Google Cloud'un Yetkili Eğitim ve Sertifikasyonlarıyla Bulutta İlerleyin!

Course Details

• • Online Training

• • Duration : 1 day

• Course Overview

This one-day instructor-led course introduces participants to the big data capabilities of Google Cloud Platform. Through a combination of presentations, demos, and hands-on labs, participants get an overview of the Google Cloud platform and a detailed view of the data processing and machine learning capabilities. This course showcases the ease, flexibility, and power of big data solutions on Google Cloud Platform.

Who should attend

This Google Cloud Platform training class is intended for the following:

·     Individuals planning to deploy applications and create application environments on Google Cloud Platform

·       Developers, systems operations professionals and solution architects getting started with Google Cloud Platform

·       Executives and business decision makers evaluating the potential of Google Cloud Platform to address their business need

Prerequisites 

Familiarity with application development, systems operations,Linux operating systems, and data analytics/machine learning is helpful in understanding the technologies covered.

Course Objectives

This course teaches participants the following skills:

·       Identify the purpose and value of Google Cloud Platform products and services

·       Interact with Google Cloud Platform services

·       Describe ways in which customers have used Google Cloud Platform

·       Choose among and use application deployment environments on Google Cloud Platform: Google App Engine, Google Container
Engine, and Google Compute Engine

·       Choose among and use Google Cloud Platform storage options: Google Cloud Storage, Google Cloud SQL, Google Cloud Bigtable,
and Google Cloud Datastore

·       Make basic use of BigQuery, Google’s managed data warehouse for analytics

Course Content

 Module 1: Introducing Google Cloud Platform

·       Explain the advantages of Google Cloud Platform

·       Define the components of Google’s network infrastructure, including: Points of presence, data centers, regions, and zones

·       Understand the difference between Infrastructure-as-a-Service (IaaS) and Platform-as-a-Service (PaaS)

·       Lab: Sign Up for the Free Trial and Create a Project

Module 2:
Getting Started with Google Cloud Platform

·       Identify the purpose of projects on Google Cloud Platform

·       Understand the purpose of and use cases for Identity and Access Management

·       List the methods of interacting with Google Cloud Platform

·       Lab: Getting Started with Google Cloud Platform

Module 3: Google App Engine and Google Cloud Datastore

·       Understand the purpose of and use cases for Google App Engine and Google Cloud Datastore

·       Contrast the App Engine Standard environment with the App Engine Flexible environment

·       Understand the purpose of and use cases for Google Cloud Endpoints

·       Lab: Deploying Applications Using App Engine and Cloud Datastore

Module 4: Google Cloud Platform Storage Options

·       Understand the purpose of and use cases for: Google Cloud Storage, Google Cloud SQL, and Google Cloud Bigtable

·       Learn how to choose between the various storage options on Google Cloud Platform

·       Lab: Integrating Applications with Google Cloud Storage

Module 5: Google Container Engine

·       Define the concept of a container and identify uses for containers

·       Identify the purpose of and use cases for Google Container Engine and Kubernetes

·       Deploying Applications Using Google Container Engine

Module 6: Google Compute Engine and Networking

·       Identify the purpose of and use cases for Google Compute Engine

·       Understand the various Google Cloud Platform networking and operational tools and services

·       Lab: Deploying Applications Using Google Compute Engine

Module 7: Big Data and Machine Learning

·       Understand the purpose of and use cases for the products and services in the Google Cloud big data and machine learning
platforms

·       Lab: Getting Started with BigQuery

 

Who should attend

This class is intended for experienced developers who are responsible for managing big data transformations including:

·        Extracting, Loading, Transforming, cleaning, and validating data

·        Designing pipelines and architectures for data processing

·        Creating and maintaining machine learning and statistical models

·        Querying datasets, visualizing query results and creating reports

Prerequisites

To get the most of out of this course, participants should have:

·        Completed Google Cloud Fundamentals: Big Data and Machine Learning (GCF-BDM) course OR have equivalent experience

·        Basic proficiency with common query language such as SQL

·        Experience with data modeling, extract, transform, load activities Developing applications using a common programming language such Python

·        Familiarity with Machine Learning and/or statistics

Course Objectives

This course teaches participants the following skills:

·        Design and build data processing systems on Google Cloud Platform

·        Process batch and streaming data by implementing autoscaling data pipelines on Cloud Dataflow

·        Derive business insights from extremely large datasets using Google BigQuery

·        Train, evaluate and predict using machine learning models using Tensorflow and Cloud ML

·        Leverage unstructured data using Spark and ML APIs on Cloud Dataproc

·        Enable instant insights from streaming data

Course Content

Module 1: Google Cloud Dataproc Overview

·        Creating and managing clusters.

