Udemy
    •  
    •  
    •  
    •  
    •  
    •  
    •  
    •  
Subscribe
Turn what you know into an opportunity and reach millions around the world.
Learn More
Your cart is empty.
Keep shopping
Performance Tuning Deep Learning Models Master Class
Rating: 4.4 out of 5(13 ratings)
236 students

Performance Tuning Deep Learning Models Master Class

A Step-by-Step Guide to Tuning Deep Learning Models
Created byMike West
Last updated 7/2021
English

What you'll learn

  • How to accelerate learning through better configured stochastic gradient descent batch size and loss functions.
  • How to combine the predictions from multiple models saved during a single training run.
  • How to accelerate learning through choosing better initial weights with greedy layer-wise pretraining and transfer learning.
  • How to reduce overfitting by updating the loss function using techniques such as weight regularization, weight constraints, and activation regularization.
  • How to combine the predictions from multiple models saved during a single training run with techniques such as horizontal ensembles and snapshot ensembles.

Course content

4 sections • 118 lectures • 5h 0m total length

  • Introduction1:51

    This lesson is the course overview.

  • Course Overview1:47

    Let's discuss what is in this course.

  • Is This Course Right for You?1:05

    Is this course right for you? 

  • Course Structure1:06

    Let's discuss the structure of the course.

  • Neural Network Defined2:54

    Let's define the components of an ANN.

  • Framework for Optimal Learning2:13

    There's a framework for optimal learning. Let's define it here.

  • Optimal Learning Techniques3:20

    There's a framework for optimal learning. Let's define it here.

  • Optimal Generalizations Techniques2:50

    There's a framework for optimal learning. Let's define it here.

  • Optimal Prediction Techniques3:26

    There's a framework for optimal learning. Let's define it here.

  • Framework Application2:54

    Let's discuss a framework for applying the learning techniques.

  • Diagnostic Learning Curves2:54

    In this lecture let's define learning curves.

  • The Fit of the Model2:54

    Let's learn about model fit in this lecture.

  • Unrepresentative Dataset1:47

    Let's learn about underrepresented datasets.

Requirements

  • A solid foundation in machine learning.
  • A solid foundation in deep learning.
  • A solid foundation in Python.
  • A solid foundation with the core machine learning libraries in Python.

Description

** Mike's courses are popular with many of our clients." Josh Gordon, Developer Advocate, Google **

Great course to see the impacts of model inputs, such as the quantity of epochs, batch size, hidden layers, and nodes, on the accuracy of the results. - Kevin

Best course on neural network tuning I've taken thus far. -Jazon Samillano

Very nice explanation. - Mohammad

Welcome to Performance Tuning Deep Learning Models Master Class.

Deep learning neural networks have become easy to create. However, tuning these models for maximum performance remains something of a challenge for most modelers. This course will teach you how to get results as a machine learning practitioner. This is a step-by-step course in getting the most out of deep learning models on your own predictive modeling projects.

My name is Mike West and I'm a machine learning engineer in the applied space. I've worked or consulted with over 50 companies and just finished a project with Microsoft. I've published over 50 courses and this is 53 on Udemy. If you're interested in learning what the real-world is really like then you're in good hands.

This course was designed around three main activities for getting better results with deep learning models: better or faster learning, better generalization to new data, and better predictions when using final models.

Who is this course for? 

This course is for developers, machine learning engineers and data scientists that want to enhance the performance of their deep learning models. This is an intermediate level to advanced level course. It's highly recommended the learner be proficient with Python, Keras and machine learning.

What are you going to Learn? 

  • An introduction to the problem of overfitting and a tour of regularization techniques

  • Accelerate learning through better configured stochastic gradient descent batch size, loss functions, learning rates, and to avoid exploding gradients via gradient clipping.

  • Learn to combat overfitting and an introduction of regularization techniques.

  • Reduce overfitting by updating the loss function using techniques such as weight regularization, weight constraints, and activation regularization.

  • Effectively apply dropout, the addition of noise, and early stopping.

  • Combine the predictions from multiple models and a tour of ensemble learning techniques.

  • Diagnose poor model training and problems such as premature convergence and accelerate the model training process.

  • Combine the predictions from multiple models saved during a single training run with techniques such as horizontal ensembles and snapshot ensembles.

  • Diagnose high variance in a final model and improve the average predictive skill.

This course is a hands on-guide. It is a playbook and a workbook intended for you to learn by doing and then apply your new understanding to your own deep learning Keras models. To get the most out of the course, I would recommend working through all the examples in each tutorial. If you watch this course like a movie you'll get little out of it. 

In the applied space machine learning is programming and programming is a hands on-sport.

Thank you for your interest in Performance Tuning Deep Learning Models Master Class.

Let's get started!


Who this course is for:

  • You're passonate about deep learning with a solid foundation in this space and want to learn how to squeeze the best performance out of your deep learning models.

Report abuse