Deep Learning

Twitter

Facebook

Copy Link

Key Facts

Year2006

Key PeopleGeoffrey Hinton, Yann LeCun, Yoshua Bengio

Foundation ForLLMs, Protein Folding, Self-Driving

Top News

SLAC Researchers Develop AI Tool for Data Compression Without Losing Critical Scientific Details

SLAC National Accelerator Laboratory researchers created an AI-based method that compresses scientific data by 10- to 100-fold without erasing subtle details. The tool uses neural networks and wavelet analysis to preserve fine features like speckles in X-ray images, addressing storage challenges for next-generation experiments generating terabytes per second.

Science2 sources

SLAC Researchers Develop AI Tool for Data Compression Without Losing Critical Scientific Details

Science2 sources

AI Decodes Hidden DNA Sequence Controlling Gene Activation in 60% of Human Genes

Researchers at University of California San Diego used machine learning to decode the initiator, a crucial DNA sequence that controls gene activation. By analyzing 500,000 initiator variants, the AI model identified this hidden code in 60% of human genes, enabling scientists to predict the effects of DNA mutations linked to cancer and other disorders.

Science3 sources

AI Decodes Hidden DNA Sequence Controlling Gene Activation in 60% of Human Genes

Science3 sources

AI Can Predict Your Vaccine Response Before You Get the Shot, Study of 4,000+ People Reveals

Arizona State University researchers analyzed blood samples from over 4,000 people and discovered that AI can identify antibody patterns present before vaccination that predict immune response strength. The study found certain sentinel antibodies against common microbes like Staphylococcus aureus and RSV signal immune readiness, potentially enabling personalized vaccination strategies.

Health3 sources

AI Can Predict Your Vaccine Response Before You Get the Shot, Study of 4,000+ People Reveals

Health3 sources

Astromech Raises $20M to Build Biological Operating System That Forecasts Evolutionary Change

Astromech, an AI startup co-founded by Ben Lamm and geneticist George Church, has raised $20 million at a $3.8 billion valuation to develop a predictive model of biology. The company uses 3.8 billion years of evolutionary history combined with genomic data to forecast how living systems will change over time, identify vulnerabilities, and anticipate drug resistance and disease progression.

Startups2 sources

Astromech Raises $20M to Build Biological Operating System That Forecasts Evolutionary Change

Startups2 sources

AI-Driven Drug-Target Interaction Prediction Shifts From Benchmarks to Real-World Drug Discovery

Chinese researchers published a comprehensive review showing how AI-driven drug-target interaction prediction is evolving from algorithm-focused benchmarks toward practical pharmaceutical research workflows. The study addresses translational barriers including data quality issues and calls for experimentally testable predictions that support candidate screening and drug repurposing.

Science2 sources

AI-Driven Drug-Target Interaction Prediction Shifts From Benchmarks to Real-World Drug Discovery

Science2 sources

AI-Powered Tissue Clocks Reveal How Each Human Organ Ages Differently, Detectable via Blood Tests

Researchers developed deep learning tissue clocks that predict biological age from histological images of 40 tissue types. The AI models achieved 4.88-year accuracy analyzing 25,713 samples and can detect organ-specific aging patterns from blood samples, linking accelerated aging to chronic diseases.

Science3 sources

AI-Powered Tissue Clocks Reveal How Each Human Organ Ages Differently, Detectable via Blood Tests

Science3 sources

Pathway's 150M Model Proves AI Cost-Efficiency Doesn't Require Massive Scale

Pathway released BDH-CQ, a 150-million-parameter model scoring 29.5% on ARC-AGI-1 at just $0.0007 per task—11 times cheaper than GPT 5.6 Luna. The breakthrough stems from Post-Transformer architecture that reasons internally rather than generating token-heavy intermediate text, challenging the assumption that intelligence requires scale.

Technology3 sources

Pathway's 150M Model Proves AI Cost-Efficiency Doesn't Require Massive Scale

Technology3 sources

New AI Model Maps Regional Brain Aging to Detect Alzheimer's Earlier Than Ever

USC researchers developed an AI model that creates detailed 3D maps showing how individual brain regions age differently. Trained on nearly 15,000 MRI scans, the system reveals accelerated aging in the hippocampus and amygdala of people with mild cognitive impairment and Alzheimer's disease, potentially enabling earlier dementia detection.