·        Leveraging custom machine types and preemptible worker nodes.

·        Scaling and deleting Clusters.

·        Lab: Creating Hadoop Clusters with Google Cloud Dataproc.

Module 2: Running Dataproc Jobs

·        Running Pig and Hive jobs.

·        Separation of storage and compute.

·        Lab: Running Hadoop and Spark Jobs with Dataproc.

·        Lab: Submit and monitor jobs.

Module 3: Integrating Dataproc with Google Cloud Platform

·        Customize cluster with initialization actions.

·        BigQuery Support.

·        Lab: Leveraging Google Cloud Platform Services.

Module 4: Making Sense of Unstructured Data with Google’s Machine Learning APIs

·        Google’s Machine Learning APIs.

·        Common ML Use Cases.

·        Invoking ML APIs.

·        Lab: Adding Machine Learning Capabilities to Big Data Analysis.

Module 5: Serverless data analysis with BigQuery

·        What is BigQuery.

·        Queries and Functions.

·        Lab: Writing queries in BigQuery.

·        Loading data into BigQuery.

·        Exporting data from BigQuery.

·        Lab: Loading and exporting data.

·        Nested and repeated fields.

·        Querying multiple tables.

·        Lab: Complex queries.

·        Performance and pricing.

Module 6: Serverless, autoscaling data pipelines with Dataflow

·        The Beam programming model.

·        Data pipelines in Beam Python.

·        Data pipelines in Beam Java.

·        Lab: Writing a Dataflow pipeline.

·        Scalable Big Data processing using Beam.

·        Lab: MapReduce in Dataflow.

·        Incorporating additional data.

·        Lab: Side inputs.

·        Handling stream data.

·        GCP Reference architecture.

Module 7: Getting started with Machine Learning

·        What is machine learning (ML).

·        Effective ML: concepts, types.

·        ML datasets: generalization.

·        Lab: Explore and create ML datasets.

Module 8: Building ML models with Tensorflow

·        Getting started with TensorFlow.

·        Lab: Using tf.learn.

·        TensorFlow graphs and loops + lab.

·        Lab: Using low-level TensorFlow + early stopping.

·        Monitoring ML training.

·        Lab: Charts and graphs of TensorFlow training.

Module 9: Scaling ML models with CloudML

·        Why Cloud ML?

·        Packaging up a TensorFlow model.

·        End-to-end training.

·        Lab: Run a ML model locally and on cloud.

Module 10: Feature Engineering

·        Creating good features.

·        Transforming inputs.

·        Synthetic features.

·        Preprocessing with Cloud ML.

·        Lab: Feature engineering.

Module 11: Architecture of streaming analytics pipelines

·        Stream data processing: Challenges.

·        Handling variable data volumes.

·        Dealing with unordered/late data.

·        Lab: Designing streaming pipeline.

Module 12: Ingesting Variable Volumes

·        What is Cloud Pub/Sub?

·        How it works: Topics and Subscriptions.

·        Lab: Simulator.

Module 13: Implementing streaming pipelines

·        Challenges in stream processing.

·        Handle late data: watermarks, triggers, accumulation.

·        Lab: Stream data processing pipeline for live traffic data.

Module 14: Streaming analytics and dashboards

·        Streaming analytics: from data to decisions.

·        Querying streaming data with BigQuery.

·        What is Google Data Studio?

·        Lab: build a real-time dashboard to visualize processed data.

Module 15: High throughput and low-latency with Bigtable

·        What is Cloud Spanner?

·        Designing Bigtable schema.

·        Ingesting into Bigtable.

·        Lab: streaming into Bigtable.

Who should attend

This class is intended for the following:

·        Data Analysts, Business Analysts, Business Intelligence professionals

·        Cloud Data Engineers who will be partnering with Data Analysts to build scalable data solutions on Google Cloud Platform

Prerequisites

To get the most out of this course, participants should have:

·        Basic proficiency with ANSI SQL

Course Objectives

This course teaches participants the following skills:

·        Derive insights from data using the analysis and visualization tools on Google Cloud Platform

