Teach on Udemy

Turn what you know into an opportunity and reach millions around the world.

Learn More

Your cart is empty.

Keep shopping

A deep dive in deep learning ocean with Pytorch & TensorFlow

Name: A deep dive in deep learning ocean with Pytorch & TensorFlow
Rating: 4.5 (117 reviews)

A comprehensive course about deep learning models with theory, intuition and implementation with Pytorch and TensorFlow

Created byZeeshan Ahmad

Last updated 10/2025

English

What you'll learn

Theory, Maths and Implementation of all the deep learning models
Pre-requisites for deep learning such as data preprocessing, Regression Analysis and Logistic Regression
Build Artificial Neural Networks and use them for Regression and Classification Problems
Using GPU with Deep Learning Models.
Creating our own custom loss functions and custom layers for deep learning models
Convolutional Neural Network ( CNN )
One Dimensional CNN
Setting early stopping criterion in deep learning models
Transfer Learning
Recurrent Neural Networks ( RNN )
Time series prediction and classification
Autoencoders and Variational Autoencoder ( VAE )
CNN Autoencoder and LSTM Autoencoder
Generative Adversarial Networks (GANs)
LSTM and Bidirectional LSTM
Transformer
Vision Transformer
Time Series Transformer
Neural Style Transfer
Implementation of deep learning models in Pytorch and Tensor Flow

Course content

46 sections • 319 lectures • 48h 30m total length

Introduction of the course10:42
Explore a comprehensive deep learning course with practical PyTorch and TensorFlow implementations, covering neural networks, CNNs, RNNs, autoencoders, GANs, transformers, and neural style transfer.
Course Material0:28
How to succeed in this course1:14

Introduction of the section2:23
Drive mounting and data reading13:51
Mount Google Drive in Colab, set the path to drive my drive / Introduction to Google Colab, upload folders, and run cells to read a CSV with pandas.
Reading and displaying images8:01
Reading more datasets4:43
Learn to read datasets from seaborn library using sns.load_dataset (iris) without mounting drives, and from Google Colab sample data using pandas.read_csv with a copied path (mNIST, California housing data).
Uploading Course Material to Google drive and observing course organization6:13
Upload and organize course material on Google Drive for deep learning with PyTorch and TensorFlow, including unzipping archives and exploring supervised and unsupervised sections.

Introduction of the section2:50
Arithmetic with python10:09
Comparison and logical operations5:52
Conditional Statements8:14
Arrays with Numpy part0111:31
Learn to create and manipulate NumPy arrays, including 1D and 2D shapes, by importing NumPy as np, inspecting shape, size, and dtype, and locating max, min, and argmax/argmin indices.
Arrays with Numpy part0215:02
Explore NumPy array creation and manipulation, including arange, linspace, and reshape. Generate zeros, ones, and identity matrices, and sample random numbers from normal, uniform distributions, and randint for integers.
Arrays with Numpy part0310:52
Plotting and Visualization part0117:51
Plotting and Visualization part0215:03
Plotting and Visualization part0313:34
Plotting and Visualization part047:35
Lists in python20:27
For loop part0121:03
Learn to use Python for loops with range, indentation, and if statements to print digits and hello, generate even and odd numbers, and sum the first ten numbers.
For loop part0220:36
while loop12:16
Learn how the while loop executes until a condition is met, avoid infinite loops with an increment operator, and use break statements, with comparisons to for loops and nested cases.
Strings in Python12:39
Print formatting with strings3:36
Dictionaries part017:11
learn how dictionaries use keys to access values via key-value pairs and curly braces, unlike arrays that use numeric indexing, and explore items, keys, and values of different types.
Dictionaries part028:04
Seaborn part018:21
Seaborn part026:50
Seaborn part037:16
Explore correlation analysis of numerical features in the Tips dataset using a correlation matrix, heat map, and scatter plots to link total bill, tip, and size.
Pandas part016:24
Pandas part025:20
Pandas part038:54
Pandas part045:54
Clean a Pandas data set by copying data, replacing nulls with 1000, and making permanent changes such as region with news and other columns with mean, median, or std.
Functions in python part018:15
Functions in python part027:59
Classes in Python15:50
Tuples in Python6:25
lambda function8:48
map function7:47
reduce function5:13
filter function4:47
zip function8:31
join function4:13

