(1.5 hours to learn)
Sparse coding is a probabilistic model of natural images where each region of an image is represented as a linaer combination of a small number of components drawn from a dictionary. When the model is fit to natural images, the dictionary elements resemble the receptive fields of cells in the primary visual cortex.
This concept has the prerequisites:
Core resources (read/watch one of the following)
→ Emergence of simple-cell receptive field properties by learning a sparse code for natural images
→ Machine Learning: a Probabilistic Perspective
A very comprehensive graudate-level machine learning textbook.
Location: Section 13.8, pages 468-474
-No Additional Notes-