Class Central is learner-supported. When you buy through links on our site, we may earn an affiliate commission.

TensorFlow Techniques for Model Optimization

Go to class Write review

Overview

This course delves into advanced TensorFlow techniques to boost model performance and reliability. Learn about using regularization and dropout to prevent overfitting, and explore real-time training improvements with callbacks. Each module is concise and impactful, equipping you with practical skills to enhance your machine learning models.

Syllabus

Unit 1: Implementing L2 Regularization in TensorFlow

Regularization: See it in Action
Modify Regularization Techniques in Model
Fix the Regularization Mistakes
Add L1 and L2 Regularization
Implement Regularization in TensorFlow

Unit 2: Adding Dropout to Prevent Overfitting

Model Summary with Dropout Layers
Adjust Dropout Rate in Model
Fix Model Dropout Issues
Add Dropout Layer to Model
Build a Model with Dropout

Unit 3: Utilizing Callbacks in TensorFlow

Implementing TensorFlow Callbacks
Modifying TensorFlow Callbacks
Debug TensorFlow Callbacks
Completing Callbacks Implementation in TensorFlow
Write TensorFlow Callbacks From Scratch

Unit 4: Bridging TensorFlow and Scikit-Learn through Keras Wrappers

Bridging Libraries for Evaluation
Adjust Cross Validation Parameters
Fix K-Fold Cross-Validation Bug
Integrate Scikit-Learn with TensorFlow
Bridging TensorFlow and Scikit-Learn

Reviews

Start your review of TensorFlow Techniques for Model Optimization