Udemy – Deep Learning : Convolutional Neural Networks with Python 2025-2

Apr 18, 2025 - 19:15

0 0

Deep Learning Course: Convolutional Neural Networks with Python. In this comprehensive course, you will start by building deep convolutional neural network architectures from scratch, augmenting the data with various transformations to increase image diversity, optimizing HyperParameteres before training the model to improve performance, validating the model on test images, calculating performance metrics including Accuracy, Precision, Recall, F1 score, and visualizing the Confusion Matrix to see detailed insights into model performance beyond simple metrics. You will then move on to advanced CNN architectures including RESNT, ALEXNET for image classification, UNET, PSPNET encoder-decoder architectures for semantic segmentation, Region-based CNNs for OD, and YOLO CNNs for real-time object detection, sample segmentation, object tracking, and state estimation. Join us in this course, where you will not only understand the core concepts but also open the door to advanced CNN architectures, equipping yourself with the skills to overcome the most challenging computer vision tasks with confidence and expertise. You will follow a complete pipeline for deep learning CNNs for real-world applications.

What you will learn:

Deep Convolutional Neural Networks with Python and Pytorch from Beginner to Expert
Introducing deep learning and its building blocks: artificial neurons
Coding a Convolutional Neural Network Architecture from Scratch with Python and Pytorch
Hyperparameter Optimization for Convolutional Neural Networks to Improve Model Performance
Custom datasets with Augmentations to increase the diversity of image data
Training and testing a convolutional neural network using Pytorch
Performance metrics (Accuracy, Precision, Recall, F1 score) for evaluating CNNs
Visualizing the Confusion Matrix and Calculating Precision, Recall, and F1 Score
Advanced CNNs for Segmentation, Object Tracking, and State Estimation
Pretrained convolutional neural networks and their applications
Transfer learning using convolutional neural network models
Encoder-decoder architectures of convolutional neural networks
YOLO convolutional neural networks for computer vision tasks
Region-based convolutional neural networks for object recognition

Who is this course suitable for?

This course is designed for people with a strong interest in deep learning and convolutional neural networks (CNN) with Python and Pytorch to solve real-world AI problems.
Whether you are a beginner looking to build a strong foundation in computer vision, object tracking, segmentation, state estimation, classification, object recognition, or an experienced professional looking to upgrade your skills, this course will provide valuable insights and hands-on experience with CNNs.

Course details: Deep Learning: Convolutional Neural Networks with Python

Publisher: Udemy
Lecturer: Dr. Mazhar Hussain , AI & Computer Science School
Training level: Beginner to advanced
Training duration: 4 hours and 38 minutes
Number of lessons: 38

Course headings

Prerequisites for the Deep Learning: Convolutional Neural Networks with Python course

A Google Gmail account is required to get started with Google Colab to write Python Code
Python programming experience is an advantage but not required