Deep Neural Network for Beginners Using Python

Deep Neural Network for Beginners Using Python

Instructor: Packt - Course Instructors

Included with Coursera Plus

Learn more

5 modules

Gain insight into a topic and learn the fundamentals.

Beginner level

Recommended experience

9 hours to complete

3 weeks at 3 hours a week

Flexible schedule

Learn at your own pace

5 modules

Gain insight into a topic and learn the fundamentals.

Beginner level

Recommended experience

9 hours to complete

3 weeks at 3 hours a week

Flexible schedule

Learn at your own pace

What you'll learn

Understand the basics of training a DNN using the Gradient Descent algorithm.
Apply knowledge to implement a complete DNN using NumPy.
Analyze and create a complete structure for DNN from scratch using Python.
Evaluate and work on a project using deep learning for the IRIS dataset.

Skills you'll gain

Details to know

Shareable certificate

Add to your LinkedIn profile

Assessments

4 assignments

Taught in English

See how employees at top companies are mastering in-demand skills

Learn more about Coursera for Business

logos of Petrobras, TATA, Danone, Capgemini, P&G and L'Oreal

There are 5 modules in this course

Updated in May 2025.

This course now features Coursera Coach! A smarter way to learn with interactive, real-time conversations that help you test your knowledge, challenge assumptions, and deepen your understanding as you progress through the course. Are you ready to become a deep learning expert? This step-by-step course guides you from basic to advanced levels in deep learning using Python, the hottest language for machine learning. Each tutorial builds on previous knowledge and assigns tasks solved in the next video. You will: - Learn to train machines to predict like humans by mastering data preprocessing, general machine learning concepts, and deep neural networks (DNNs). - Cover the architecture of neural networks, the Gradient Descent algorithm, and implementing DNNs using NumPy and Python. - Understand DNN methodologies with real-world datasets, such as the IRIS dataset. Designed for those interested in data science or advancing their skills in DNNs, this course requires a background in deep learning and a basic understanding of Python and mathematics will be helpful. It’s clear and beginner-friendly, teaching theoretical concepts followed by practical implementation.

In this module, we will provide a brief overview of the course and introduce the instructor. We will also outline the learning objectives and what students can expect to achieve by the end of the course.

What's included

3 videos1 reading

In this module, we will delve into the foundational aspects of deep learning. We will start by examining a real-world problem and progressively introduce key concepts such as perceptrons, linear equations, and error functions. This section includes hands-on coding exercises to solidify understanding.

What's included

37 videos1 plugin

37 videosTotal 126 minutes

Problem to Solve Part 12 minutesPreview module
Problem to Solve Part 22 minutes
Problem to Solve Part 31 minute
Linear Equation3 minutes
Linear Equation Vectorized3 minutes
3D Feature Space3 minutes
N-Dimensional Space2 minutes
Theory of Perceptron1 minute
Implementing Basic Perceptron5 minutes
Logical Gates for Perceptrons2 minutes
Perceptron Training Part 11 minute
Perceptron Training Part 23 minutes
Learning Rate3 minutes
Perceptron Training Part 33 minutes
Perceptron Algorithm1 minute
Coding Perceptron Algo (Data Reading and Visualization)5 minutes
Coding Perceptron Algo (Perceptron Step)7 minutes
Coding Perceptron Algo (Training Perceptron)6 minutes
Coding Perceptron Algo (Visualizing the Results)4 minutes
Problem with Linear Solutions2 minutes
Solution to Problem1 minute
Error Functions2 minutes
Discrete Versus Continuous Error Function2 minutes
Sigmoid Function3 minutes
Multi-Class Problem1 minute
Problem of Negative Scores3 minutes
Need of SoftMax1 minute
Coding SoftMax4 minutes
One-Hot Encoding2 minutes
Maximum Likelihood Part 15 minutes
Maximum Likelihood Part 23 minutes
Cross Entropy4 minutes
Cross Entropy Formulation7 minutes
Multi-Class Cross Entropy3 minutes
Cross Entropy Implementation4 minutes
Sigmoid Function Implementation1 minute
Output Function Implementation2 minutes

1 pluginTotal 15 minutes

Implementing Logic Gates with Perceptrons15 minutes

In this module, we will focus on more advanced topics in deep learning. We will cover gradient descent, logistic regression, and the architecture of neural networks. Practical coding sessions will help learners apply these concepts and build their own deep learning models.

