Performance Tuning Deep Learning Models Master Class
A Step-by-Step Guide to Tuning Deep Learning Models
Ratings 4.23 / 5.00
What You Will 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.
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 Should Attend!
- 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.