Introduction of the section3:09
Need of data preprocessing4:02
Learn why data preprocessing matters in deep learning. Tackle missing values, noise, and uninterpretable data from sensors, and scale features with different magnitudes to improve model training.
Data Normalization and MinMax scaling6:27
Project01 : Data Normalization and MinMax scaling part019:16
Project01 : Data Normalization and MinMax scaling part0211:25
Data Standardization4:23
Project02 : Data Standardization8:21
Project03 : Dealing with missing values16:37
Learn to preprocess data by handling missing values in a pandas data frame. Replace uninterpretable marks with NaN, then apply column-specific strategies using mean, median, and standard deviation.
Project04 : Dealing with categorical features14:53
Project05 : Feature Engineering9:05
Project06 : Feature Engineering by window method12:48
Explore feature engineering by window method in data pre-processing, creating new features from sliding windows, including the minimum, maximum, mean, and standard deviation, and updating the labels accordingly.

Introduction of the section5:03
Origin of the Regression13:11
Definition of Regression3:49
Define linear regression as a linear relationship between a feature and a target. Transform the linear model into the regression equation using weight w and bias w0.
Requirement from Regression3:23
Simple Linear Regression6:38
Discover simple linear regression with a single feature, where weight acts as the slope linking x to y, using a salary dataset and zero-bias or zero-weight cases.
Multiple Linear Regression4:32
Target and predicted values3:50
Explore target values versus predicted values in a one-feature linear regression model, learn how prediction errors arise, and understand how zero error yields 100% accuracy.
Loss function4:08
Least square method14:32
Numerical example on least square method5:07
Evaluation metrics for regression8:07
Project01 : simple regression part019:41
Project01 : simple regression part028:46
Project01 : simple regression part0318:26
Project02 : multiple regression part0110:49
Project02 : multiple regression part0210:37
Transform make regression data into a named data frame with research, salaries, infrastructure, and expenditure, then apply multiple regression and visualize feature influence on expenditure.
Project02 : multiple regression part0315:46
Project03 : multiple regression15:04
Apply multiple linear regression in Python to predict yearly spend from features like average session length, time on app, website time, and membership length; evaluate with rmse and r-squared.
Regression by Gradient descent9:58
Project04 : Gradient descent on simple linear regression19:31
Project05 : Gradient descent on multiple linear regression15:31
Polynomial Regression6:30
Project06 : Polynomial Regression12:10
Implement polynomial regression in python by transforming the experience feature into polynomial features and applying linear regression. Evaluate r-squared, rmse, and mae to identify the optimal degree for predicting salary.
Cross-validation3:32
Use cross-validation to evaluate models on limited data by splitting into k folds, such as five-fold or ten-fold, training on k-1 folds, testing on remainder, and averaging results across folds.
Project07 : Cross-validation13:57
Bias-variance tradeoff ( Overfitting and underfitting )12:04
Concept of regularization4:31
Ridge regression OR L2 regularization9:55
Lasso regression OR L1 regularization8:02
Explore lasso regression and L1 regularization, which shrink weights toward zero to produce sparse models, especially under multicollinearity. Learn how lambda controls penalty, bias, and feature selection.
Comparing Ridge and Lasso regularization3:06
Elastic Net regularization3:16
Project08 : Regularization21:18
Grid search cross-validation4:02
Project09 : Grid search CV20:31

Introduction of the section2:21
Basic concept7:34
Limitations of regression models9:26
Transforming Linear regression into logistic regression8:05
Project01 : Getting class probabilities part018:23
Train a logistic regression model to estimate class probabilities for cancer using tumor size data. Learn data preparation, 2d reshaping, and using predict_proba and predict to classify a test sample.
Project01 : part0211:31
Loss function for logistic regression5:33
Model evaluation - Confusion Matrix10:14
Learn to evaluate a logistic regression model with a confusion matrix, understanding true positives, true negatives, false positives, false negatives, and compute accuracy and type one and two errors.
Accuracy, precision, recall, f1-score14:02
ROC curves and area under ROC3:42
Project02 : Evaluating Logistic Regression Model21:27
Project03 : Logistic Regression Model with cross-validation17:01
Project04 : Multiclass classification with logistic regression21:46
Project05 : Logistic Regression on challenging data part017:14
Project05 : Logistic Regression on challenging data part025:56
Project05 : Logistic Regression on challenging data part037:45
Grid search CV13:14
Apply grid search cross-validation to optimize logistic regression, tuning penalty, C, fit intercept, and solvers, and evaluate with classification report, confusion matrix, and roc curve on a dataset with two features.

