#ConvolutionalNeuralNetworks
LAOMUSIC ARTS 2026
presents

I just finished the course “Deep Learning with Python: Convolutional Neural Networks” by Frederick Nwanganga!

Check it out:

www.linkedin.com/learning/dee...

#lao #music #arts #laomusic #laomusicarts #ai #python #convolutionalneuralnetworks #deeplearning
April 8, 2026 at 8:49 AM
Before caffeine, my brain works just like a beginner AI. Mostly confused. Always scanning.

A short (fun) article on computer vision.

open.substack.com/pub/dianawol...

#computervision #aivision #aiexplained #ConvolutionalNeuralNetworks #alexnet #convolution
December 7, 2025 at 7:39 AM
#ConvolutionalNeuralNetworks ( #CNNs in short) are immensely useful for many #imageProcessing tasks and much more in #DeepLearning.

Yet you sometimes encounter some bits of code with little explanation. Have you ever wondered about the origins of the values for image normalization in #imagenet ?
January 5, 2025 at 11:13 PM
Log-quant cuts model memory 4× with minimal accuracy loss; compute fits mobile SoCs, enabling real-time, wearable lung-sound screening. #convolutionalneuralnetworks
Patient-Specific CNN-RNN for Lung-Sound Detection With 4× Smaller Memory
hackernoon.com
September 9, 2025 at 9:38 AM
Mel-spectrograms feed a CNN-RNN; last layers retrain on tiny patient sets, then log-quant weights trim memory 4× for wearables. #convolutionalneuralnetworks
Dataset, Features, Model, and Quantization Strategy for Respiratory Sound Classification
hackernoon.com
September 9, 2025 at 9:34 AM
Hybrid spectrogram CNN-RNN outperforms VGG/MobileNet and shows that transfer learning solves data scarcity in respiratory AI. #convolutionalneuralnetworks
Patient-Specific CNN-RNN for Wheeze and Crackle Detection with 4× Memory Savings
hackernoon.com
September 9, 2025 at 9:26 AM
This article’s results show Faster R-CNN with ResNet backbones beats YOLOv5 for road damage detection, with noted gains and failure case insights. #convolutionalneuralnetworks
Lessons from Testing AI Models on Global Damage Data
hackernoon.com
August 13, 2025 at 3:30 AM
This article compares YOLOv5 and Faster R-CNN for road damage detection, finding two-stage models with ResNet backbones yield top generalized results. #convolutionalneuralnetworks
Potholes, Pipelines, and Precision: Benchmarking Object Detectors for Global Road Safety
hackernoon.com
August 13, 2025 at 3:15 AM
This article details model choice, tuning, and dataset prep for road damage detection, comparing Faster R-CNN and YOLOv5 on a global multi-country dataset. #convolutionalneuralnetworks
Benchmarking Faster R-CNN and YOLOv5 for Global Road Damage Detection Across Countries
hackernoon.com
August 13, 2025 at 3:00 AM
VTAB-1k results show our method beats LoRA in few-shot tasks, with Grad-CAM visuals confirming better spatial awareness and superior generalization. #convolutionalneuralnetworks
More Than a Feeling: Visualizing Why Filter Atoms Outsmart LoRA in Fine-Tuning
hackernoon.com
July 1, 2025 at 9:15 AM
This method fine-tunes ConvNets by adapting only filter atoms, preserving pre-trained knowledge for efficient, high-performance transfer learning. #convolutionalneuralnetworks
Tuning the Pixels, Not the Soul: How Filter Atoms Remake ConvNets
hackernoon.com
July 1, 2025 at 9:09 AM
Fine-tune models by adapting only spatial filter atoms, preserving channel knowledge to prevent overfitting for superior, parameter-efficient results. #convolutionalneuralnetworks
Keep the Channel, Change the Filter: A Smarter Way to Fine-Tune AI Models
hackernoon.com
July 1, 2025 at 9:05 AM
Fine-tune models by adapting only spatial filter atoms, preserving channel knowledge to prevent overfitting for superior, parameter-efficient results. #convolutionalneuralnetworks
Keep the Channel, Change the Filter: A Smarter Way to Fine-Tune AI Models
hackernoon.com
July 1, 2025 at 9:01 AM
All those long excavation evenings sorting #pottery ... why not teaching computers how to do it (by means of #ConvolutionalNeuralNetworks)? 🤔🏺

https://www.eurekalert.org/pub_releases/2021-05/nau-atc051721.php via @EurekAlert
November 27, 2024 at 3:58 PM