# Building machine learning and deep learning models on Google Cloud platform : a comprehensive guide for beginners

9781484244692, 1484244699

Part 1. Getting started with Google Cloud platform. What is Cloud computing?

An overview of Google Cloud platform services

The Google Cloud SDK and Web CLI

Google Cloud Storage (GCS)

Google compute engine (GCE)

JupyterLab Notebooks

Google colaboratory

Part 2. Programming foundations for data science. What is data science?

Python

NumPy

Pandas

Matplotlib and Seaborn

Part 3. Introducing machine learning. What is machine learning?

Principles of learning

Batch vs. online learning

Optimization for machine learning: gradient descent

Learning algorithms

Part 4. Machine learning in practice. Introduction to Scikit-learn

Linear regression

Logistic regression

Regularization for linear models

Support vector machines

Ensemble methods

More supervised machine learning techniques with Scikit-learn

Clustering

Principal component analysis (PCA)

Part 5. Introducing deep learning. What is deep learning?

Neural network foundations

Training a neural network

Part 6. Deep learning in practice. TensorFlow 2.0 and Keras

The multilayer perceptron (MLP)

Other considerations for training the network

More on optimization techniques

Regularization for deep learning

Convolutional neural networks (CNN)

Recurrent neural networks (RNNs)

Autoencoders

Part 7. Advanced analytics/machine learning on Google platform. Google BigQuery

Google Cloud dataprep

Google Cloud dataflow

Google cloud machine learning engine (Cloud MLE)

Google AutoML: cloud vision

Google AutoML: cloud natural language processing

Model to predict the critical temperature of superconductors

Part 8. Productionalizing machine learning solutions on GCP. Containers and Google Kubernetes engine

Kubeflow and Kuberflow pipelines

Deploying an end-to-end machine learning solution on Kubeflow pipelines

Includes index

"For professionals by professionals."