What you'll learn

Learn the basic of Artificial Intelligence from scratch.
Learn how Neural Networks work.
Program Multilayer Perceptron Network from scratch in python.
You'll know how recurrent neural networks work.
You'll learn how to create LSTM networks using python and Keras
You'll know how to forecast Google stock price with high accuracy
Use k Nearest Neighbor classification method to classify datasets.
Classify datasets by using Support Vector Machine method
Understand main concept behind Support Vector Machine method.
Classify Handwritten Images by Logistic classification method
You'll know how Linear Regression work.
You'll know how Multi Linear Regression work using sklearn and Python.
Program Logistic Regression from scratch in python.
Build Model to Predict CO2 and Global Temperature by Polynomial Regression.
You'll know the ideas behind Genetic Algorithm.
You'll know the ideas behind Particle Swarm Optimization Method.
You'll know how to find optimum point for complicated Trigonometric functions.
You'll learn how to solve well known problems like Travelling Salesman Problem (TSP).

Requirements

All you need is a decent PC/Laptop (2GHz CPU, 4GB RAM). You will get the rest from me.
You must know basic python programming.
Install Sublime and required library for python.
You should have a great desire to learn artificial intelligence and do it in a hands-on fashion.

Description

Do you like to learn how to forecast economic time series like stock price or indexes with high accuracy?

Do you like to know how to predict weather data like temperature and wind speed with a few lines of codes?

Do you like to classify Handwritten digits more accurately ?

If you say Yes so read more ...

In computer science, Artificial intelligence (AI), sometimes called machine intelligence, is intelligence demonstrated by machines, in contrast to the natural intelligence displayed by humans and other animals. In this you are going to learn essential concepts of AI using Python:

Neural Networks

Classification Methods

Regression Analysis

Optimization Methods

in the First, Second,Third sections you will learn Neural Networks

You will learn how to make Recurrent Neural Networks using Keras and LSTMs:

you'll learn how to use python and Keras to forecast google stock price .
you'll know how to use python and Keras to predict NASDAQ Index precisely.
you'll learn how to use python and Keras to forecast New York temperature with low error.
you'll know how to use python and Keras to predict New York Wind speed accurately.

In the next section you learn how to use python and sklearn MLPclassifier to forecast output of different datasets like

Logic Gates

Vehicles Datasets

Generated Datasets

In the third section you can forecast output of different datasets using Keras library like

Random datasets

Forecast International Airline passengers

Los Angeles temperature forecasting

Next you will learn how to classify well known datasets into with high accuracy using k-Nearest Neighbors, Bayes, Support Vector Machine and Logistic Regression.

In the 4th section you learn how to use python and k-Nearest Neighbors to estimate output of your system. In this section you can classify:

Python Dataset

IRIS Flowers

Make your own k Nearest Neighbors Algorithm

In the 5th section you learn how to use Bayes and python to classify output of your system with nonlinear structure .In this section you can classify:

IRIS Flowers

Pima Indians Diabetes Database

Make your own Naive Bayes Algorithm

You can also learn how to classify datasets by by Support Vector Machines to find the correct class for data and reduce error. Next you go further You will learn how to classify output of model by using Logistic Regression

In the 6th section you learn how to use python to estimate output of your system. In this section you can estimate output of:

Random dataset

IRIS Flowers

Handwritten Digits

In the 7th section you learn how to use python to classify output of your system with nonlinear structure .In this section you can estimate output of:

Blobs

IRIS Flowers

Handwritten Digits

After it we are going to learn regression methods like Linear, Multi-Linear and Polynomial Regression.

In the 8th section you learn how to use Linear Regression and python to estimate output of your system. In this section you can estimate output of:

Random Number

Diabetes

Boston House Price

Built in Dataset

In the 9th section you learn how to use python and Multi Linear Regression to estimate output of your system with multivariable inputs.In this section you can estimate output of:

Global Temprature

Total Sales of Advertising Campaign

Built in Dataset

In the 10th section you learn how to use python Polynomial Regression to estimate output of your system. In this section you can estimate output of:

Nonlinear Sine Function

Python Dataset

Temperature and CO2

Finally I want to learn you theory behind bio inspired algorithms like Genetic Algorithm and Particle Swarm Optimization Method. You'll learn basic genetic operators like mutation crossover and selection and how they are work. You'll learn basic concepts of Particle Swarm and how they are work.

In the 11th section you will learn how to use python and deap library to solve optimization problem and find Min/Max points for your desired functions using Genetic Algorithm.

you'll learn theory of Genetic Algorithm Optimization Method
you'll know how to use python and deap to optimize simple function precisely.
you'll learn how to use python and deap to find optimum point of complicated Trigonometric function.
you'll know how to use python and deap to solve Travelling Salesman Problem (TSP) accurately.

In the 12th section we go further you will learn how to use python and deap library to solve optimization problem using Particle Swarm Optimization

you'll learn theory of Particle Swarm Optimization Method
you'll know how to use python and deap to optimize simple function precisely.
you'll learn how to use python and deap to find optimum point of complicated Trigonometric function.
you'll know how to use python and deap to solve Rastrigin standard function accurately.

Who this course is for:

Anyone who wants to make the right choice when starting to learn Artificial Intelligence.
Learners who want to work in data science and big data field
students who want to learn machine learning
Data analyser, Researcher, Engineers and Post Graduate Students