Skip to content

Latest commit

 

History

History
44 lines (31 loc) · 2.14 KB

README.md

File metadata and controls

44 lines (31 loc) · 2.14 KB

MLLN

logo

Machine Learning Leaf Node

An optimal start node for beginning your machine learning journey

📁 algorithms

📁 applications

🆕 🔥 SMLFDL - 📄article

SVMs multi-class loss feedback based discriminative dictionary learning for image classification

SMLFDL integrates dictionary learning and support vector machines training into a unified learning framework by looping the designed multi-class loss term, which is inspired by the feedback mechanism in cybernetics.

analysis has been done on scene-15 dataset.
Feature vectors has been prepared by four-level spatial pyramid, dense DAISY feature description followed by PCA.
As article proposed SMLFDL are faster in predictions and converge in lower epochs.
code for features will be added soon.