·        Load, clean, and transform data at scale with Google Cloud Dataprep

·        Explore and Visualize data using Google Data Studio

·        Troubleshoot, optimize, and write high performance queries

·        Practice with pre-built ML APIs for image and text understanding

·        Train classification and forecasting ML models using SQL with BQML

Course Content

·        Module 1: Introduction to Data on the Google Cloud Platform

·        Module 2: Big Data Tools Overview

·        Module 3: Exploring your Data with SQL

·        Module 4: Google BigQuery Pricing

·        Module 5: Cleaning and Transforming your Data

·        Module 6: Storing and Exporting Data

·        Module 7: Ingesting New Datasets into Google BigQuery

·        Module 8: Data Visualization

·        Module 9: Joining and Merging Datasets

·        Module 10: Advanced Functions and Clauses

·        Module 11: Schema Design and Nested Data Structures

·        Module 12: More Visualization with Google Data Studio

·        Module 13: Optimizing for Performance

·        Module 14: Data Access

·        Module 15: Notebooks in the Cloud

·        Module 16: How Google does Machine Learning

Who should attend

·        Data Engineers and programmers interested in learning how to apply machine learning in practice.

·        Anyone interested in learning how to build and operationalize TensorFlow models.

Prerequisites

To get the most out of this course, participants should have:

·        Experience coding in Python

·        Knowledge of basic statistics

·        Knowledge of SQL and cloud computing (helpful)

Course Objectives

Learn how to write distributed machine learning models that scale in Tensorflow, scale out the training of those models, and offer high-performance predictions. Convert raw data to features in a way that allows ML to learn important characteristics from the data and bring human insight to bear on the problem. Finally, learn how to incorporate the right mix of parameters that yields accurate, generalized models and knowledge of the theory to solve specific types of ML problems. You will experiment with end-to-end ML, starting from building an ML-focused strategy and progressing into model training, optimization, and productionalization with hands-on labs using Google Cloud Platform

This course teaches participants the following skills:

·        Frame a business use case as a machine learning problem

·        Create machine learning datasets that are capable of achieving generalization

·        Implement machine learning models using TensorFlow

·        Understand the impact of gradient descent parameters on accuracy, training speed, sparsity, and generalization

·        Build and operationalize distributed TensorFlow models

·        Represent and transform features

Course Content

1: How Google Does Machine Learning

What is machine learning, and what kinds of problems can it solve? Google thinks about machine learning slightly differently: it’s about logic, rather than just data. We talk about why such a framing is useful when thinking about building a pipeline of machine learning models. Then we discuss the five phases of converting a candidate use case to be driven by machine learning, and consider why it is important not to skip the phases. We end with a recognition of the biases that machine learning can amplify and how to recognize them.

·        Develop a data strategy around machine learning

·        Examine use cases that are then reimagined through an ML lens

·        Recognize biases that ML can amplify

·        Leverage Google Cloud Platform tools and environment to do ML

·        Learn from Google’s experience to avoid common pitfalls

·        Carry out data science tasks in online collaborative notebooks

·        Invoke pre-trained ML models from Cloud Datalab

2: Launching into Machine Learning

Starting from a history of machine learning, we discuss why neural networks today perform so well in a variety of problems. We then discuss how to set up a supervised learning problem and find a good solution using gradient descent. This involves creating datasets that permit generalization; we talk about methods of doing so in a repeatable way that supports experimentation.

·        Identify why deep learning is currently popular

·        Optimize and evaluate models using loss functions and performance metrics

·        Mitigate common problems that arise in machine learning

·        Create repeatable and scalable training, evaluation, and test datasets

3: Intro to TensorFlow

We introduce low-level TensorFlow and work our way through the necessary concepts and APIs so as to be able to write distributed machine learning models. Given a TensorFlow model, we explain how to scale out the training of that model and offer high-performance predictions using Cloud Machine Learning Engine.

·        Create machine learning models in TensorFlow

·        Use the TensorFlow libraries to solve numerical problems

·        Troubleshoot and debug common TensorFlow code pitfalls

·        Use tf_estimator to create, train, and evaluate an ML model

·        Train, deploy, and productionalize ML models at scale with Cloud ML Engine

4: Feature Engineering

A key component of building effective machine learning models is to convert raw data to features in a way that allows ML to learn important characteristics from the data. We discuss how to represent features and code this up in TensorFlow. Human insight can be brought to bear in machine learning problems through the use of custom feature transformations. In this module, we talk about common types of transformations and how to implement them at scale.

·        Turn raw data into feature vectors

·        Preprocess and create new feature pipelines with Cloud Dataflow

·        Create and implement feature crosses and assess their impact

·        Write TensorFlow Transform code for feature engineering

5: The Art and Science of ML

Machine Learning is both an art that involves knowledge of the right mix of parameters that yields accurate, generalized models and a science that involves knowledge of the theory to solve specific types of ML problems. We discuss regularization, dealing with sparsity, multi-class neural networks, reusable embeddings, and many other essential concepts and principles.

