English | MP4 | AVC 1920×1080 | AAC 44KHz 2ch | 135 lectures (16h 12m) | 18.13 GB
From Zero to your own AI models: Master Deep Learning with PyTorch. No previous experience required.
Have you ever watched AI automatically classify images or detect spam and thought, “I wish I could do that”? With this course, you’ll learn how to build and deploy your own deep learning models in just 15 days – gaining practical, hands-on experience every step of the way.
Why This Course?
From day one, you’ll get comfortable with the essential concepts that power modern AI. No fluff, no endless theory – you’ll learn by building real-world projects like Spam filters, or image detections. By the end, you won’t just know what neurons and neural networks are – you’ll be able to train, refine, and apply them to projects that truly matter.
Who Is This Course For?
- Absolute beginners eager to break into the world of AI and deep learning.
- Data enthusiasts who want to strengthen their portfolios with hands-on projects.
- Developers and data scientists looking to deepen their PyTorch and model deployment skills.
- Anyone who craves a clear roadmap to mastering deep learning, one day at a time.
What Makes This Course Unique?
- Day-by-Day Progression: Follow a structured, 15-day plan that ensures you never feel lost or overwhelmed.
- Real-World Projects: Predict used car prices, detect spam in SMS, classify handwritten digits, recognize fashion items—all using deep learning techniques.
- Modern Tools & Frameworks: Master industry-standard tools like PyTorch and dive into CNNs, transfer learning with ResNet, and more.
- Practical Deployment: Learn how to turn your trained models into interactive apps with Gradio, making your projects truly come alive.
By the End of This Course, You Will:
- Confidently implement, train, and evaluate deep learning models.
- Understand how to prepare and process various types of data, from text to images.
- Know how to improve and optimize your models to achieve better performance.
- Be ready to deploy your AI solutions, making them accessible and interactive for real users.
No Prior Experience Needed
Whether you’re a coding novice or a data analyst stepping into AI, this course starts from the very basics. You’ll be guided through installing Python, PyTorch, and setting up your coding environment, all the way to training full-fledged neural networks on your GPU.
Get Ready to Dive In
If you’ve always wanted to get into deep learning, now is your chance. Enroll today and join me on a practical, hands-on journey that will transform the way you see and build AI solutions. In 15 days, you’ll have gone from curious beginner to proud deep learning practitioner—with real projects to show for it.
What you’ll learn
- 15-Day Roadmap to AI Mastery: Build, train, and deploy deep learning models in a structured timeline – step by step from beginner to pro
- Hands-On Project Focus: Create real-world applications like spam filters, image classifiers, and price predictors to solidify your skills
- Practical Deployment Expertise: Transform models into interactive apps with Gradio for immediate, hands-on results
- From Basics to Advanced: Dive into neurons, CNNs, transfer learning, and more. Master the PyTorch easily on the way
- Effective Data Handling: Learn how to preprocess, optimize, and evaluate diverse data types (images, text, …)
- Have fun while learning: Many interactive quizzes and practical exams included
- Harness the Power of Transfer Learning with ResNet for Advanced Classification
- Master Essential Tools: Python, PyTorch, Jupyter, and Visual Studio Code
Table of Contents
Introduction
1 Overview Practical Deep Learning
Day 1 Foundations of Neural Networks From Models and Neurons to Tensors
2 Test your knowledge about the Foundations of Machine Learning and Models
3 Course Materials
4 Test your knowledge on Neurons and Tensors in Machine Learning
5 Installing the necessary tools Windows
6 Test your knowledge on Simple Neural Networks and PyTorch Basics
7 Installing the necessary tools Linux
8 Installing the necessary tools macOS
9 Running a first file
10 What is a model
11 A First Neuron
12 A First Neuron in Python
13 What is a Tensor
14 Handling the Data Type of a Tensor in PyTorch
15 Manually Setting Parameters
Day 2 Neuron Training From Adjusting Parameters to Batch Learning
16 Test your knowledge on Training Neurons and Learning Parameters
17 Test your knowledge on Loss Functions Learning Rates Parameter Initialization
18 Test your knowledge on Gradient Descent
19 Test your knowledge on Data Handling and Iterative Training
20 Test your knowledge on Batch Learning Loss Functions and Training Process
21 Introduction to Neuron Training
22 What is learning
23 How Neuron Learns A Scalable Approach