Science4 sources

New AI Model Maps Regional Brain Aging to Detect Alzheimer's Earlier Than Ever

Science4 sources

CapuchinAI Brings Automated Cognitive Testing to Wild Monkeys in Their Natural Habitat

Emory University and Georgia Institute of Technology researchers developed CapuchinAI, an open-source AI system using facial recognition and touchscreen tasks to study wild capuchin monkeys. Field-tested in Costa Rica's Taboga Forest Reserve, the battery-powered platform achieved 97% accuracy in identifying individual primates.

Science4 sources

CapuchinAI Brings Automated Cognitive Testing to Wild Monkeys in Their Natural Habitat

Science4 sources

New study reveals 3D genome disruption drives Alzheimer's disease in brain cells

Researchers from Carnegie Mellon University and the University of Pittsburgh discovered that the three-dimensional architecture of the genome is fundamentally altered in specific brain cells of individuals with Alzheimer's disease. Using single-cell technology, spatial tissue mapping, and a novel AI model called Hicformer, the team linked genome folding to gene activity and brain tissue organization, establishing higher-order chromatin reorganization as a primary layer of Alzheimer's pathology.

Health2 sources

New study reveals 3D genome disruption drives Alzheimer's disease in brain cells

Health2 sources

Meta Brain2Qwerty v2 decodes typed sentences from brain scans at 61% accuracy without implants

Meta unveiled Brain2Qwerty v2, an AI system that converts brain activity into text without surgery, achieving 61% word accuracy using magnetoencephalography scanners. The non-invasive brain-computer interface trained on 22,000 sentences from nine volunteers marks a leap from single-digit accuracy in previous methods, though it requires room-sized equipment and can't operate in real time.

Technology7 sources

Meta Brain2Qwerty v2 decodes typed sentences from brain scans at 61% accuracy without implants

Technology7 sources

AI reads entire ancient scroll from Herculaneum for first time, revealing lost Stoic philosophy

Researchers have achieved the first complete reading of a sealed Herculaneum scroll carbonised by Mount Vesuvius in 79 AD. Using AI-powered 3D scanning and advanced X-ray imaging, the Vesuvius Challenge team digitally unrolled the charred papyrus without physically opening it, uncovering 1.5 meters of text on Stoic philosophy dating back over 2,000 years.

Science9 sources

AI reads entire ancient scroll from Herculaneum for first time, revealing lost Stoic philosophy

Science9 sources

UCLA's AI platform tracks cancer treatment responses in tumor organoids at single-cell level

Researchers at UCLA Health Jonsson Comprehensive Cancer Center developed an AI platform that combines 3D bioprinting, advanced imaging, and artificial intelligence to monitor how cancer responds to treatment. The technology analyzes thousands of patient-derived tumor organoids simultaneously, detecting rare resistant tumor populations and helping identify promising therapies for rare and hard-to-treat cancers.

Science2 sources

UCLA's AI platform tracks cancer treatment responses in tumor organoids at single-cell level

Science2 sources

AI discovers hidden antibiotic candidates inside prion proteins linked to brain diseases

Researchers at the University of Pennsylvania used AI to uncover a surprising source of antibiotics: prion proteins known for causing fatal brain diseases. The deep-learning platform identified over 1,000 antimicrobial peptides called prionins, with dozens showing strong activity against drug-resistant bacteria in lab and mouse tests.

Science2 sources

AI discovers hidden antibiotic candidates inside prion proteins linked to brain diseases

Science2 sources

Deep learning identifies promising antibiotic candidates against drug-resistant gonorrhea

Researchers at Harvard's Wyss Institute used deep learning to screen 6 million compounds and identified two promising candidates against multi-drug resistant Neisseria gonorrhoeae. The lead compound, called A1, targets alanine racemase, an enzyme critical for bacterial cell wall formation. The study marks the first use of Organ Chip technology for antibiotic preclinical testing, offering a faster validation pipeline.

Science2 sources

Deep learning identifies promising antibiotic candidates against drug-resistant gonorrhea

Science2 sources

Prev12 3 4 5 6 Next