What you'll learn

Course content

6 sections • 36 lectures • 2h 29m total length

Applications of Deep Learning5:12
Explore how deep learning enables applications from colorizing black-and-white images to language recognition and translation, image captioning, sentiment analysis, and autonomous vehicles.
What is Deep Learning?1:36
Why Deep Learning?1:08
Why now?1:38
Explore how data, cheap and fast computing power, and history of neural networks from the 1980s–1990s enabled deep learning breakthroughs, including computer vision in 2012 and machine translation in 2014.

Perceptron12:13
Sigmoid Function6:39
Learn how the sigmoid function converts model scores into probabilities for binary classification, enabling probability-based decisions between apple and orange and moving beyond 0/1 outputs.
Softmax Function5:27
One Hot Encoding3:56
Represent categorical variables with one-hot encoding, using binary indicators to mark each category's presence. Avoid ordinal bias and apply dummy variable representation with color examples.
Activation Functions4:50
Logic Gates and XOR Problem3:54

Cross Entropy6:19
Loss Optimization3:24
Explain loss optimization in neural networks by using a linear model wx + b to produce class scores and convert them to probabilities, then minimize cross-entropy loss across training data.
Gradient Descent12:10
Non Linear Models3:20
Feed Forward3:00
Backward Propagation2:18
Overfitting problem4:42
Early Stopping5:57
Regularization4:26
Drop out1:23
Vanishing Gradient Problem4:03

Need for feature extraction5:18
Explore why convolutional neural networks require feature extraction to capture spatial and temporal characteristics in images, rather than just flattening pixels for effective image classification.
Preprocessing1:39
Convolution Operation21:10
Pooling Layer4:25
Flattening
Flattening converts two dimensional feature maps after pooling into vectors for the fully connected layers, enabling classification after a sequence of convolution and pooling stages.

Interested in the field of Machine Learning and Deep Learning? Then this course is for you!

This course is designed in a very simple and easily understandable content.

You might have seen lots of buzz on deep learning and you want to figure out where to start and explore.

This course is designed exactly for people like you!

If basics are strong, we can do bigger things with ease.

My focus in this course is to build complicated things starting from very basics

In this course, I will cover the following things

Session 1 – Introductory material on Deep learning, its applications and significance.
Session 2 - Introduces the fundamental building block of deep learning
Session 3 – Logistic Regression, Activation Functions, Perceptron, One Hot Encoding, XOR problem and Multi-Layer Perceptron models
Session 4 – Training of Neural Networks: Cross Entropy, Loss Function, Gradient descent Algorithm, Non-Linear Models, Feed Forward, Backward propagation, Overfitting problem, Early stopping, Regularization, drop out and Vanishing Gradient problem.
Session 5 – Convolution Neural Networks: Feature Extraction, Convolution Layer, Pooling Layer, Relu, Flattening and Deep Convolution Neural Networks.
Session 6 – Sequence Models: Recurrent Neural Networks, LSTMs

Are there any course requirements or prerequisites?

Who this course is for:

Anyone interested in Machine Learning and Deep Learning
Students who have high school knowledge in mathematics and who want to start learning Deep Learning
Any intermediate level people who know the basics of machine learning, who want to learn more advanced topics like deep learning
Any students in college who want to start a career in Data Science
Any data analysts who want to level up in Machine Learning and Deep Learning
Any people who are not satisfied with their job and who want to become a Data Scientist
Any people who want to create added value to their business by using powerful Learning tools
Build a foundation on the principles of Deep Learning to understand the latest trends

Anyone interested in Machine Learning and Deep Learning
Students who have high school knowledge in mathematics and who want to start learning Deep Learning
Any intermediate level people who know the basics of machine learning, who want to learn more advanced topics like deep learning
Any students in college who want to start a career in Data Science
Any data analysts who want to level up in Machine Learning and Deep Learning
Any people who are not satisfied with their job and who want to become a Data Scientist.
Any people who want to create added value to their business by using powerful Learning tools.
Build a foundation on the principles of Deep Learning to understand the latest trends