Paths
Advanced Machine Learning on Google Cloud Platform
This path focuses on advanced machine learning topics using Google Cloud Platform where you will get hands-on experience optimizing, deploying, and scaling production ML models of... Read more
What you will learn:
This path teaches the following skills
- Know the best practices for machine learning systems
- Improve machine learning models’ accuracy with augmentation, feature extraction, and fine-tuning hyperparameters
- Build image recognition models
- Predict future values of a time-series
- Classify free form text
- Address time-series and text problems with recurrent neural networks
- Devise a content-based recommendation engine
- Implement a collaborative filtering recommendation engine
- Build a hybrid recommendation engine with user and content embeddings
Pre-requisites
Participants should have already completed the “Machine Learning on GCP” learning path. Participants should be familiar with SQL, TensorFlow, and Python.
Beginner
In order to recap the Machine Learning with TensorFlow on Google Cloud Platform learning path, this section starts with a workshop in which you will do End-to-End Machine Learning with TensorFlow on Google Cloud Platform. Then you learn about the components and best practices of a high-performing ML system in production environments.
End-to-End Machine Learning with TensorFlow on GCP
3h 16m
Description
One of the best ways to review something is to work with the concepts and technologies that you have learned. So, this course is set up as a workshop and in this workshop, you will do End-to-End Machine Learning with TensorFlow on Google Cloud Platform. It involves building an end-to-end model from data exploration all the way to deploying an ML model and getting predictions from it.
Table of contents
- Welcome to the Course
- Machine Learning (ML) on Google Cloud Platform (GCP)
- Explore the Data
- Create the dataset
- Build the Model
- Operationalize the model
- Summary
Production Machine Learning Systems
3h 18m
Description
In this course, we will dive into the components and best practices of a high-performing ML system in production environments.
Table of contents
- Welcome to the course
- Architecting Production ML Systems
- Ingesting data for Cloud-based analytics and ML
- Designing Adaptable ML systems
- Designing High-performance ML systems
- Hybrid ML systems
- Course Summary
Intermediate
This section offers a look at different strategies for building an image classifier using convolutional neural networks. You will improve a machine learning model's accuracy with augmentation, feature extraction, and fine-tuning hyperparameters while trying to avoid overfitting the data. You will also look at practical issues that arise, for example, when you don’t have enough data; as well as how to incorporate the latest research findings into our models. You will get hands-on practice building and optimizing your own image classification models on a variety of public datasets. The section next introduces sequence models and their applications, including an overview of sequence model architectures and how to handle inputs of variable length. You will get hands-on practice building and optimizing your own text classification and sequence models on a variety of public datasets.
Image Understanding with TensorFlow on GCP
4h 20m
Description
In this course, we will take a look at different strategies for building an image classifier using convolutional neural networks. We'll improve the model's accuracy with augmentation, feature extraction, and fine-tuning hyperparameters while trying to avoid overfitting our data. We will also look at practical issues that arise, for example, when you don’t have enough data and how to incorporate the latest research findings into our models. You will get hands-on practice building and optimizing your own image classification models on a variety of public datasets in the labs we’ll work on together.
Table of contents
- Welcome to Image Understanding with TensorFlow on GCP
- Linear and DNN Models
- Convolutional Neural Networks (CNNs)
- Dealing with Data Scarcity
- Going Deeper Faster
- Pre-built ML Models for Image Classification
- Summary
Sequence Models for Time Series and Natural Language Processing
4h 32m
Description
In this course, we’ll learn how to make predictions on sequences of data. We’ll cover common business use cases like- 1.time-series prediction and how to deal with more recent data points getting more relevance 2.translating entire sentences (aka sequences of words) into other languages You will get hands-on practice building and optimizing your own text classification and sequence models on a variety of public datasets in the labs we’ll work on together.
Table of contents
- Working with Sequences
- Recurrent Neural Networks
- Dealing with Longer Sequences
- Text Classification
- Reusable Embeddings
- Encoder-Decoder Models
- Summary
Advanced
In this section, you'll apply your knowledge of classification models and embeddings to build a ML pipeline that functions as a recommendation engine.
Recommendation Systems with TensorFlow on GCP
6h 46m
Description
In this course, you'll apply your knowledge of classification models and embeddings to build a ML pipeline that functions as a recommendation engine.
Table of contents
- Recommendation Systems Overview
- Content-Based Recommendation Systems
- COLLABORATIVE FILTERING RECOMMENDATION SYSTEMS
- Neural Networks for Recommendation Systems
- Building an End-to-End Recommendation System
- Summary