Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization

Mark as Favorite Share
image

What Will You Learn?

In the second Deep Learning Specialization course, uncover the inner workings of deep learning, learning systematic approaches to drive performance. By the end, you'll master key practices for training, analyzing bias/variance, and implementing standard neural network techniques in TensorFlow, including regularization, hyperparameter tuning, and optimization algorithms like gradient descent and Adam. Gain practical skills for building robust deep learning applications.

About This Course

Provider: Coursera
Format: Online
Duration: 23 hours to complete [Approx]
Target Audience: Intermediate
Learning Objectives: By the end, you will learn the best practices to train and develop test sets and analyze bias/variance for building deep learning applications
Course Prerequisites: Intermediate Python skills: basic programming, understanding of for loops, if/else statements, data structures, A basic grasp of linear algebra & ML
Assessment and Certification: Earn a Certificate upon completion from the relevant Provider
Instructor: DeepLearning.AI
Key Topics: Deep Learning, Tensorflow, hyperparameter tuning, Mathematical Optimization
Topic Covered: 
  2. - Train / Dev / Test sets
  3. - Bias / Variance
  4. - Basic Recipe for Machine Learning
  5. - Regularization
  6. - Why Regularization Reduces Overfitting?
  7. - Dropout Regularization
  8. - Understanding Dropout
  9. - Other Regularization Methods
  10. - Normalizing Inputs
  11. - Vanishing / Exploding Gradients
  12. - Weight Initialization for Deep Networks
  13. - Numerical Approximation of Gradients
  14. - Gradient Checking
  15. - Mini-batch Gradient Descent
  16. - Understanding Mini-batch Gradient Descent
  17. - Exponentially Weighted Averages
  18. - Understanding Exponentially Weighted Averages
  19. - Bias Correction in Exponentially Weighted Averages
  20. - Gradient Descent with Momentum
  21. - RMSprop
  22. - Adam Optimization Algorithm
  23. - Learning Rate Decay
  24. - The Problem of Local Optima
  25. - Tuning Process
  26. - Using an Appropriate Scale to pick Hyperparameters
  27. - Hyperparameters Tuning in Practice: Pandas vs. Caviar
  28. - Normalizing Activations in a Network
  29. - Fitting Batch Norm into a Neural Network
  30. - Why does Batch Norm work?
  31. - Batch Norm at Test Time
  32. - Softmax Regression
  33. - Training a Softmax Classifier
  34. - Deep Learning Frameworks
  35. - TensorFlow

0 Comments

No reviews yet !!

Please login first

Course Tags
Deep Learning Course Deep Learning Free Course Neural Networks Course Machine Learning Course Machine Learning Free Course Top Free Course