Вы находитесь на странице: 1из 2

ARTIFICIAL INTELLIGENCE

Python Basics
 Introduction to Python
 Environment creation
 variables and expression
 conditional code
 fucntions
 loops and iteration
 List
 Tuples
 Data Dictionary
 File handling
 importing library
 random libraries
 Sorting, Formatting
 Statistics
 basics of flask & django
 arrays and graph plotting

Introduction to Machine learning

Introduction to Data Operation


 Basic Operations
 Moving Data Around
 Computing on Data
 Plotting Data
 Control Statements: for, while, if statement
 Vectorization
Types of ML algorithm- an overview
 Supervisied learning
 Unsupervisied Learning
 Reinforcement Learning
Linear Algebra
 Matrices and Vectors
 Addition and Scalar Multiplication
 Matrix Vector Multiplication
 Matrix Matrix Multiplication
 Matrix Multiplication Properties
 Inverse and Transpose
 Practice Quiz: Linear Algebra
Linear Regression
 Model Representation
 Cost Function
 Gradient Descent
 Gradient Descent For Linear Regression
 Features and Polynomial Regression
 Normal Equation
 Normal Equation Noninvertibility
Logistic Regression
 Classification
 Hypothesis Representation
 Decision Boundary
 Simplified Cost Function and Gradient Descent
 Advanced Optimization
 Multiclass Classification: One-vs-all
Regularization
 The Problem of Overfitting
 Regularized Linear Regression
 Regularized Logistic Regression
Machine Learning System Design
 Prioritizing What to Work On
 Inverse and Transpose
 Error Metrics for Skewed Classes
 Trading Off Precision and Recall
 Data For Machine Learning
Supervised Learning
 SVM
 Nearest Neighbour
 Kernels
 few more
Unsupervised Learning
 K-Means Algorithm
 Optimization Objective
 Random Initialization
 Choosing the Number of Clusters
Large Scale Machine Learning
 Learning with large datasets
 Stochastic Gradient Descent
 Mini-Batch Gradient Descent
 Stochastic Gradient Descent Convergence
 Map Reduce and Data Parallelism
Training Artificial Neural Networks for Image Recognition
 Modeling complex functions with artificial neural networks
 Classifying handwritten digits
 Training an artificial neural network
 Convergence in neural networks
 Other neural network architectures

Tools for ML

Practical Applications

Вам также может понравиться