Machine Learning Algorithms

---

---

Machine learning algorithms is a master's course in algorithms and computations presented at the University of Tehran.

Teacher:

• Ali Fahim

👨‍🎓 Teacher Assistant:

---

• Asef Afsahi (👨‍🍳)
• Hossein Tavakolian
• Zahra Boreiri
• Parsa Hadadian
• Mohammad Jalai
• Mohammad Hatami

📃 sylabes:

PART I. DATA ANALYSIS FOUNDATIONS

Data Mining and Analysis

---

• 1 Data Matrix
• 2 Attributes
• 3 Data: Algebraic and Geometric View
• 4 Data: Probabilistic View

Numeric Attributes

---

• 1 Univariate Analysis
• 2 Bivariate Analysis
• 3 Multivariate Analysis
• 4 Data Normalization
• 5 Normal Distribution

Categorical Attributes

---

• 1 Univariate Analysis
• 2 Bivariate Analysis
• 3 Multivariate Analysis
• 4 Data Normalization
• 5 Normal Distribution

Kernel Methods

---

• 1 Kernel Matrix
• 2 Vector Kernels
• 3 Basic Kernel Operations in Feature Space
• 4 Kernels for Complex Objects
• 5 Normal Distribution

Dimensionality Reduction

---

• 1 Background
• 2 Principal Component Analysis
• 3 Kernel Principal Component Analysis
• 4 Singular Value Decomposition

PART II. CLUSTERING

Representative-based Clustering

---

• 1 K-means Algorithm
• 2 Kernel K-means
• 3 Expectation-Maximization Clustering

Hierarchical Clustering

---

• 1 Preliminaries
• 2 Agglomerative Hierarchical Clustering

Density-based Clustering

---

• 1 The DBSCAN Algorithm
• 2 Kernel Density Estimation
• 3 Density-based Clustering: DENCLUE

Clustering Validation

---

• 1 External Measures
• 2 Internal Measure
• 3 Relative Measure

PART III. CLASSIFICATION

Clustering Validation

---

• 1 External Measures
• 2 Internal Measure
• 3 Relative Measure

Probabilistic Classification

---

• 1 Bayes Classifier
• 2 Naive Bayes Classifier
• 3 K Nearest Neighbors Classifier

Decision Tree Classifier

---

• 1 Decision Trees
• 2 Decision Tree Algorithm

Linear Discriminant Analysis

---

• 1 Optimal Linear Discriminant
• 2 Kernel Discriminant Analysis

Support Vector Machinesn

---

• 1 Support Vectors and Margins
• 2 SVM: Linear and Separable Case
• 3 Soft Margin SVM: Linear and Nonseparable Case
• 4 Kernel SVM: Nonlinear Case
• 5 SVM Training: Stochastic Gradient Ascent

Classification Assessment

---

• 1 Classification Performance Measures
• 2 Classifier Evaluation
• 3 Bias-Variance Decomposition
• 4 Ensemble Classifiers

PART IV. REGRESSION

Linear Regression

---

• 1 Linear Regression Model
• 2 Bivariate Regression
• 3 Multiple Regression
• 4 Ridge Regression
• 5 Kernel Regression
• 6 L1 Regression: Lasso

Logistic Regression

---

• 1 Binary Logistic Regression
• 2 Multiclass Logistic Regression

Neural Networks

---

• 1 Artificial Neuron: Activation Functions
• 2 Neural Networks: Regression and Classification
• 3 Neural Networks: Regression and Classification
• 4 Deep Multilayer Perceptrons

Deep Learning

---

• 1 Recurrent Neural Networks
• 2 Gated RNNS: Long Short-Term Memory Networks
• 3 Multiple Regression
• 4 Convolutional Neural Networks
• 5 Convolutional Neural Networks

Regression Evaluation

---

• 1 Univariate Regression
• 2 Multiple Regression

---

License

---