This 5-course specialization, "Advanced Machine Learning on Google Cloud," is designed to provide hands-on experience in optimizing, deploying, and scaling production ML models using Google Cloud Platform. It is the continuation of the "Machine Learning on GCP" course and covers advanced topics in machine learning.
The specialization starts with exploring production machine learning systems, moving on to computer vision fundamentals, natural language processing on Google Cloud, and ends with building recommendation systems. Throughout the courses, you will learn to build scalable, accurate, and production-ready models for structured data, image data, time-series, and natural language text. The topics introduced in earlier courses are referenced in later courses, making it essential to take the courses in the specified order for a comprehensive learning experience.
Certificate Available ✔Get Started / More Info
This specialization covers production machine learning systems, computer vision fundamentals, natural language processing on Google Cloud, and recommendation systems, providing hands-on experience in building scalable, accurate, and production-ready models for various data types.
Compare static versus dynamic training and inference.
Manage model dependencies.
Set up distributed training for fault tolerance, replication, and more.
Export models for portability.
Understand at a high-level the types of problems computer vision may solve.
Understand some of the key concepts and model architectures typically used using computer vision.
This course introduces the products and solutions to solve NLP problems on Google Cloud. Additionally, it explores the processes, techniques, and tools to develop an NLP project with neural networks by using Vertex AI and TensorFlow.
Devise a content-based recommendation engine.
Implement a collaborative filtering recommendation engine.
Build a hybrid recommendation engine with user and content embeddings.
Use reinforcement learning techniques for contextual bandits in the context of recommendations.
This course on AI Workflow focuses on data analysis and hypothesis testing, offering hands-on case studies and practical skills to deepen expertise in building and...
A hands-on 2-hour project training a deep learning model to classify scenery in images and use Grad-Cam for model explanation.
Machine Learning Models in Science provides a comprehensive overview of applying machine learning techniques to scientific problems, focusing on data preprocessing,...
Deploy deep learning models with TensorFlow Serving and Docker in this hands-on guided project. Train, deploy, and perform model inference within 90 seconds using...