers to grasp blocks of different sizes. 🧊📊

Read Full Article

#AutismResearch #MachineLearning #GripAnalysis #DiagnosisInnovation #ASD

Unmasking human trafficking: AI reveals hidden recruitment networks. Using machine learning to analyze millions of online ads, researchers link deceptive job offers to sex trafficking networks. Traffickers often lure victims from economically vulnerable areas and suburbs, rather than large cities. 🕵️‍♂️🔍💔

Read Full Article

#HumanTrafficking #AIAwareness #MachineLearning #EndHumanTrafficking #StopTheTraffick

Scientists use deep learning to uncover hidden motor signs of neurodivergence 🤖✨ | Using AI to analyze subtle patterns in how people move their hands during simple tasks 🤲, identifying with surprising accuracy whether someone is likely to have autism 🧩, attention-deficit traits, or both.

Read Full Article

#DeepLearning #Neurodivergence #AIResearch #AutismAwareness #MachineLearning

Machine learning reveals historical seismic events in the Yellowstone caldera 🌋 - researchers have now been able to detect and designate ten times more earthquakes 🌍 than previously detected 📈.

Read Full Article

#MachineLearning #YellowstoneCaldera #SeismicEvents #EarthquakeDetection #ResearchInnovation

LLMs are not consistently capable of updating their metacognitive judgments based on their experiences, and, like humans, LLMs tend to be overconfident 🤖💭✨

Read Full Article

#LLMs #Metacognition #AIConfidence #MachineLearning #TechEthics

A new study analysed over 1 million research papers and found growing use of large language models, especially in computer science, where up to 22% show signs of LLM editing. 📊📚✨

Read Full Article

#AIResearch #MachineLearning #LanguageModels #ComputerScience #DataAnalysis

Brain cells learn faster than machine learning, new research reveals 🧠📈✨

Read Full Article

#BrainCells #MachineLearning #Neuroscience #CognitiveScience #ResearchFindings

New algorithm compares hundreds of 3D faces thousands of times faster than old methods by using a calculated "average face" as a clever shortcut, achieving nearly the same accuracy in minutes instead of days 🕒💻👤✨

Read Full Article

#3DFaceRecognition #AIAlgorithms #TechInnovation #MachineLearning #FaceComparison

My blue is your blue: different people’s brains process colours in the same way. Neuroscientists can predict what colour 🎨 a person is looking at using a machine-learning tool trained on the brain activity of others. 🧠✨

Read Full Article

#ColorPerception #Neuroscience #MachineLearning #BrainActivity #Blue

Artificial Intelligence promotes dishonesty 🤖: When people delegated tasks to machine agents–whether voluntarily or in a forced manner–they were more likely to cheat 💰.

Read Full Article

#ArtificialIntelligence #EthicsInTech #MachineLearning #HonestyMatters #DigitalTrust

Researchers implemented five machine learning models, utilizing 307 data points encompassing composting strategies, physicochemical properties, and composting time stages, to predict nitrogen loss during organic solid waste composting 🌱📊🧪🕒💧

Read Full Article

#MachineLearning #CompostingResearch #NitrogenLoss #SustainableWasteManagement #DataScience

Researchers have developed a new AI algorithm to automate the detection of a few cancer cells among millions of normal blood cells in approximately 10 minutes 🧬🩸⏱️

Read Full Article

#AIDetection #CancerResearch #HealthInnovation #MedicalTechnology #MachineLearning

AI system can diagnose sepsis with 99% accuracy before it becomes life-threatening 🤖💉⚠️

Read Full Article

#AI #SepsisDiagnosis #HealthcareInnovation #MachineLearning #PatientSafety

Researchers have developed a new computational method, a machine learning-based algorithm, to interpret complex single-cell data. The method, called Coralysis, helps researchers identify and group cell types across samples and is available as an open-source software. 🧬🔍💻

Read Full Article

#Coralysis #MachineLearning #SingleCellAnalysis #OpenSource #Bioinformatics

Machine learning identifies the dominant physiological components in intrinsic water-use efficiency 💧 and photosynthetic performance index 🌱 in dryland maize 🌾.

Read Full Article

#MachineLearning #WaterUseEfficiency #Photosynthesis #DrylandAgriculture #MaizeResearch

Using machine learning to analyze patterns of anti-Muslim hate speech online in Norway shows that the number of hateful posts is growing and that most are posted by a small group of users who often don’t remain active for long. Engaging with them can be effective in getting them to stop.

Read Full Article

#HateSpeech #MachineLearning #DataScience

🔬 OsloMet senior researcher Yuri Kasahara, in collaboration with the Norwegian Directorate for Children, Youth, and Family Affairs (Bufdir), utilized machine learning to analyze anti-Muslim hate speech on Facebook and Twitter (now X) from 2010 to 2022, examining approximately one million public comments.

📈 Over the 12-year study period, the share of hateful comments within conversations rose from roughly 1% to about 4%, indicating an increase in the total volume of hateful comments.

👥 A key finding was that a significant portion of anti-Muslim hate speech originated from a small group of individuals, who appear to be real people rather than bots or foreign actors, though the individuals generating the most hate changed over time.

#HateSpeech #MachineLearning #Norway

* 🤖 MIT researchers have discovered "attribution decay" in AI image generators, meaning that as models are trained on more data, the influence of any single training image diminishes to the point where removing it doesn't change the output.

* 🏗️ To overcome the prohibitive cost of retraining AI models, MIT CSAIL developed a "diffusion ensemble" architecture. This allows researchers to effectively remove the influence of specific training data by disabling components rather than re-engineering the entire model.

* ⚖️ This "attribution decay" has significant implications for copyright law, potentially meaning AI outputs are not derivative works and are themselves copyrightable, as they are not attributable to any single piece of training data.

#AI #Copyright #MachineLearning

(⚠️ Formatting disabled due to Markdown error)

🐘 A new study published in Scientific Reports used machine learning to analyze hundreds of African elephant rumble recordings from Kenya's Amboseli National Park. The analysis identified distinct rumble types like "coo" for calves, "contact" calls, "let's-go" signals, and "greeting" rumbles.

🤝 Researchers found that different rumbles sometimes became progressively similar, a phenomenon called "vocal convergence," which was observed mainly during situations where elephants were coordinating group behavior. This could potentially indicate agreement, though further research is needed.

📊 The machine learning algorithm was able to predict elephant behaviors based on rumble recordings better than chance, suggesting that similar situations may involve vocalizations with similar acoustic properties.

#ElephantCommunication #AnimalBehavior #MachineLearning