·        Optimize model performance with hyperparameter tuning

·        Experiment with neural networks and fine-tune performance

·        Enhance ML model features with embedding layers

·        Create reusable custom model code with the Custom Estimator

Who should attend

This course is intended for the following participants:

·        Cloud professionals interested in taking the Data Engineer certification exam.

·        Data engineering professionals interested in taking the Data Engineer certification exam.

Prerequisites

To get the most out of this course, participants should:

·        Familiarity with Google Cloud Platform to the level of the Data Engineering on Google Cloud Platform course (suggested, not required)

Course Objectives

This course teaches participants the following skills:

·        Position the Professional Data Engineer Certification

·        Provide information, tips, and advice on taking the exam

·        Review the sample case studies

·        Review each section of the exam covering highest-level concepts sufficient to build confidence in what is known by the candidate and indicate skill gaps/areas of study if not known by the candidate

·        Connect candidates to appropriate target learning

Course Content

This full-day instructor-led course helps prospective candidates structure their preparation for the Professional Data Engineer exam. The session will cover the structure and format of the examination, as well as its relationship to other Google Cloud certifications. Through lectures, quizzes, and discussions, candidates will familiarize themselves with the domain covered by the examination, so as to help them devise a preparation strategy. Rehearses useful skills including exam question reasoning and case comprehension. Tips. Review of topics from the Data Engineering curriculum.

Who should attend

·        Conversational Architects

·        Contact center virtual agent and application developers

·        Business managers

Prerequisites

·        Completed Google Cloud Product Fundamentals or have equivalent experience.

·        Desirable but not required: Knowledge of a programming language such as Python or JavaScript.

Course Objectives

·        Define what Google Contact Center AI is.

·        Explain how Dialogflow can be used in contact center applications.

·        Describe how natural language understanding (NLU) is used to enable Dialogflow conversations.

·        Implement a chat virtual agent.

·        Implement a voice virtual agent.

·        Describe options for storing parameters and fulfilling user requests.

·        Deploy a virtual agent to production.

·        Identify best practices for design and deployment of virtual agents.

·        Identify key aspects, such as security and compliance in the context of contact centers.

Course Content

Module 1 – Overview of Contact Center AI

·        Define what Contact Center AI (CCAI) is and what it can do for contact centers.

·        Identify each component of the CCAI Architecture: Speech Recognition, Dialogflow, Speech Synthesis, Agent Assist, and Insights.

·        Describe the role each component plays in a CCAI solution.

·        Quiz – Contact Center AI fundamentals

Module 2 – Conversational Experiences

·        List the basic principles of a conversational experience.

·        Explain the role of conversation virtual agents in a conversation experience.

·        Articulate how STT (speech to text) can determine the quality of a conversation experience.

·        Demonstrate and test how speech adaptation can improve the speech recognition accuracy of the agent.

·        Recognize the different NLU (natural language understanding) and NLP (natural language processing) techniques and the role they play in conversation experiences.

·        Explain the different elements of a conversation (intents, entities, etc.).

·        Use sentiment analysis to help with the achievement of a higher-quality conversation experience.

·        Improve conversation experiences by choosing different TTS voices (Wavenet vs. Standard).

·        Modify the speed and pitch of a synthesized voice.

·        Describe how to leverage SSML to modify the tone and emphasis of a synthesized passage.

·        Quiz – Conversational Experiences

Module 3 – Fundamentals of Building Conversations with Dialogflow

·        Identify user roles and their journeys.

·        Write personas for virtual agents and users.

·        Model user-agent interactions.

·        List the basic elements of the Dialogflow user interface.

·        Build a virtual agent to handle identified user journeys.

·        Train the NLU model through the Dialogflow console.

·        Define and test intents for a basic agent.

·        Train the agent to handle expected and unexpected user scenarios.

·        Recognize the different types of entities and when to use them.

·        Create entities.

·        Define and test entities on a basic agent.

·        Implement slot filling using the Dialogflow UI.

·        Describe when Mega Agent might be used.

·        Demonstrate how to add access to a knowledge base for your virtual agent to answer customer questions straight from a company FAQ

·        Quiz – DF Fundamentals: Intents and Entities

·        Lab – DF Fundamentals: Build a Basic Virtual Chat Agent That Uses Intents and Entities

·        Lab – Creating a Knowledge Base Connector

Module 4 – Maintaining Context in a Conversation

·        Create follow-up intents.

·        Recognize the scenarios in which context should be used.

·        Identify the possible statuses of a context (active versus inactive context).

·        Implement dialogs using input and output contexts.

