Learn Artificial Neural Network From Scratch in Python

The MOST in-depth look at neural network theory, and how to code one with pure Python and Numpy

3.95 (67 reviews)
Udemy
platform
English
language
Other
category
instructor
11,377
students
18 hours
content
Apr 2021
last update
$44.99
regular price

What you will learn

Code a neural network from scratch in Python and numpy

Learn the math behind the neural networks

Get a proper understanding of Artificial Neural Networks (ANN) and Deep Learning

Derive the backpropagation rule from first principles

Describe the various terms related to neural networks, such as "activation", "backpropagation" and "feedforward"

Learn to evaluate the neural network models

Description

Welcome to the course where we will learn about Artificial Neural Network (ANN) From Scratch!

If you're looking for a complete Course on Deep Learning using ANN that teaches you everything you need to create a Neural Network model in Python?

You've found the right Neural Network course!

After completing this course you will be able to:

  • Identify the business problem which can be solved using Neural network Models.

  • Have a clear understanding of Advanced Neural network concepts such as Gradient Descent, forward and Backward Propagation etc.

  • Create Neural network models in Python and ability to optimize the model tuning hyper parameters

  • Confidently practice, discuss and understand Deep Learning concepts

This course will get you started in building your FIRST artificial neural network using deep learning techniques. Following my previous course on logistic regression, we take this basic building block, and build full-on non-linear neural networks right out of the gate using Python and Numpy. All the materials for this course are FREE.

You should take this course if you are interested in starting your journey toward becoming a master at deep learning, or if you are interested in machine learning and data science in general. We go beyond basic models like logistic regression and linear regression and I show you something that automatically learns features.

What is covered in this course?

This course teaches you all the steps of creating a Neural network based model i.e. a Deep Learning model, to solve business problems.

Below are the course contents of this course on ANN:

  • Part 1 - Python basics

    This part gets you started with Python and learn the brush up the basics like data structures, comprehensions, Object Oriented Programming and so on.

    This part will help you set up the python and Jupyter environment on your system and it'll teach you how to perform some basic operations in Python. We will understand the importance of different libraries such as Numpy, Pandas, Seaborn and matplotlib libraries.

  • Part 2 - Theoretical Concepts

    This part will give you a solid understanding of concepts involved in Neural Networks.

    In this section you will learn about the neurons and how neurons are stacked to create a network architecture. Once architecture is set, we understand the Gradient descent algorithm to find the minima of a function and learn how this is used to optimize our network model.

  • Part 3 - Creating Regression and Classification ANN model in Python and R

    In this part you will learn how to create ANN models in Python.

    We will learn how to model the neural network in two ways: first we model it from scratch and after that using scikit-learn library.

  • Part 4 - Tutorial numerical examples on Backpropagation

    One of the most important concept of ANN is backpropagation, so in order to apply the theory we learnt in lecture session in the real world neural networks, we are going to execute backpropagation taking one numerical example. We are going to take the help of partial differentiation and update the weights in backpropagation using gradient descent algorithms.

By the end of this course, your confidence in creating a Neural Network model in Python will soar. You'll have a thorough understanding of how to use ANN to create predictive models and solve business problems.


Content

Introduction

Introduction
Install anaconda on your machine
Set up environment and Download Machine Learning Libraries
Introduction to Jupyter Notebook
Introduction to Artificial Intelligence and Machine Learning [lecture]

Optional but Recommended [Learn Python in Easy Way]

Download and setup Pycharm code editor on Windows
Download Visual Studio code editor on Windows (Optional)
Download and setup Pycharm code editon on Linux
How to read Python documentation
Variables on Python
Data Types: String, Set and Numbers
Data Types: List, Dictionaty and Tuple
Operators and Operands
Logical Operators and Operations
Comments and User Input
Built-in Modules and Creating your own Modules
Python "List" Data Structures
Python "Dictionary" Data Structures
Python Indentation
Python Conditionals: if...else statements
Looping in Python: while Loops
Looping in Python: for Loops
User Defined Functions in Python
Default Arguments in Python
Classes and Objects in Python
Basic Inheritance in Python
Multiple Inheritance in Python
__name__ == __main__

Prerequisite: ML libraries for data preprocessing

Data Types in Machine Learning
Data Preprocessing Part 1
Data Preprocessing Part 2
Data Preprocessing Part 3
Introduction to numpy module
Introduction to pandas module
Train and Test Splitting of Data
Encoding Process in Machine Learning
Introduction to overfit and underfit of model
Cross entropy of Logistic Regression

Lecture: Introduction to neural networks --Mandatory (Don't miss out)

Introduction to Artificial Intelligence
Introduction to Neural Networks
Inspiration and representation for Neural Network
History and Application of Neural Network
Example of neural network
Updating the weights [partial differentiation]
Introduction to partial differentiation
Introduction to the Activation Function
Why do we need bias in the program
Why we use regularization in the Neural Network
Introduction to the gradient descent [review]
Introduction to Stochastic Gradient Descent and Adam Optimizer
Introduction to mini-batch SGD

Tutorial: Numerical on Backpropagation

Derivative of sigmoid function [must watch]
Introduction to the problem
Forward Propagation of Artificial Neural Network
Error in the problem
Backpropagation in ANN

Workshop: Coding Artificial Neural Network from Scratch

Setting up environment and coding single neuron
Coding neuron layer
Using dot product to code neuron layer
Coding dense layer [must know Object Oriented Programming]
Introduction to Activation Function
Implementation of activation function [step and sigmoid]
Implementation of activation function [tanh and ReLu]

Workshop: Coding Multi Layer Perception (MLP) Classifier

Creating data sets on our own!!
Implementation of MLP classifier using scikit-learn
Evaluation of the model (Neural Network)
Experimentation of hyper parameters

Explore more: Computational Neural Network [advanced]

Introduction to feed forward and backward propagation in computational graph

Screenshots

Learn Artificial Neural Network From Scratch in Python - Screenshot_01Learn Artificial Neural Network From Scratch in Python - Screenshot_02Learn Artificial Neural Network From Scratch in Python - Screenshot_03Learn Artificial Neural Network From Scratch in Python - Screenshot_04

Reviews

Marcel
February 15, 2023
Great class that explains the basic concepts of neural networks very well. The coding examples are very good as well and I liked that the jupiter notebooks were available for download. What I was just missing were advanced types of ANNs like RNNs, CNNs, encoder/decoder or transformers with exercises.

Coupons

DateDiscountStatus
4/4/202190% OFF
expired
4/4/2021100% OFF
expired
6/2/2021100% OFF
expired

Charts

Price

Learn Artificial Neural Network From Scratch in Python - Price chart

Rating

Learn Artificial Neural Network From Scratch in Python - Ratings chart

Enrollment distribution

Learn Artificial Neural Network From Scratch in Python - Distribution chart
3956286
udemy ID
4/3/2021
course created date
4/4/2021
course indexed date
Bot
course submited by