Introduction of the section1:57
Explore the foundations of neural networks and deep learning, from perceptrons and artificial neurons to weights, activation functions, forward and backward propagation, and the rise of deep learning with PyTorch.
The perceptron16:03
Features, weights and Activation function7:01
Explore how perceptrons process features with weights and activation functions to produce neural network outputs and make binary decisions, exemplified by candidate selection.
Learning of Neural Network9:34
Explore how neural networks learn through forward propagation to generate predictions and backward propagation to update weights and bias using gradient descent with a learning rate.
Rise of deep learning7:40

Introduction of the section1:49
Classification by perceptron part017:27
Learn how a perceptron classifies boolean and gate data by learning a linear decision boundary with weights and bias, demonstrated on a 2d dataset.
Classification by perceptron part027:07
Why we need Activation functions6:54
Learn why activation functions are essential for neural networks to learn non-linear patterns, illustrated by the XOR gate, enabling non-linear classification beyond linear models.
Adding Activation function to Neural Network4:58
Explore how to add activation functions to hidden and output layers in a neural network, enabling non-linear learning and aiding classification or regression, demonstrated with PyTorch.
Sigmoid as activation function8:01
Hyperbolic tangent function5:08
ReLU and Leaky ReLU functions6:19

Requirements

Some Programming Knowledge is preferable but not necessary
Gmail account ( For Google Colab )
Basic Maths

Description

Course Contents

Deep Learning and revolutionized Artificial Intelligence and data science. Deep Learning teaches computers to process data in a way that is inspired by the human brain.

This is complete and comprehensive course on deep learning. This course covers the theory and intuition behind deep learning models and then implementing all the deep learning models both in Pytorch and Tensor flow.

Practical Oriented explanations Deep Learning Models with implementation both in Pytorch and Tensor Flow.

No need of any prerequisites. I will teach you everything from scratch.

Job Oriented Structure

Sections of the Course

· Introduction of the Course

· Introduction to Google Colab

· Python Crash Course

· Data Preprocessing

· Regression Analysis

· Logistic Regression

· Introduction to Neural Networks and Deep Learning

· Activation Functions

· Loss Functions

· Back Propagation

· Neural Networks for Regression Analysis

· Neural Networks for Classification

· Dropout Regularization and Batch Normalization

· Optimizers

· Adding Custom Loss Function and Custom Layers to Neural Networks

· Convolutional Neural Network (CNN)

· One Dimensional CNN

· Setting Early Stopping Criterion in CNN

· Recurrent Neural Network (RNN)

· Long Short-Term Memory (LSTM) Network

· Bidirectional LSTM

· Generative Adversarial Network (GAN)

· DCGANs

· Autoencoders

· LSTM Autoencoders

· Variational Autoencoders

· Neural Style Transfer

· Transformers

· Vision Transformer

· Time Series Transformers

. K-means Clustering

. Principle Component Analysis

. Deep Learning Models with implementation both in Pytorch and Tensor Flow.

Who this course is for:

Beginners who want to learn Deep Learning from Scratch.
Students enrolled in Deep Learning course in universities and colleges.
Researchers in Deep Learning and Generative AI
Students and Researchers who want to develop Python Programming skills and want to implement deep learning models both in Pytorch and TensorFlow
For those who know how to implement deep learning in Matlab but want to switch to Pytorch and TensorFlow

A deep dive in deep learning ocean with Pytorch & TensorFlow

What you'll learn

Explore related topics

Course content

Introduction of the course and course material3 lectures • 12min

Introduction to Google Colab5 lectures • 35min

Python crash course36 lectures • 5hr 51min

Pre-requisites sections1 lecture • 2min

Pre-requisite : Data Preprocessing11 lectures • 1hr 40min

Pre-requisite : Regression Analysis34 lectures • 5hr 29min

Pre-requisite : Logistic Regression17 lectures • 2hr 55min

Introduction to Neural Networks and Deep Learning5 lectures • 42min

Activation Functions8 lectures • 48min

Loss Function4 lectures • 25min

Requirements

Description

Who this course is for: