Your cart is empty.
Keep shoppingTransfer Learning in modern DL: 3 AI Projects with PyTorch
New
105 students
Transfer Learning in modern DL: 3 AI Projects with PyTorch
Understand concepts, compare CNN and NLP models, fine-tune and evaluate, and develop 3 practical AI projects.
Created bySwetha S
Last updated 8/2026
English
What you'll learn
- understand fundamentals of Transfer learning and why it is widely used in modern AI applications
- understand the difference between traditional deep learning and modern transfer learning approaches
- 3 hands on projects in computer vision, NLP, Speech recognition with elaborated fine tuning methods to understand about evaluation metrics better
- detailed explanation of code with possible range of values that can be given to each parameter
- students can confidently explain the theory behind Transfer learning
- effectively fine-tune pretrained models to improve prediction accuracy.
- identify the project shortcomings and tune the project better.
- those 3 project uses more than two transfer learning models and traditional ML approach to compare better performance.
- ResNet and EfficientNet architecture with projects
- BERT basics and project ideas
- Whisper in deep learning and sppech recognition
Explore related topics
Course content
5 sections • 5 lectures • 6h 26m total length
Requirements
- knowledge of python programming language upto object oriented programming. basic understanding of AI model understanding and is optional as basic architecture is explained briefly. tools needed: google colab notebook, visual studio code for projects.
Description
Almost all cutting-edge AI applications use pretrained models rather than training from scratch, and transfer learning is one of the most useful techniques in contemporary deep learning.
In this course, you'll learn transfer learning from the ground up through clear theoretical explanations and three complete real-world projects.
You'll first build a strong conceptual understanding by learning:
What is Transfer Learning?
Knowledge Base and Knowledge Transfer
Source and Target Domains
Source and Target Tasks
Transfer Learning Workflow
Feature Extraction vs Fine-Tuning
Transfer Learning Terminologies
Types of Transfer Learning
Popular Pretrained Models architecture and applications:
ResNet
EfficientNet
MobileNet
Densenet
VGGNet
BERT
ELMo
Word2Vec
Glove
Whisper
ASR
text2speech
Advantages and Disadvantages of Transfer learning
Once you have mastered the theory, you will use these ideas in three real-world projects:
Flower Image Prediction using MobileNet, ResNet50, and EfficientNetB0 with model comparison and fine-tuning.
SaaS Ticket Routing using DistilBERT and TF-IDF Vectorization + Logistic Regression to categorize the customer complaints and compares performance with traditional machine learning approach and Transfer learning model.
Video Caption Generation using faster Whisper for automatic speech-to-text transcription.
You will learn how to create, train, assess, compare, and implement transfer learning models while gaining practical experience with PyTorch throughout the course.
By the end of this course, you'll have both the theoretical knowledge and practical experience needed to confidently implement transfer learning in your own AI projects.
Who this course is for:
- machine and deep learning students who wants to understand how pre trained models are used in real world applications
- python programmers who are curious to learn about modern AI applications with detailed code
- graduate students seeking for better understanding of pretrained models like ResNet, MobileNet, EfficientNet, BERT, DistilBERT, and Whisper