Deep Learning

[Paper Exploration] In-Depth Analysis of the Segment Anything Model (SAM)
A comprehensive exploration of Meta AI's Segment Anything Model (SAM), a foundation model designed to generalize across various segmentation tasks with minimal prompting, zero-shot and few-shot learning capabilities, and applications in a wide range of domains.
paper-exploration / deep learning / computer vision / meta ai / model analysis / research    sota / zero shot / few shot / machine learning / deep learning / sam / computer vision / image segmentation / meta ai
[Paper Exploration] Deep Residual Learning for Image Recognition
The paper introduces a novel architecture called residual networks (ResNets), which significantly improves deep neural network training by using skip connections to mitigate the vanishing gradient problem. This approach achieved state-of-the-art performance on several benchmarks, including the ImageNet dataset, and has become foundational in modern deep learning applications.
paper-exploration    sota / gradient descent / machine learning / deep learning / resnet
Flight delay prediction and exploration in the United States
EDA and Predictive Models on Airlines Delay
georgia-tech / capstone-project    correlation / dimensionality reduction / PCA / Random Forest / Deep Learning / XGBoost / AdaBoost / analytics / group-project / machine-learning / random-forest / XGBoost / data-viz