Machine Learning and Deep Learning Using TensorFlow
Learn AI: Machine Learning, Deep Learning (DNN), and CNNs. Explore cutting-edge techniques for intelligent systems and data analysis.
Course Content
Machine Learning and Deep Learning Using TensorFlow is an all-levels Udemy course taught by Saikat Ghosh. It runs 10h 5m, is taught in English, and includes a certificate of completion. Learners rate it 4.7 out of 5 from 50 reviews, with 625 students enrolled. It is a paid course, first published April 2022.
Dive into the world of Machine Learning with this comprehensive course! Perfect for those seeking a deep and clear understanding of core concepts, this course progresses step-by-step, ensuring you grasp each idea thoroughly. We dedicate ample time to explanations, sometimes spending over 10 minutes on a single slide to solidify your knowledge.
What You'll Learn:
- Fundamentals of Machine Learning: Start with a solid foundation in Machine Learning principles.
- Linear Regression: Understand Linear Regression and how to calculate parameters using Gradient Descent with the Mean Squared Error (MSE) Cost Function.
- Logistic Regression: Explore Logistic Regression for classification, including Decision Boundaries and the Sigmoid Function. Learn Gradient Descent and address the limitations of MSE Cost Function with Entropy and Cross-Entropy.
- Cross-Entropy Cost Function: Master Cross-Entropy as a cost function for Logistic Regression and implement Gradient Descent with it.
- Multiclass Classification: Learn Logistic Regression for Multiclass Classification.
- Introduction to Neural Networks: Discover the basics of Neural Networks and how they model logical operators using Perceptrons.
- Biological Neuron & Neural Network Anatomy: Understand the inspiration behind Neural Networks from the biological neuron and explore the anatomy of an image.
- Deep Neural Networks (DNN): Delve into Deep Neural Networks (DNN) and learn how to calculate weights using Backpropagation. Master techniques to update weights in hidden layers using the Cross Entropy Cost Function.
- Convolutional Neural Networks (CNN): Explore Convolutional Neural Networks (CNN), including CNN Architecture, Feature Extraction, Filters, and Pooling Layers.
- Image Classification with CNNs: Build CNN models for Image Classification using Google Colab and TensorFlow.
- Overfitting & Underfitting: Learn practical methods to address Overfitting and Underfitting, including Regularization, Data Augmentation, Dropout, and Early Stopping.
- Practical Applications: Develop a Diabetes prediction model using Google Colab and apply techniques like Regularization, Dropout, and Early Stopping to improve performance.
- Model Management: Learn how to Save Weights and Load the Saved Weights in Google Colab.
- Advanced Techniques: Explore Functional API and Transfer Learning in Google Colab.
- Intermediate Layer Manipulation: Extract output from intermediate layers and add new layers to build custom models.
Hands-on Experience:
This course emphasizes practical application with downloadable hands-on examples using TensorFlow 2 in Google Colab. You'll gain experience running complex neural network jobs and develop skills applicable to real-world projects. The first two videos provide a great introduction to the course content.
Key Concepts Covered:
- Gradient Descent
- Cross Entropy
- Backpropagation
- Regularization
- Data Augmentation
- Dropout
- Early Stopping
- TensorFlow 2
- Google Colab
- CNN Architecture
- Feature Extraction
- Filters
- Pooling Layers
- Transfer Learning
Want AI in your product? Hire the team behind TutorialSearch.io
LLM features, RAG, agents and automation wired into a real product — built by the devs who shipped this site.