List of 98 Machine Learning Algorithms

This is not an exhaustive list, but rather a comprehensive one that includes classical algorithms, variations, techniques, and recent approaches. These are categorized to facilitate understanding.

I. Supervised Learning

Regression:

1.  Simple Linear Regression
2.  Multiple Linear Regression
3.  Polynomial Regression
4.  Logistic Regression
5.  Ridge Regression
6.  Lasso Regression
7.  Elastic Net Regression
8.  Support Vector Regression (SVR)
9.  Non-Linear Regression
10. Quantile Regression

**Classification:**

11. Logistic Regression (Binary Classification)
12. Multinomial Logistic Regression (Multiclass Classification)
13. K-Nearest Neighbors (KNN)
14. Decision Trees
15. Random Forest
16. Gradient Boosting (XGBoost, LightGBM, CatBoost, AdaBoost)
17. Support Vector Machines (SVM)
18. Naive Bayes (Gaussian, Multinomial, Bernoulli)
19. Perceptron
20. Artificial Neural Networks (Multilayer Perceptron - MLP)
21. Convolutional Neural Networks (CNNs)
22. Recurrent Neural Networks (RNNs, LSTM, GRU)
23. Discriminant Analysis (Linear Discriminant Analysis - LDA, Quadratic Discriminant Analysis - QDA)
24. Gaussian Process Classifier
25. Extreme Learning Machines (ELM)
26. Ensemble Classifiers (Voting, Bagging)
27. Rule-Based Classifiers
28. Bayesian Classifiers        

Other:

29. Generalized Linear Models (GLM)
30. Hidden Markov Models (HMMs)
31. Conditional Random Fields (CRFs)
32. Gaussian Mixture Models (GMMs) (Also used in unsupervised learning)
33. Generalized Additive Models (GAMs)        

II. Unsupervised Learning

Clustering:

34. K-Means
35. K-Medoids (PAM - Partitioning Around Medoids)
36. Hierarchical Clustering (Agglomerative, Divisive)
37. DBSCAN (Density-Based Spatial Clustering of Applications with Noise)
38. OPTICS (Ordering Points To Identify the Clustering Structure)
39. Mean Shift
40. Spectral Clustering
41. Gaussian Mixture Models (GMMs) (Probabilistic Clustering)
42. Birch
43. Affinity Propagation
44. Graph-Based Clustering
45. Density-Based Hierarchical Clustering
46. Fuzzy C-Means Clustering        

Dimensionality Reduction:

47. Principal Component Analysis (PCA)
48. Linear Discriminant Analysis (LDA) (Also in Supervised Learning)
49. t-distributed Stochastic Neighbor Embedding (t-SNE)
50. Uniform Manifold Approximation and Projection (UMAP)
51. Non-negative Matrix Factorization (NMF)
52. Kernel PCA
53. Autoencoders (Variational, Denoising, Sparse)
54. Feature Selection Methods (Forward, Backward, etc)
55. Locally Linear Embedding (LLE)
56. Isomap
57. Spectral Embedding
58. Independent Component Analysis (ICA)
59. Truncated SVD
60. Multidimensional Scaling (MDS)        

Other:

61. Association Rule Learning (Apriori, Eclat)
62. Anomaly Detection (One-Class SVM, Isolation Forest, Local Outlier Factor - LOF)
63. Self-Organizing Maps (SOM)
64. Topic Modeling (LDA, pLSA)
65. Collaborative Filtering
66. Time Series Decomposition        

III. Reinforcement Learning

67. Q-Learning
68. SARSA (State-Action-Reward-State-Action)
69. Deep Q-Networks (DQN)
70. Policy Gradients (e.g., REINFORCE, A2C, A3C)
71. Actor-Critic Methods (e.g., DDPG, TD3, SAC)
72. Monte Carlo Tree Search (MCTS)
73. Temporal Difference Learning (TD Learning)
74. Multi-Armed Bandits
75. Markov Decision Processes (MDPs)
76. Imitation Learning
77. Inverse Reinforcement Learning        

IV. Semi-Supervised Learning

78. Self-Training
79. Co-Training
80. Transductive SVM
81. Graph-Based Semi-Supervised Learning
82. Pseudo-Labeling
83. Consistency Regularization        

V. Specific Techniques and Approaches:

84. Ensemble Learning (Bagging, Boosting, Voting)
85. Active Learning
86. Transfer Learning
87. One-Shot Learning
88. Few-Shot Learning
89. Meta-Learning
90. Federated Learning
91. Uncertainty Quantification
92. Explainable AI (XAI)
93. Adversarial Learning
94. Online Learning
95. Reinforcement Learning from Human Feedback (RLHF)
96. Bayesian Optimization
97. Evolutionary Algorithms
98. Optimization Algorithms (e.g., Gradient Descent, Adam, SGD)        

This is a comprehensive list, but I faced challenges in its creation due to the variations that each algorithm can have, characteristics of other approaches forming hybrid algorithms, some algorithms can be used in both supervised and unsupervised learning, and to keep the list dynamic, new techniques and algorithms continually emerge.

References:

https://pmc.ncbi.nlm.nih.gov/articles/PMC7983091/