24 Understanding Gradient Descent for Neuron Optimization
25 Training a Neuron 1 Preparing and Optimizing
26 Optimizing Training for Our Neuron Model
27 Training a Neuron 2 Iterative Learning and Adjustments
28 The Importance of Mean Squared Error in Model Training
29 Batch Learning and Making Predictions with PyTorch
Day 3 4 Single Neuron Regression Predicting Used Car Prices with PyTorch
30 Test your knowledge on Used Car Dataset and Jupyter
31 Test your knowledge on Data Exploration and Preparation with Pandas
32 Test your knowledge on Data Preparation and Initial Neuron Training Steps
33 Test your knowledge on Output Data Normalization
34 Test your knowledge on Input Data Normalization
35 Test your knowledge on Data Preparation Model Training and Evaluation
36 Day 3 Introduction to Predicting Used Car Prices
37 Overview of the Used Car Price Dataset
38 Getting Started with Jupyter Interactive Python Programming
39 Exploring the Used Car Dataset with Pandas
40 Investigating Key Data Relationships for Model Training
41 Finalizing Input and Target Columns for Model Training
42 Structuring Data for Model Input and Running an Initial Prediction
43 Training the Model Initial Setup and Challenges
44 Day 4 Understanding Output Normalization for Stable Learning
45 Implementing Output Normalization in PyTorch for Consistent Predictions
46 Understanding Input Normalization for Consistent Training
47 Implementing Input Normalization in PyTorch for Improved Predictions
48 Experimenting with Training Parameters Through Loss Visualization
49 Saving and Loading Model in PyTorch
50 Exercise Adding an Additional Column to the Model
51 Solution Adding an Additional Column to the Model
Day 5 6 Neuron Classifier Spam Detection in SMS
52 Test your knowledge on Spam Detection and Text Preprocessing
53 Test your knowledge on Model Training and Sigmoid Function for Spam Detection
54 Test your knowledge on Loss Functions and Evaluation Metrics in Spam Detection
55 Test your knowledge on Data Segmentation in Model Development
56 Optional extra Test your knowledge on Enhancing Detection with LLM Embeddings
57 Test your knowledge on Spam Detection Techniques
58 Day 5 Introduction to Spam Detection
59 Exploring and Preprocessing the SMS Spam Dataset
60 Using Count Vectorizer to Transform Text into Numerical Data
61 Optional Extra Exploring TFIDF Vectorizer for Improved Text Preprocessing
62 Training the Model for Spam Classification
63 Optimizing Training for Our Neuron Classifier
64 Understanding the Sigmoid Activation Function for Probability Output
65 Switching to Binary Cross Entropy Loss for Effective Training
66 Using BCE with Sigmoid for Loss Calculation and Prediction
67 Evaluating Model with Key Performance Metrics
68 Day 6 Understanding Training Validation and Test Data in Model Development
69 Implementing Training and Validation Data Splits in Python
70 Applying and Evaluating the Model on Fresh Data
71 Optional extra Improving Spam Detection with Large Language Model Embeddings
72 Optional extra Generating Embeddings with BART for Spam Detection
73 Optional extra Building a Function to Generate Embeddings for Spam Detection
74 Optional extra Integrating Embeddings into the Spam Filter
Day 6 Exam
75 PRACTICE EXAM Test your knowledge so far 12
Day 7 8 Neural Network Classifier Student Exam Results Prediction
76 Test your knowledge on Neural Network Fundamentals
77 Test your knowledge on Data Analysis and Neural Network Training
78 Test your knowledge on Neural Network Application Techniques
79 Test your knowledge on Optimizing Neural Networks with ReLU and Adam
80 Test your knowledge on Essential Neural Network Concepts
81 Day 7 From Single Neuron to Neural Networks
82 Optional Understanding Activation Functions in Neural Networks
83 Optional extra Exploring Nonlinearity and Its Impact on Neural Networks
84 Understanding Backpropagation in Neural Networks
85 Optional Decoding the Mathematics of Backpropagation
86 Analyzing Student Performance Data for Exam Predictions
87 Optional Applying a Single Neuron to Student Exam Data
88 Building and Training Our First Neural Network
89 Optimizing Training for Our Neural Network Classifier
90 Evaluating Neural Network Performance
91 Simplifying the Code with nnSequential
92 Day 8 Introducing ReLU Activation Function
93 Optimizing Training with Adam
94 Implementing MiniBatch Learning for Efficient Training
95 Optimizing Loss Tracking in MiniBatch Training
Day 8 Exercise Loan Approval Classification
96 Introduction to Loan Approval Prediction
97 Exploring the Loan Approval Dataset
98 Solution Part 1 Preparing Data for the Loan Approval Model
99 Solution Part 2 Building and Training the Loan Approval Model
Day 9 10 Neural Network for MultiClass Classification Handwritten Digits
100 Test your knowledge on Data Preparation for Neural Network Training
