Learning Regularity: “Bulldozer computing” Nearest neighbors: pattern recognition Neural nets: mimic biology Boosting: theory Constraints: human-like learning One-shot Explanation-based learning Nearest neighbor A detection mechanism generates a vector of features. These features are converted in a vector of values that…
9. Constraints: Visual Object Recognition
Borders and faces orientation Discerning borders of objects and face orientation with vectors, an initial computer vision theory seemed plausible but too difficult to implement. Orthographic projection In orthographic projection, the correspondence of a system of points of three known…
8. Constraints: Search, Domain Reduction
https://www.youtube.com/watch?v=d1KyYyLmGpA Domain Reduction Algorithm Vocabulary Variable v: something that can have an assignment Value x: something that can be assigned Domain d: set of all different values Constraint c: limit on variable values With a depth-first search, the domain reduction algorithm…
7. Constraints: Interpreting Line Drawings
Computer vision Empirical approach Using lines on pictures of real-world objects, the edges between shapes could serve to identify the number of objects in it. The different intersections possible generally form two types of trihedral vertexes to identify shapes: arrow…
6. Search: Games, Minimax, and Alpha-Beta
How a computer can play games (like Chess) How human play chess: mixing analysis, strategy, tactics to choose a move If-Then rules Look ahead and evaluate British museum algorithm To evaluate the potential of the next situation of the board,…