Formation Machine Learning on Google Cloud (MLGC)

Module 01 - How Google Does Machine Learning:

Explore the Vertex AI Platform for building AutoML models seamlessly. Learn best practices, develop a machine learning data strategy, and leverage Google Cloud Platform tools. Gain insights from Google's experience to navigate common pitfalls and execute data science tasks in collaborative online notebooks.

Module 02 - Launching into Machine Learning:

Delve into Vertex AI AutoML, BigQuery ML, and data quality improvement. Conduct exploratory data analysis, build and train supervised learning models, and optimize them using loss functions and metrics. Address common machine learning problems and establish repeatable, scalable training, evaluation, and test datasets.

Module 03 - TensorFlow on Google Cloud:

Create TensorFlow and Keras machine learning models, understand key components, and use tf.data for data manipulation. Build models using tf.keras preprocessing layers, Sequential and Functional APIs, and explore model subclassing. Utilize tf.keras.preprocessing for image, text, and sequence data. Learn to train, deploy, and scale ML models with Cloud AI Platform.

Module 04 - Feature Engineering:

Understand Vertex AI Feature Store, key aspects of good features, and create feature combinations. Perform feature engineering with BigQuery ML, Keras, and TensorFlow. Explore feature preprocessing with Dataflow, Dataprep by Trifacta, and apply TensorFlow transformations.

Module 05 - Machine Learning in the Enterprise:

Grasp tools for data management and governance, delve into data preprocessing using Dataflow, Dataprep, and SQL. Differentiate AutoML, BigQuery ML, and custom training frameworks. Explore hyperparameter tuning with Vertex Vizier, understand prediction, model monitoring, and the benefits of Vertex AI Pipelines for enterprise-level machine learning.