What's included

31 videos1 assignment1 plugin

31 videosTotal 153 minutes

Introduction to Gradient Descent5 minutesPreview module
Convex Functions2 minutes
Use of Derivatives3 minutes
How Gradient Descent Works3 minutes
Gradient Step2 minutes
Logistic Regression Algorithm1 minute
Data Visualization and Reading6 minutes
Updating Weights in Python4 minutes
Implementing Logistic Regression12 minutes
Visualization and Results8 minutes
Gradient Descent Versus Perceptron4 minutes
Linear to Non-Linear Boundaries4 minutes
Combining Probabilities2 minutes
Weighted Sums3 minutes
Neural Network Architecture12 minutes
Layers and DEEP Networks4 minutes
Multi-Class Classification2 minutes
Basics of Feed Forward7 minutes
Feed Forward for DEEP Net5 minutes
Deep Learning Algo Overview2 minutes
Basics of Backpropagation6 minutes
Updating Weights2 minutes
Chain Rule for Backpropagation5 minutes
Sigma Prime2 minutes
Data Analysis NN (Neural Networks) Implementation5 minutes
One-Hot Encoding (NN Implementation)3 minutes
Scaling the Data (NN Implementation)1 minute
Splitting the Data (NN Implementation)5 minutes
Helper Functions (NN Implementation)2 minutes
Training (NN Implementation)12 minutes
Testing (NN Implementation)3 minutes

1 assignmentTotal 15 minutes

Assessment 115 minutes

1 pluginTotal 15 minutes

Exploring Cross Entropy and Gradient Descent15 minutes

In this module, we will address optimization challenges in deep learning. Topics include underfitting vs. overfitting, regularization techniques, and strategies to overcome common issues like local minima and vanishing gradients. Learners will gain insights into improving their model's performance and reliability.

What's included

10 videos1 plugin

10 videosTotal 38 minutes

Underfitting vs Overfitting5 minutesPreview module
Early Stopping4 minutes
Quiz1 minute
Solution and Regularization6 minutes
L1 and L2 Regularization3 minutes
Dropout3 minutes
Local Minima Problem3 minutes
Random Restart Solution4 minutes
Vanishing Gradient Problem4 minutes
Other Activation Functions3 minutes

1 pluginTotal 15 minutes

Understanding Underfitting and Overfitting in Neural Networks15 minutes

In this module, we will undertake a comprehensive final project, applying all the concepts and skills learned throughout the course. Starting with data exploration and progressing through model training and testing, this project will solidify your understanding and ability to implement deep learning solutions.

What's included

5 videos3 assignments

Earn a career certificate

Add this credential to your LinkedIn profile, resume, or CV. Share it on social media and in your performance review.

Instructor

Packt - Course Instructors

Packt

751 Courses121,394 learners

Offered by

Packt

Explore more from Machine Learning

Edureka
Practical Deep Learning with Python
Course
IBM
Introduction to Deep Learning & Neural Networks with Keras
Course
Packt
Deep Learning - Crash Course 2023
Course
IBM
Deep Learning with Keras and Tensorflow
Course

Why people choose Coursera for their career

Felipe M.

Learner since 2018

"To be able to take courses at my own pace and rhythm has been an amazing experience. I can learn whenever it fits my schedule and mood."

Jennifer J.

Learner since 2020

"I directly applied the concepts and skills I learned from my courses to an exciting new project at work."

Larry W.

Learner since 2021

"When I need courses on topics that my university doesn't offer, Coursera is one of the best places to go."

Chaitanya A.

"Learning isn't just about being better at your job: it's so much more than that. Coursera allows me to learn without limits."

New to Machine Learning? Start here.

Open new doors with Coursera Plus

Unlimited access to 10,000+ world-class courses, hands-on projects, and job-ready certificate programs - all included in your subscription

Learn more

Advance your career with an online degree

Earn a degree from world-class universities - 100% online

Explore degrees

Join over 3,400 global companies that choose Coursera for Business

Upskill your employees to excel in the digital economy

Learn more

Frequently asked questions

Yes, you can preview the first video and view the syllabus before you enroll. You must purchase the course to access content not included in the preview.

If you decide to enroll in the course before the session start date, you will have access to all of the lecture videos and readings for the course. You’ll be able to submit assignments once the session starts.

Once you enroll and your session begins, you will have access to all videos and other resources, including reading items and the course discussion forum. You’ll be able to view and submit practice assessments, and complete required graded assignments to earn a grade and a Course Certificate.