- Duration: 2 days
- Skill-level: Foundation-level AI as a Service for Intermediate skilled team members. This is not a basic class.
- Targeted Audience: This course is geared for software developers who wants to build and implement serverless AI applications, without bogging you down with a lot of theory. Instead, you’ll find easy-to-digest instruction and two complete hands-on serverless AI builds in this must-have guide!
- Hands-on Learning: This course is approximately 50% hands-on lab to 50% lecture ratio, combining engaging lecture, demos, group activities and discussions with machine-based student labs and exercises. Student machines are required.
- Delivery Format: This course is available for onsite private classroom presentation, or remote instructor led delivery, or CBT/WBT (by request).
- Customizable: This course may be tailored to target your specific training skills objectives, tools of choice and learning goals.
AI as a Service teaches you how to quickly harness the power of serverless computing and cloud-based AI services. After an introduction to the basics of this dynamic technology duo, you’ll dive right into your first hands-on serverless AI project: a system that can recognize images from arbitrary web pages. In it you’ll explore tools like Amazon Recognition for image analysis and techniques like deployment of cloud infrastructure, a crawler service, and a simple API. When you’ve mastered the concepts and skills in that fun and interesting project, you’ll move on to building a serverless to-do application that employs cloud-based AI tools like AWS Transcribe and Polly for speech-to-text and text-to-speech functionality and Lex for creating interactive chatbots. When you’re finished with this essential course, you’ll have the skills to quickly build end-to-end serverless AI systems, making you indispensable as this rapidly emerging paradigm becomes the business standard!
Working in a hands-on learning environment, led by our AI expert instructor, students will learn about and explore:
- you’ll explore tools like Amazon Recognition for image analysis and techniques like deployment of cloud infrastructure, a crawler service, and a simple API.
- you’ll move on to building a serverless to-do application that employs cloud-based AI tools like AWS Transcribe and Polly for speech-to-text and text-to-speech functionality and Lex for creating interactive chatbots
Topics Covered: This is a high-level list of topics covered in this course. Please see the detailed Agenda below
- Cloud AI from development to production
- Applying cloud AI services to your existing platform
- Understanding orchestration patterns for cloud AI systems
- How to architect and build scalable, resilient data pipelines
- Debugging and troubleshooting cloud AI services
- Getting started immediately with serverless templates
Audience & Pre-Requisites
This course is geared for those who wants to build and implement serverless AI applications, without bogging you down with a lot of theory.
Pre-Requisites: Students should have
- For software developers with intermediate skills in at least one programming language and a basic understanding of IP networking and HTTP protocol.
- Familiarity with cloud-based version control systems such as GitHub would be helpful.
- No prior knowledge of AI is necessary.
- Good foundational mathematics or logic skills
- Basic Linux skills, including familiarity with command-line options such as ls, cd, cp, and su
Course Agenda / Topics
- A Tale of Two Technologies
- Cloud Landscape
- What is Serverless?
- The Need for Speed
- What is AI?
- The Democratization of Compute Power and Artificial Intelligence
- Canonical Serverless AI architecture
- Realization on Amazon Web Services
- Building a Serverless Image Recognition System
- Our First System
- Getting ready
- Implementing the Asynchronous services
- Implementing the Synchronous Services
- Running the System
- Removing the System
- Build and Secure a Web Application the Serverless Way
- The To Do List
- Getting ready
- Step 1 The Basic Application
- Step 2 Securing with Cognito
- Adding AI Interfaces to a Web Application
- Step 3 Adding a Speech to Text Interface
- Step 4 Adding Text to Speech
- Step 5 Adding a Conversational Chat Bot Interface
- Removing the System
- Applying AI to Existing Platforms
- Integration Patterns for Serverless AI
- Improving identity verification with Textract
- An AI Enabled Data Processing Pipeline with Kinesis
- Deploying the API
- On the fly translation with Translate
- Testing the Pipeline
- Sentiment Analysis with Comprehend
- Training a Custom Document Classifier
- Using the Custom Classifier
- Testing the Pipeline End to End
- Removing the Pipeline
- Benefits of Automation
- Gathering Data at Scale for Real-World AI
- Scenario: Finding Events and Speakers
- Gathering Data from the Web
- Introduction to Web Crawling
- Implementing an Item Store
- Creating a Frontier to Store and Manage URLs
- Building the Fetcher to Retrieve and Parse Web Pages
- Determining the Crawl Space in a Strategy Service
- Orchestrating the Crawler with a Scheduler
- Extracting Value from Large Data Sets with AI
- Using AI to Extract Significant Information from Web Pages
- Understanding Comprehend Entity Recognition APIs
- Preparing Data for Information Extraction
- Managing Throughput with Text Batches
- Asynchronous Named Entity Abstraction
- Checking Entity Recognition Progress
- Deploying and Testing Batch Entity Recognition
- Persisting Recognition Results
- Tieing it all Together
- Wrapping Up
Student Materials: Each student will receive a Student Guide with course notes, code samples, software tutorials, diagrams and related reference materials and links (as applicable). Our courses also include step by step hands-on lab instructions and and solutions, clearly illustrated for users to complete hands-on work in class, and to revisit to review or refresh skills at any time. Students will also receive the project files (or code, if applicable) and solutions required for the hands-on work.