Title here
Summary here
Certified AI Practitioner
Resources
Amazon SageMaker Documentation
Exam Domains
Click to expand Exam Domain
The following domain are available for the the exam. Note: These are taken from the Exam Overview in the link above
- Domain 1: Fundamentals of AI and ML (20% of scored content)
- Domain 2: Fundamentals of Generative AI (24% of scored content)
- Domain 3: Applications of Foundation Models (28% of scored content)
- Domain 4: Guidelines for Responsible AI (14% of scored content)
- Domain 5: Security, Compliance, and Governance for AI Solutions (14% of scored content)
Definitions
Click to expand
| Definition | Description |
|---|---|
| What is an Artificial Intelligence? | The theory and development of computer systems able to perform tasks that normally require human intelligence, such as visual perception, speech recognition, decision-making, and translation between languages. |
| What is Machine Learning? | Ability of machine to learn without being programmed. |
| What is a Model? | A model is a program that has been trained on a set of data to recognise certain patterns or make certain decision without further human intervention. Model apply different algorithms (not manually set rules) to relevant data inputs to achieve the tasks, or output. |
| What is an Algorithm? | Algorithms are procedures, often described in mathematical language or pseudocode, to be applied to a dataset to achieve a certain function or purpose. AI models use algorithms to recognise patterns and trends in data. Multiple algorithms working together comprise an AI program or model. |
Machine Learning Algorithms Categories
Click to expand Machine Learning Algorithms
There three types of Machine Learning Algorithms
- Supervised
- Unsupervised
- Reinforcment
| Criteria | Supervised ML | Unsupervised ML | Reinforcement ML |
|---|---|---|---|
| Definition | Learn by using labelled data | Trained using unlabelled data without any guidance | Works on interacting with the environment |
| Type of Data | Labelled Data | Unlabelled data | No - predefined data |
| Supervision | Extra supervision | No supervision | No supervision |
| Algorithms | Linear Regression Logistic Regression | K - Means, C - Means, Apriori | Q - Learning, SARSA |
| Aim | Calculate Outcomes | Discover underlying patterns | Learn a series of actions |
| Application | Risk Evaluation, Forecast Sales | Recommndation System, Anomaly Detection | Self Driving Cars, Gaming, Healthcare |
AWS AI/ML Products
Click to expand Machine Learning Algorithms
| Question | Answer |
|---|---|
| What is Sage Maker? | SageMaker is a fully managed machine learning service that helps you create powerful machine learning models. With SageMaker, data scientists and developers can build and train machine learning models, and then directly deploy them into a production-ready hosted environment. |
| What is Bedrock | Amazon Bedrock is a fully managed service that offers a choice of high-performing foundation models (FMs) from leading AI companies. |
SageMaker
SageMaker Overview
Typical SageMaker Workflow for Machine Learning includes
- Generate The Data Example
- Train the Model
- Deploy to Model to Production
Sub-Step for Workflow
- Generate Example Data
- Fetch the data
- Clean the data
- Prepare or transform the data
- Train the Model
- Training the model
- Evaluating the model
- Deploy the model
- Deploy the model then optomise the model by going back to step when necessary
Machine learning is a continuous cycle. After deploying a model, you monitor the inferences, collect more high-quality data, and evaluate the model to identify drift. You then increase the accuracy of your inferences by updating your training data to include the newly collected high-quality data. As more example data becomes available, you continue retraining your model to increase accuracy.
Sagemaker Model Deployment Options
| Deployment Option | Use Case |
|---|---|
| Real-time Inference | For persistent, real-time endpoints that make one prediction at a time, use SageMaker real-time hosting services |
| Serverless Inference | Workloads that have idle periods between traffic spikes and can tolerate cold starts |
| Asynchronous Inference | Requests with large payload sizes up to 1GB, long processing times, and near real-time latency requirements |
| Batch Transforms | To get predictions for an entire dataset, use SageMaker batch transform. See Batch transform for inference with Amazon SageMaker. |
Next
About Guides