Introduction to artificial intelligence algorithms

The three cornerstones of artificial intelligence are algorithms, data and computing power. Algorithms, as one of them, are very important. So what algorithms are involved in artificial intelligence?

According to different model training methods, it can be divided into supervised learning (Supervised Learning), unsupervised learning (Unsupervised Learning), and semi-supervised learning (Semi-supervised Learning) and reinforcement learning (Reinforcement Learning) four major categories.

Common supervised learning algorithms include the following categories: (Recommended learning: PHP video tutorial)

(1) Artificial neural Network (Artificial Neural Network) category: Backpropagation, Boltzmann Machine, Convolutional Neural Network, Hopfield Network, Multilayer Perceptron , Radial Basis Function Network (RBFN), Restricted Boltzmann Machine (Restricted Boltzmann Machine), Recurrent Neural Network (RNN), Self-organizing Map (SOM) , Spiking Neural Network, etc.

(2) Bayesin: Naive Bayes, Gaussian Naive Bayes, Multinomial Naive Bayes, average- Dependency Evaluation (Averaged One-Dependence Estimators, AODE)

Bayesian Belief Network (BBN), Bayesian Network (BN), etc.

(3) Decision Tree (Decision Tree) class: Classification and Regression Tree (CART), Iterative Dichotomiser3 (Iterative Dichotomiser 3, ID3), C4.5 Algorithm (C4.5 Algorithm) , C5.0 Algorithm, Chi-squared Automatic Interaction Detection (CHAID), Decision Stump, ID3 Algorithm, Random Forest, SLIQ (Supervised Learning in Quest), etc.

(4) Linear Classifier class: Fisher's Linear Discriminant

Linear Regression, Logistic Regression, Multinomial Logic Regression (Multionmial Logistic Regression), Naive Bayes Classifier (Naive Bayes Classifier), Perception (Perception), Support Vector Machine (Support Vector Machine), etc.

Common unsupervised learning algorithms include:

(1) Artificial Neural Network (Artificial Neural Network): Generative Adversarial Networks (GAN), Feedforward Neural Network ( Feedforward Neural Network), Logic Learning Machine (Logic Learning Machine), Self-organizing Map (Self-organizing Map), etc.

(2) Association Rule Learning category: Apriori Algorithm, Eclat Algorithm, FP-Growth algorithm, etc.

(3) Hierarchical Clustering: Single-linkage Clustering, Conceptual Clustering, etc.

(4) Cluster analysis: BIRCH algorithm, DBSCAN algorithm, Expectation-maximization (EM), Fuzzy Clustering, K-means algorithm, K-means clustering Class (K-means Clustering), K-medians clustering, mean-shift algorithm (Mean-shift), OPTICS algorithm, etc.

(5) Anomaly detection (Anomaly detection) category: K-nearest Neighbor (KNN) algorithm, local outlier factor algorithm (Local Outlier Factor, LOF), etc.

Common semi-supervised learning algorithms include:

Generative Models, Low-density Separation, and Graph-based methods -based Methods), joint training (Co-training), etc.

Common reinforcement learning algorithms include:

Q-learning, State-Action-Reward-State-Action-Reward- State-Action, SARSA), DQN (Deep Q Network), Policy Gradients, Model Based RL, Temporal Differential Learning, etc.

Common deep learning algorithms include:

Deep Belief Machines, Deep Convolutional Neural Networks, and Deep Recurrent Neural Networks Network (Deep Recurrent Neural Network), Hierarchical Temporal Memory (HTM), Deep Boltzmann Machine (DBM), Stacked Autoencoder (Stacked Autoencoder), Generative Adversarial Networks) etc.

For more PHP related technical articles, please visit the PHP Graphic Tutorial column to learn!

The above is the detailed content of Introduction to artificial intelligence algorithms. For more information, please follow other related articles on the PHP Chinese website!