·        Quiz – Context

·        Lab – Context: Add to your virtual chat agent using input and output contexts to map more intricate conversational scenarios

Module 5 – Moving from Chat agent to Voice agent

·        Describe two ways that the media type changes the conversation

·        Configure the telephony gateway for testing

·        Test a basic voice agent

·        Modify the voice of the agent

·        Show how the different media types can have different responses

·        Consider the modifications needed when moving to production

·        Be aware of the telephony integration for voice in a production environment

·        Quiz – Chat versus Voice agent.

·        Lab – Voice Agent: Add voice to your virtual agent.

Module 6 – Taking Actions with Fulfillment

·        Define the role of fulfillment with respect to Contact Center AI.

·        Characterize what needs to be collected in order to fulfill a request.

·        Identify existing backend systems on the customer infrastructure.

·        Use Firestore to store mappings returned from functions.

·        Appreciate that the interaction with customers’ data storage will vary based on their data warehouses.

·        Implement fulfillment using Cloud Functions.

·        Implement fulfillment using Python on AppEngine.

·        Describe the use of Apigee for application deployment.

·        Quiz – Fulfillment

·        Lab – Fulfillment: Using cloud functions to persist and query data from a database.

Module 7 – Testing and Logging

·        Debug a virtual agent by testing intent accuracy.

·        Debug fulfillment by testing the different functions and integrations with backend systems through API calls.

·        Implement version control to achieve more scalable collaboration.

·        Log conversations using Cloud Logging.

·        Recognize ways that audits can be performed.

·        Quiz – Testing and Logging

·        Lab – Logging: Use Cloud Logging to debug your virtual agent code

Module 8 – Intelligent Assistance for Live Agents

·        Recognize use cases where Agent Assist adds value.

·        Identify, collect, and curate documents for knowledge base construction.

·        Set up knowledge bases.

·        Describe how FAQ Assist works.

·        Describe how Document Assist works.

·        Describe how the Agent Assist UI works.

·        Describe how Dialogflow Assist works.

·        Describe how Smart Reply works.

·        Describe how real-time entity extraction works.

·        Quiz – Helping agents enhance the customer experience with knowledge bases, smart replies, and document assistance

Module 9 – Drawing Insights from Recordings

·        Analyze audio recordings using the Speech Analytics Framework (SAF).

·        Lab: Use the Speech Analytics Framework to draw insights from contact center logs

Module 10 – Integrating a Virtual Agent with Third Parties

·        Use the Dialogflow API to programmatically create and modify the virtual agent.

·        Describe connectivity protocols: gRPC, REST, SIP endpoints, and phone numbers over PSTN.

·        Replace existing head intent detection on IVRs with Dialogflow intents.

·        Describe virtual agent integration with Google Assistant.

·        Describe virtual agent integration with messaging platforms.

·        Describe virtual agent integration with CRM platforms (such as Salesforce and Zendesk).

·        Describe virtual agent integration with enterprise communication platforms (such as Genesys, Avaya, Cisco, and Twilio).

·        Explain the ability that telephony providers have of identifying the caller and how that can modify the agent design.

·        Incorporate IVR features in the virtual agent.

·        Quiz – IVR Features

·        Quiz – Common platforms of integration

·        Quiz – Contact Center AI integration points

Module 11 – Environment Management

·        Create Draft and Published versions of your virtual agent.

·        Create environments where your virtual agent will be published.

·        Load a saved version of your virtual agent to Draft.

·        Change which version is loaded to an environment.

·        Quiz – Environment Management

·        Lab – Use the Dialogflow Environment Management feature to deploy a draft version of your virtual agent to a new environment

Module 12 – Methods of Compliance with Federal Regulations

·        Describe two ways that security can be implemented on a Contact Center AI integration.

·        Identify current compliance measures and scenarios where compliance is needed.

·        Quiz – Audit

Module 13 – Best Practices for Virtual Agents

·        Convert pattern matching and decision trees to smart conversational design.

·        Recognize situations that require escalation to a human agent.

·        Support multiple platforms, devices, languages, and dialects.

·        Use Diagflow’s built-in analytics to assess the health of the virtual agent.

·        Perform agent validation through the Dialogflow UI.

·        Monitor conversations and Agent Assist.

·        Institute a DevOps and version control framework for agent development and maintenance.

·        Consider enabling spell correction to increase the virtual agent’s accuracy.

·        Quiz – Best practices

Module 14 – Google Implementation Methodology (Partners only)

·        Identify the stages of the Google Implementation Methodology.

·        Enumerate the key activities of each implementation stage.

·        Acknowledge how to use Google’s support assets for Partners.

Module 15 – Course Summary

·        Recapitulate what was covered during this course.