101 Test your knowledge on Binary Classifier Essentials
102 Test your knowledge on Preparing Data for MultiClass Classification
103 Test your knowledge on Neural Network Adjustments for MultiClass Classification
104 Test your knowledge on Softmax and Network Architecture
105 Test your knowledge on Overfitting in Neural Network
106 Test your knowledge on MultiClass Classifier Fundamentals
107 Day 9 Introduction to Handwritten Digit Classification
108 Exploring MNIST Data with TorchVision
109 From Dataset to DataLoader Preparing Data for Neural Network
110 Building a Binary Classifier for 0 Detection
111 Evaluating the Binary Classifier for 0 Detection
112 MultiClass Classification in Neural Networks
113 Understanding OneHot Encoding
114 Training a Neural Network for MultiClass Classification
115 Optimizing Training for Our Neural Network MultiClass Classifier
116 Evaluating a Neural Network for MultiClass Classification
117 Day 10 Understanding Softmax for Class Probability Normalization
118 Applying Softmax in Neural Network
119 Experimenting with Different Neural Network Architectures
120 Understanding Overfitting in Neural Networks
121 Demonstrating Overfitting in Neural Network Training
122 Strategies to Counter Overfitting
123 Optional extra Applying a Neural Network to Custom Images
124 Optional extra Overcoming Preprocessing Challenges in Model Application
Day 11 12 Convolutional Networks Fashion Item Classification multiclass
125 Test your knowledge on CNN Basics and Image Processing
126 Test your knowledge on CNN Architecture and Functionality
127 Test your knowledge on Max Pooling in CNNs
128 Test your knowledge on Utilizing GPUs with PyTorch
129 Test your knowledge on CNN Layer Configurations
130 Test your knowledge on Dropout and Batch Normalization
131 Test your knowledge on Key CNN Techniques
132 Day 11 Introduction to Convolutional Neural Networks
133 Exploring Fashion MNIST Data
134 Optional Assessing Previous Model Performance on Fashion MNIST Data
135 Exploring Edge Detection with the Sobel Operator
136 Understanding the Structure of Convolutional Neural Networks for Edge Detection
137 Part 1 Implementing a CNN
138 Part 2 Advancing CNN Implementation
139 Optimizing Training for Our CNN
140 Reducing CNN Complexity with Max Pooling
141 Utilizing GPU Acceleration with PyTorch
142 Optional Enabling CUDA on NVIDIA GPUs
143 Leveraging Google Colabs Free GPU
144 Optimizing Tensor Computations on GPU
145 Running Simple Model on GPU
146 Accelerating CNN Execution Speed with GPU
147 Day 12 Advancing CNN Complexity
148 Enhancing CNN Performance with Increased Filter Complexity
149 Introducing Dropout for Improved Generalization
150 Optimizing CNN with Dropout Layers
151 Refining CNN with Batch Normalization
152 Optional Understanding the Mathematics of Batch Normalization
153 Optional extra Application of Overfitting Detection and Model Finalization
Day 13 14 Transfer Learning with ResNet for Tire Quality Prediction
154 Test your knowledge of Transfer Learning and ResNet
155 Test your knowledge on Preparing and Modifying ResNet for Transfer Learning
156 Test your knowledge on Training and Evaluating a Transfer Learning Model
157 Test your knowledge on Enhancing Models with Data Augmentation
158 Test your knowledge on Tire Quality Prediction and Transfer Learning
159 Day 13 Introduction to Transfer Learning and Tire Quality Prediction
160 Preparing the Tire Quality Dataset
161 Exploring the Tire Quality Dataset
162 An Introduction to ResNet in Transfer Learning
163 Using ResNet50 to Classify an Image of a Cat
164 Optional extra Exploring the ResNet Research Paper
165 Preparing Data for ResNet Training
166 Part 1 Customizing ResNet50 for Tire Quality Prediction
167 Part 2 Building a Transfer Learning Model for Tire Quality Prediction
168 Day 14 Part 3 Training the Transfer Learning Model
169 Part 4 Evaluating Model Performance and Addressing Overfitting
170 Data Augmentation for Combating Overfitting
171 Integrating Data Augmentation into Model Training for Improved Accuracy
172 Adapting Model Weights for Universal Compatibility
173 Using the Trained Model to Predict Tire Quality
174 Testing Approaches for Tire Model Deployment
Day 15 Deploying AI Models with Gradio From Setup to RealWorld Predictions
175 Test your knowledge on Gradio and AI Model Integration
176 Test your knowledge on RealWorld Testing of Gradio Apps
177 Introduction to Deploying AI Models with Gradio
178 Getting Started with Gradio for Simple AI Apps
179 Uploading and Processing Images with Gradio
180 Integrating Gradio with PyTorch for Predictions
181 Deploying Gradio for RealWorld Tire Predictions
Day 15 Exam
182 PRACTICE EXAM Test your knowledge so far 22
Closing words
183 Closing words
Resolve the captcha to access the links!