##DeepLearning
Sign up online! Get e-mail alerts for The Vasty Deep, the @radiology-ai.bsky.social editor's blog https://radiologyai.substack.com/ #MachineLearning #DeepLearning #ArtificialIntelligence
November 9, 2026 at 2:16 PM
Check out today's #FreeFriday @radiology-ai.bsky.social article from #PubMedCentral!

The Evolution of Radiology Image Annotation in the Era of Large Language Models

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12319696 #DeepLearning #Radiomics #ArtificialIntelligence
November 6, 2026 at 2:16 PM
#ThrowbackThursday – The Cost of Convenience: How Labeling Errors by Large Language Models Can Distort Evaluations of AI Performance (Feb 2026) https://doi.org/10.1148/ryai.251044 #AI #MachineLearning #DeepLearning
November 5, 2026 at 2:16 PM
Latent phenotyping uses deep learning to capture hidden multidimensional traits beyond predefined measurements, challenging traditional abstraction in plant science. #PlantPhenotyping #DeepLearning #LatentTraits
Details: doi.org/10.1016/j.pl...
November 6, 2026 at 1:33 PM
📝 "Deep AI Learning Part 2: Building Neurons, Layers, and the Training Loop"

Build your own neural network from scratch in Python.

👤 Vasiliki Dalakiari

🔗 https://itnext.io/build-neural-network-from-scratch-python-3ed125f758ed?source=rss-f1558d10c1f5------2

#pyladies#python#deeplearning
November 5, 2026 at 3:07 PM
#HighlyViewedPaper
📖 Defect Detection Method for Large-Curvature and Highly Reflective Surfaces Based on Polarization Imaging and Improved YOLOv11
✍ By Zeyu Yu et al.
👉 mdpi.com/2304-6732/12/4/368
#Photonics #Optics #PolarizationImaging #DefectDetection #YOLOv11 #DeepLearning
November 5, 2026 at 10:24 AM
CNN models estimate root length from minirhizotron images without segmentation, achieving R² up to 0.986 across four crop species and stress conditions. #RootPhenotyping #DeepLearning #PrecisionAg
Details: doi.org/10.34133/pla...
November 9, 2026 at 2:14 PM
Deep Learning Compilers: Architecture, Optimization, and Empirical Characterization

#CUDA #DeepLearning #DL #Compilers

hgpu.org?p=31472
Deep Learning Compilers: Architecture, Optimization, and Empirical Characterization
As deep learning (DL) models become increasingly complex and hardware architectures grow more heterogeneous, DL compilers play a critical role in optimizing computational efficiency and enabling sc…
hgpu.org
November 8, 2026 at 8:33 PM
The new method predicts enzyme kinetic parameters using deep learning, reducing metabolic flux variability by several folds and improving model accuracy in growth rate and proteome fraction predictions.

#Ecgems #DeepLearning #KineticParameters
Median flux variability reduced by several folds
Source: PLOS Computational Biology
realfeedapp.com
November 7, 2026 at 10:00 AM
Ripple-65B Preview: 65B Dense AI Model for Coding Agents on Hugging Face

RicursiveAI releases Ripple-65B Preview, a 65-billion-parameter AI model optimized for reasoning and agentic coding tasks, outperforming models 10x its size…

#science #AI #MachineLearning #DeepLearning
Ripple-65B Preview: 65B Dense AI Model for Coding Agents on Hugging Face
RicursiveAI releases Ripple-65B Preview, a 65-billion-parameter AI model optimized for reasoning and agentic coding tasks, outperforming models 10x its size…
sciherald.com
November 7, 2026 at 6:07 AM
"Deep Learning to Unveil Correlations between Urban Landscape and Population Health" links satellite imagery to 25 health indicators, identifying four urban clusters with significant health associations in NYC. #DeepLearning #PublicHealth #UrbanHealth buff.ly/DCchPSl
Deep Learning to Unveil Correlations between Urban Landscape and Population Health
The global healthcare landscape is continuously changing throughout the world as technology advances, leading to a gradual change in lifestyle. Several diseases such as asthma and cardiovascular…
buff.ly
November 4, 2026 at 9:36 AM
Numbat: 14 Trillion Parameter Leaked Anthropic AI Model

A massive 14 trillion parameter AI model, codenamed Numbat and linked to Anthropic, has been published on Hugging Face as a leaked mid-training checkpoint.

#science #AI #MachineLearning #DeepLearning
Numbat: 14 Trillion Parameter Leaked Anthropic AI Model
A massive 14 trillion parameter AI model, codenamed Numbat and linked to Anthropic, has been published on Hugging Face as a leaked mid-training checkpoint.
sciherald.com
November 4, 2026 at 6:16 AM