Asset 20

Overview

This course will give you hands-on experience optimizing, deploying, and scaling a variety of production ML models. You'll learn how to build scalable, accurate, and production-ready models for structured data, image data, time-series, and natural language text, along with recommendation systems.

Duration: 40h

Asset 2
Objective

After completing the course, students will have the following knowledge:

  • Implement the various flavors of production ML systems—static, dynamic, and continuous training; static and dynamic inference; and batch and online processing.
  • Solve an ML problem by building an end-to-end pipeline, going from data exploration, preprocessing, feature engineering, model building, hyperparameter tuning, deployment, and serving.
  • Develop a range of image classification models from simple linear models to high-performing convolutional neural networks (CNNs) with batch normalization, augmentation, and transfer learning.
  • Forecast time-series values using CNNs, recurrent neural networks (RNNs), and LSTMs.
  • Apply ML to natural language text using CNNs, RNNs, LSTMs, reusable word embeddings, and encoder-decoder generative models.
  • Implement content-based, collaborative, hybrid, and neural recommendation models in TensorFlow.
Asset 4
Audience
  • Data Engineer hoặc lập trình viên quan tâm đến việc áp dụng Machine learning trong thực tế .
  • Cá nhân hứng thú với ứng dụng Machine learning đẻ giải quyết các vấn đề trong kinh doanh cho doanh nghiệp.
prerequisite
  • Knowledge of machine learning and TensorFlow to the level covered in Machine Learning on Google Cloud coursework.
  • Basic knowledge ML, TensorFlow
  • Experience coding in Python.
  • Knowledge of basic statistics.
  • Knowledge of SQL and cloud computing (helpful).
Asset 6

OUTLINE

01

Machine Learning on Google Cloud Platform

+
Effective ML.
+
Fully managed ML.

02

Explore the Data

+
Exploring the dataset.
+
BigQuery.
+
BigQuery and AI Platform Notebooks.

03

Creating the dataset

+
Creating a dataset.

04

Build the Model

+
Build the model.

05

Operationalize the model

+
Operationalizing the model.
+
Cloud AI Platform.
+
Train and deploy with Cloud AI Platform.
+
BigQuery ML.
+
Deploying and Predicting with Cloud AI Platform.

06

Architecting Production ML Systems

+
The Components of an ML System.
+
The Components of an ML System: Data Analysis and Validation.
+
The Components of an ML System: Data Transformation + Trainer.
+
The Components of an ML System: Tuner + Model Evaluation and Validation.
+
The Components of an ML System: Serving.
+
The Components of an ML System: Orchestration + Workflow.
+
The Components of an ML System: Integrated Frontend + Storage.
+
Training Design Decisions.
+
Serving Design Decisions.
+
Designing from Scratch.

07

Ingesting data for Cloud-based analytics and ML

+
Data On-Premise.
+
Large Datasets.
+
Data on Other Clouds.
+
Existing Databases.

08

Designing Adaptable ML systems

+
Adapting to Data.
+
Changing Distributions.
+
Right and Wrong Decisions.
+
System Failure.
+
Mitigating Training-Serving Skew through Design.
+
Debugging a Production Model.

09

Designing High-performance ML systems

+
Training.
+
Predictions.
+
Why distributed training?
+
Distributed training architectures.
+
Faster input pipelines.
+
Native TensorFlow Operations.
+
TensorFlow Records.
+
Parallel pipelines.
+
Data parallelism with All Reduce.
+
Parameter Server Approach.
+
Inference.L

10

Hybrid ML systemsL

+
Machine Learning on Hybrid Cloud.
+
KubeFlow.
+
Embedded Models.
+
TensorFlow Lite.
+
Optimizing for Mobile.

11

Welcome to Image Understanding with TensorFlow on GCP

+
Images as Visual Data.
+
Structured vs Unstructured Data.

12

Linear and DNN Models

+
Linear Models.
+
DNN Models Review.
+
Review: What is Dropout

13

Convolutional Neural Networks (CNNs)

+
Understanding Convolutions.
+
CNN Model Parameters.
+
Working with Pooling Layers.
+
Implementing CNNs with TensorFlow.

14

Dealing with Data Scarcity

+
The Data Scarcity Problem.
+
Data Augmentation.
+
Transfer Learning.
+
No Data, No Problem.

15

Going Deeper Faster

+
Batch Normalization.
+
Residual Networks.
+
Accelerators (CPU vs GPU, TPU).
+
TPU Estimator.
+
Neural Architecture Search.

16

Pre-built ML Models for Image Classification

+
Pre-built ML Models.
+
Cloud Vision API.
+
AutoML Vision.
+
AutoML Architecture.

17

Working with Sequences

+
Sequence data and models.
+
From sequences to inputs.
+
Modeling sequences with linear models.
+
Modeling sequences with DNNs.
+
Modeling sequences with CNNs.
+
The variable-length problem

18

Recurrent Neural Networks

+
Introducing Recurrent Neural Networks.
+
How RNNs represent the past.
+
The limits of what RNNs can represent.
+
The vanishing gradient problem.

19

Dealing with Longer Sequences

+
LSTMs and GRUs.
+
RNNs in TensorFlow.
+
Deep RNNs.
+
Improving our Loss Function.
+
Working with Real Data.

