Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
ai:methods [2022/04/07 22:22]
cyril delete
— (current)
Line 1: Line 1:
-====== Catalog of methods in AI/vision/robotics ====== 
- 
- 
- 
-This is a classification of techniques and algorithms, in order to give a broad view of solutions available to deal with classical problems. 
- 
- 
- 
-Other pages contain some more details about, which can be seen as memos with references to find more information (with the origin paper when possible). 
- 
- 
- 
-===== Learning ===== 
-==== Supervised learning ==== 
-=== Classification === 
- 
-  * __MLP (Multi Layers Perceptron)__ - //PMC (Perceptron multicouches)// 
-    * gradient backpropagation - //rétropropagation du gradient// 
-      * stochastic 
-      * with inertia 
-      * simulated annealing - //recuit simulé// 
-    * newton (second order) 
-  * __RBFNN (Radial Basis Functions Neural Networks)__ 
-    * k-means then gradient descent 
-    * incremental addition of neurons then exact method 
-  * __SVM (Support Vectors Machine)__ 
-  * __Decision tree__ - //arbre de décision// 
-    * ID3 (based on entropy) 
-  * __k-nearest neighbors__ - //k plus proches voisins// 
-  * __Boosting__ 
-    * Boosting by majority 
-    * AdaBoost (ADAptive BOOSTing) 
-      * Discrete AdaBoost 
-      * Real AdaBoost 
-      * Gentle AdaBoost 
-      * LogitBoost 
-      * Probabilistic AdaBoost 
-      * FloatBoost 
-      * AdaBoost.Reg 
-      * Multiclass AdaBoost.M1 
-      * Multiclass AdaBoost.M2 
-      * Multilabel AdaBoost.MR 
-      * Multilabel AdaBoost.MH 
-      * Multiclass AdaBoost.MO 
-      * Multiclass AdaBoost.OC 
-      * Multiclass AdaBoost.ECC 
-      * GrPloss 
-      * BoostMA 
-      * AdaBoost.M1W 
-      * SAMME (Stagewise Additive Modeling using a Multi-class Exponential loss function) 
-      * GAMBLE (Gentle Adaptive Multiclass Boosting Learning) 
-    * UBoost 
-    * LPBoost (Linear Programming BOOSTing) 
-    * TotalBoost (TOTALly corrective BOOSTing) 
-    * RotBoost 
-    * alphaBoost 
-    * MILBoost (Multiple Instance Learning BOOSting) 
-    * CGBoost (Conjugate Gradient BOOSTing) 
-    * Bootstrap Aggregating 
-  * __Cascades of detectors__ [[classification#cascades_of_detectors|[+] ]] 
-  * __Trees of detectors__ 
- 
- 
- 
-=== Regression === 
- 
-  * __MLP (Multi Layers Perceptron)__ 
-  * __RBFNN (Radial Basis Functions Neural Network)__ 
-  * __SVR (Support Vectors Regressor)__ 
- 
-=== Pattern recognition === 
- 
-  * __Viola-Jones Detector__ [[pattern-recognition#viola-jones_detector|[+] ]] 
-    * with Extended Set of Haar features 
-    * Stumps or CART trees 
-    * Rotation Invariant 
-    * **Multiview** 
-      * Parallel Cascades 
-      * Pyramid Cascade 
-      * Tree Cascade 
-      * Vector Boosting 
- 
-==== Unsupervised learning ==== 
-=== Vector quantization / Clustering === 
- 
-  * Sequential leader 
-  * k-means - //k-moyennes// 
-  * GNG (Growing Neural Gas) 
-  * Auto-organizing maps (Kohonen) - //cartes auto-organisatrices de Kohonen// 
- 
- 
-==== Reinforcement learning ==== 
- 
-  * __MDP (Markov Decision Processes)__ 
-    * Q-learning 
-    * Value iteration 
-    * Policy iteration 
- 
-===== Planification ===== 
-==== Symbolic ==== 
-=== State space search === 
- 
-  * A* 
-    * WA* 
-    * IDA* 
-  * Dijkstra 
- 
-=== Logics === 
- 
-  * __GraphPlan__ 
-    * Stan 
-    * IPP 
-    * SGP 
-  * __SATplan (SATisfiability PLANning)__ 
- 
-==== Others ==== 
- 
-  * __Genetic algorithms__ - //algorithmes génétiques// 
-  * __Ant colonies__ - //colonies de fourmis// 
- 
-==== Specific ==== 
-=== Path planning === 
- 
-  * __Configurations space__ 
-  * __Potential fields__ 
- 
-===== Perception ===== 
-==== Vision ==== 
-=== Color Quantization === 
- 
-  * RGB cone 
-  * YUV polygon 
-  * HSV rectangle 
-  * Lab 
- 
-=== Image segmentation === 
- 
-  * Floodfill - //inondation// 
-  * Watershed - //lignes de partage des eaux// 
- 
-=== Filters === 
- 
-  * **Anti-noise (smoothing)** 
-    * Median Filter - //filtre médian// 
-    * Vector Median Filter 
-    * Kuwahara filter 
-    * Peer Group Filtering 
-    * Anisotropic Filtering 
-  * **Gradient** [[vision#gradient|[+] ]] 
-    * Prewitt [[vision#prewitt|[+] ]] 
-    * Roberts [[vision#roberts|[+] ]] 
-    * Sobel [[vision#sobel|[+] ]] 
-    * Laplace [[vision#laplace|[+] ]] 
-    * Scharr [[vision#scharr|[+] ]] 
-  * **Morphological** 
-    * dilation - //dilatation// 
-    * erosion - //érosion// 
-    * opening - //ouverture// 
-    * closing - //fermeture// 
- 
-=== Edge detection === 
- 
-  * Canny detector 
-    * Canny-Deriche 
- 
-=== Pattern recognition === 
- 
-  * Mean-Square Regression - //Régression aux moindres carrés// 
-  * __Hough Transforms__ [[pattern-recognition#hough_transforms|[+] ]] 
-    * Standard Hough Transform 
-    * Randomized Hough Transform 
-    * Connective Randomized Hough Transform 
-    * Combinatorial Hough Transform 
-    * Adaptive Hough Transform 
-    * Probabilistic Hough Transform 
-    * Adaptive Probabilistic Hough Transform 
-    * Progressive Probabilistic Hough Transform 
-    * Hierarchical Hough Transform 
-    * Sampling Hough Transform 
-    * Generalized Hough Transform 
-  * UpWrite method 
-  * Curvogram 
-  * **Shape Descriptors** 
-    * Ankerst's Shape histograms 
-  * Chamfer matching 
-    * Contour Likelihood Measurement 
- 
- 
-=== Tracking === 
- 
-  * Kalman Filter 
-    * Generalized Kalman Filter 
-  * Correlation Tracking 
-    * ACA (Area Correlation Algorithm) 
-  * KLT Tracker (Kanade-Lucas-Tomasi) 
-  * IPAN Tracker 
-  * MeanShift 
-  * **Features detection** 
-    * Harris detector 
-    * Susan detector 
-    * Multiresolution Contrast detector 
- 
-==== Sensors fusion ==== 
- 
-  * Kalman filter 
-  * Particles filter (bayesian network) - //filtrage particulaire// 
  
CC Attribution-Share Alike 4.0 International
Driven by DokuWiki Recent changes RSS feed Valid CSS Valid XHTML 1.0