What is Machine Learning, and what problems can it solve? This five-day course provides a deep understanding of Machine Learning, its implementation and the value it can provide.
5 day course
Supporting material
Google Cloud Partner of the Year
Private
Private
A private training session for your team. Groups can be of any size, at a location of your choice including our training centres.
On this course, you’ll learn how to write distributed machine learning models that scale in Tensorflow 2.x, perform feature engineering in BQML and Keras, evaluate loss curves and perform hyperparameter tuning, and train models at scale with Cloud AI Platform.
You will learn the key phases of converting a candidate use case to be driven by machine learning and the correct order in which these phases should be undertaken. You will also discover how ML optimization works and how various hyperparameters affect models during optimisation.
You will learn how to write models in TensorFlow using both pre-made estimators as well as custom ones and train them locally or in Cloud AI Platform, and why feature engineering is critical to success and how you can use various technologies including Cloud Dataflow and Cloud Dataprep.
You will also cover how to set up a supervised learning problem and find a good, generalisable solution using gradient descent and creating datasets.
Jellyfish has recently been named a Google Cloud Specialisation Partner of the Year. This title recognises our commitment to provide world-leading Cloud-based Training solutions that help our clients succeed. Our Machine Learning on Google Cloud Platform course is available as a private training session that can be held at a location of your choice or via Virtual Classroom.
Course overview
Who should attend:
This course is designed for Data Engineers and Programmers interested in learning how to apply machine learning in practice and anyone interested in learning how to leverage machine learning in their enterprise.
Walk away with the ability to:
Frame a business use case as a machine learning problem
Describe how to improve data quality
Perform exploratory data analysis
Build and train supervised learning models
Optimise and evaluate models using loss functions and performance metrics
Create repeatable and scalable training, evaluation, and test datasets
Implement machine learning models using Keras and TensorFlow 2.x
Understand the impact of gradient descent parameters on accuracy, training speed, sparsity, and generalisation
Represent and transform features
Train models at scale with AI platform
Prerequisites
Foundational skills in Google Cloud Platform and Data which can be derived from the course; Google Cloud Platform Fundamentals: Big Data & Machine Learning.
Course agenda
Module 1: How Google does Machine Learning
Develop a data strategy around machine learning
Examine use cases that are then reimagined through an ML lens
Recognise biases that ML can amplify
Leverage Google Cloud Platform tools and environment to do ML
Learn from Google's experience to avoid common pitfalls
Carry out data science tasks in online collaborative notebooks
Invoke pre-trained ML models from Cloud Datalab
Module 2: Launching into Machine Learning
Describe how to improve data quality
Perform exploratory data analysis
Build and train supervised learning models
Optimise and evaluate models using loss functions and performance metrics
Mitigate common problems that arise in machine learning
Create repeateable and scalable training, evaluation and test datasets
Module 3: Introduction to TensorFlow
Create TensorFlow 2.x and Keras machine learning models
Describe Tensorflow 2.x key components
Use the tf.data library to manipulate data and large datasets
Use the Keras Sequential and Functional APIs for simple and advanced model creation
Train, deploy, and productionalise ML models at scale with Cloud ML Platform
Module 4: Feature Engineering
Compare the key required aspects of a good feature
Combine and create new feature combinations through feature crosses
Perform feature engineering using BQML, Keras, and TensorFlow 2.x
Understand how to preprocess and explore features with Cloud Dataflow and Cloud Dataprep
Understand and apply how TensorFlow transforms features
Module 5: The Art and Science of ML
Optimise model performance with hyperparameter tuning
Experiment with neural networks and fine-tune performance