20

Text Classification

+
Working with Text.
+
Text Classification.
+
Selecting a Model.
+
Python vs Native TensorFlow.

21

Reusable Embeddings

+
Historical methods of making word embeddings.
+
Modern methods of making word embeddings.
+
Introducing TensorFlow Hub.
+
Using TensorFlow Hub within an estimator.

22

Recurrent Neural NetworksEncoder-Decoder Models

+
Introducing Encoder-Decoder Networks.
+
Attention Networks.
+
Training Encoder-Decoder Models with TensorFlow.
+
Introducing Tensor2Tensor.
+
AutoML Translation.
+
Dialogflow.

23

Module 23: Recommendation Systems Overview

+
Types of Recommendation Systems.
+
Content-Based or Collaborative.
+
Recommendation System Pitfalls.

24

Content-Based Recommendation Systems

+
Content-Based Recommendation Systems.
+
Similarity Measures.
+
Building a User Vector.
+
Making Recommendations Using a User Vector.
+
Making Recommendations for Many Users.
+
Using Neural Networks for Content-Based Recommendation Systems.

25

Collaborative Filtering Recommendation Systems

+
Types of User Feedback Data.
+
Embedding Users and Items.
+
Factorization Approaches.
+
The ALS Algorithm.
+
Preparing Input Data for ALS.
+
Creating Sparse Tensors For Efficient WALS Input.
+
Instantiating a WALS Estimator: From Input to Estimator.
+
Instantiating a WAL Estimator: Decoding TFRecords.
+
Instantiating a WALS Estimator: Recovering Keys.
+
Instantiating a WALS Estimator: Training and Prediction.
+
Issues with Collaborative Filtering.
+
Cold Starts.

26

Neural Networks for Recommendation Systems

+
Hybrid Recommendation System.
+
Context-Aware Recommendation Systems.
+
Context-Aware Algorithms.
+
Contextual Postfiltering.
+
Modeling Using Context-Aware Algorithms.

27

Building an End-to-End Recommendation System

+
Architecture Overview..
+
Cloud Composer Overview.
+
Cloud Composer: DAGs.
+
Cloud Composer: Operators for ML9.
+
Cloud Composer: Scheduling.
+
Cloud Composer: Triggering Workflows with Cloud Functions.
+
Cloud Composer: Monitoring and Logging.
Study with
Google Cloud expert

Asset 2@2x
Asset 32@2x
Asset 2

Student feedback

Cloud Ace Training
Bringing great experiences to students

Asset 4

Trần Tuấn Anh

IT

After completing the Associate Cloud Engineer course, I knew how to operate and deploy projects on Google Cloud and confidently took the Google Cloud certification exam.

Nguyễn Ngọc Minh Thy

Data Engineer

After completing the Professional Data Engineer course, I have enough knowledge and confidence to take the Google Cloud certification exam to prepare for my upcoming job.

Trương Quốc Thắng

Data Engineer

I learned how to choose tools and apply them to businesses to process data effectively through the Professional Data Engineer course.

Phạm Văn Hùng

IT

Khóa học rất chi tiết và đầy đủ, sau khi học xong khóa học Associate Cloud Engineer, mình rất muốn có cơ hội học thêm các khóa học khác để hiểu rõ hơn về Google Cloud

Dương Minh Phương

Engineer

Sau khi học xong khóa học Associate Cloud Engineer, mình đã hiểu rõ về Google Cloud và có thể đưa ra các giải pháp cho doanh nghiệp triển khai các dự án trên GCP
Asset 5

REGISTER NOW

TO BECOME " GOOGLE CLOUD EXPERT"

Asset 8@2x

    câu hỏi thường gặp

    Cloud Ace is a Google Cloud training unit, so it does not organize exams and provide Google Cloud certifications. Cloud Ace only supports providing certificates of course completion for students while waiting for the Google Cloud certification exam

    In addition, if you want to take the Google Cloud certification exam, Cloud Ace will guide you to register for the Online or Offline exam at the authorized Google Cloud test centers in Vietnam.

    Of course, during the learning process, you will constantly be solving quizzes, simulated mock tests that are similar to Google Cloud's actual exam questions. In addition, Cloud Ace also provides Dump questions that are constantly updated with question types, exam questions from Google Cloud to help you have the best preparation for the exam.

    Of course. You will be supported by Cloud Ace during the learning process and even at the end of the course. You can interact with the Trainer via Slack, email hoặc qua Group Google Cloud Plartform User HCM để được các Trainer hỗ trợ nhé.

    After completing the course, if you have any questions about the knowledge or have difficulties in implementing the project on Google Cloud, you can contact the Trainer for answers.

    The Google Cloud course is not only suitable for software engineers or system development engineers, but also suitable for data processing engineers such as Data Analytics, Data Engineer, Data Scientist.

    In addition, if you are a Marketer or working in the field of finance, banking, e-commerce, logistics .... constantly faced with big data to solve, then you can refer to the courses Big Data Machine Learning Fundamental or From Data to Insight on Google Cloud Platform courses to refer to simple data processing and create professional reports on Google Cloud.