Advanced Machine Learning with TensorFlow on Google Cloud
This five-day course teaches you how to build recommendation systems and scalable, accurate, and production-ready models for structured data, image data, time series, and natural language text.
Book this courseCourse Overview
5 day course
Certificate of Attendance
Private
Partner of the Year
Jellyfish is an award-winning Google Cloud Partner. Our trainers work with Google Cloud on a daily basis, so you'll benefit from the years of industry experience they’ll share with you.
The session focuses on teaching you to implement the various flavors of production ML systems and solve an ML problem by building an end-to-end pipeline; going from data exploration, preprocessing, feature engineering, model building, hyperparameter tuning, deployment, and serving.
You'll develop a range of image classification models from simple linear models to high-performing convolutional neural networks (CNNs) with batch normalization, augmentation, and transfer learning while forecasting time-series values using CNNs, recurrent neural networks (RNNs), and LSTMs.
By the end of the session, you'll also be able to implement content-based, collaborative, hybrid, and neural recommendation models in TensorFlow.
This Advanced Machine Learning with TensorFlow on Google Cloud course is available as a private session that can be delivered virtually or at a location of your choice in the UK.
What you'll learn
By the end of this course, you will be able to:
Implement the various flavors of production ML systems—static, dynamic, and continuous training; static and dynamic inference; and batch and online processing
Develop a range of image classification models from simple linear models to high-performing convolutional neural networks (CNNs) with batch normalization, augmentation, and transfer learning
Apply ML to natural language text using CNNs, RNNs, LSTMs, reusable word embeddings, and encoder-decoder generative models
Solve an ML problem by building an end-to-end pipeline, going from data exploration, preprocessing, feature engineering, model building, hyperparameter tuning, deployment, and serving
Forecast time-series values using CNNs, recurrent neural networks (RNNs), and LSTMs
Implement content-based, collaborative, hybrid, and neural recommendation models in TensorFlow
Course agenda
Module 1: End-to-End Machine Learning with TensorFlow on GCP
- In the first module, we recap what was covered in the Machine Learning with TensorFlow on Google Cloud Platform Specialization
Module 2: Production ML Systems
- Compare static vs. dynamic training and inference
- Manage model dependencies
- Set up distributed training for fault tolerance, replication, and more
- Export models for portability
Module 3: Image Classification Models
- Classify images using deep learning
- Implement convolutional neural networks
- Improve the model by augmentation, batch normalization, etc.
- Leverage transfer learning
Module 4: Sequence Models
- Predict future values of a time-series
- Classify free form text
- Address time-series and text problems with recurrent neural networks
- Choose between RNNs/LSTMs and simpler models
- Train and reuse word embeddings in text problems
Module 5: Recommendation Models
- Devise a content-based recommendation engine
- Implement a collaborative filtering recommendation engine
- Build a hybrid recommendation engine with user and content embeddings
Who it's for
This course is ideal for data engineers and programmers interested in learning how to apply machine learning in practice. It's also perfect for anyone interested in learning how to build and operationalize TensorFlow models.
Prerequisites
In order to get the most out of this session, you should already have knowledge of machine learning and TensorFlow equivalent to the level of Machine Learning on GCP specialization. Prior experience with programming languages such as SQL and Python, as well as cloud computing, will also be helpful.
BOOK THIS COURSE
Enquire for a team or large group
For private sessions call our sales team