CertifyDeckCargando contenido…
The official AWS Certified AI Practitioner syllabus, organized by domain. Check off each point as you review it.
Inicia sesión para guardar tu progreso entre sesiones.
Explain basic AI concepts and terminologies
An ML model is trained on historical data to learn patterns and then performs inference, making predictions on new data. A good fit generalizes: an overfit model is accurate on training data but fails on new data, while an underfit model fails on both. Bias produces unequal outcomes across groups and harms fairness; an LLM is a very large deep learning model pre-trained on huge volumes of text.
What is Overfitting? ↗What is Artificial Intelligence (AI)? ↗
AI is the umbrella term; ML is one of its branches and learns patterns from data without explicit instructions, and deep learning is a type of ML that uses neural networks with many layers. Generative AI uses deep learning models to create new content instead of only classifying it. Agentic AI combines those models with autonomy to plan and take actions through tools toward a goal.
What's the Difference Between AI and Machine Learning? ↗Comparing traditional AI to software agents and agentic AI ↗
Real-time inference serves interactive, low-latency requests, and serverless inference removes instance management and suits intermittent traffic that tolerates cold starts. Asynchronous inference queues requests with large payloads or long processing and can scale to zero instances. Batch inference, such as batch transform or Amazon Bedrock batch inference, processes large volumes of data without a persistent endpoint.
Deploy models for inference ↗Process multiple prompts with batch inference ↗
Structured data fits into tables with a fixed schema; unstructured data, such as audio, images or free text, follows no predefined rules. Labeled data pairs each input with its correct answer and is required for supervised learning, while unlabeled data is used to discover patterns and to pre-train LLMs. Time-series data adds a timestamp to each value so that future values can be forecast.
What's the Difference Between Structured Data and Unstructured Data? ↗What is Data Labeling? ↗
Supervised learning trains on inputs paired with labeled outputs (classification and regression); unsupervised learning finds patterns in unlabeled data (clustering, anomaly detection); semi-supervised learning mixes a little labeled data with a lot of unlabeled data. Reinforcement learning learns by trial and error to maximize a reward, and RLHF applies it with human preferences to align LLMs.
Identify practical use cases for AI
AI/ML adds value by automating routine tasks such as extracting and classifying data from documents, by helping people decide better and faster by surfacing patterns in large data volumes, and by scaling services such as 24/7 customer support. It fits best with problems whose patterns are complex or keep changing, such as fraud or personalized recommendations.
What is Machine Learning? ↗What is Artificial Intelligence (AI)? ↗
ML is probabilistic: it provides predictions, not guaranteed exact results, so when the logic is known and a specific, reproducible outcome is required, a rules-based system is the better fit. Before investing, compare ML with a simpler baseline and estimate its total cost: data preparation and labeling, training, hosting, and maintenance.
MLCOST02-BP01 Identify if machine learning is the right solution ↗What is Machine Learning? ↗
Regression predicts continuous values, such as a house price, and classification assigns each item to predefined classes: binary with two classes, such as spam or not spam, and multiclass with several. Without labels, clustering discovers groups of similar items, anomaly detection flags rare observations, and topic modeling organizes documents into topics not known in advance.
Types of Algorithms - Amazon SageMaker AI ↗Built-in algorithms and pretrained models in Amazon SageMaker ↗
Computer vision analyzes images and video, such as defect inspection; NLP extracts sentiment or entities from text, and speech recognition turns audio into text. Recommendations come from user interactions, fraud is detected as an anomaly, forecasting uses time series, knowledge bases answer from proprietary data, and agentic AI acts on its own toward a goal.
Built-in algorithms and pretrained models in Amazon SageMaker ↗What is Agentic AI? - AWS ↗
Amazon Transcribe converts speech to text, Amazon Polly turns text into lifelike speech, and Amazon Translate translates text between languages. Amazon Comprehend extracts entities, key phrases and sentiment and builds custom classifiers with AutoML; Amazon Lex builds voice and text bots that understand intent. Amazon SageMaker AI is the managed service to build, train and deploy your own models.
Traditional ML suits specific tasks on well-labeled tabular data and, when regulation requires explaining each decision, interpretable models such as decision trees. FMs suit unstructured or unlabeled data, generated content, or tasks that need context, but they are deep networks that are harder to interpret; when you use one, start with the smallest model that meets the bar.
Data differences between generative AI and traditional ML - AWS Prescriptive Guidance ↗MLPERF06-BP02 Evaluate model explainability - Machine Learning Lens ↗
Describe the AI/ML development lifecycle
The ML lifecycle runs through business goal, problem framing, data processing (collection, preprocessing and feature engineering), model development (training, tuning and evaluation), deployment and monitoring, with feedback loops. Data is split into training, validation and test sets, and the same preprocessing applied to training data is applied to inference requests.
Well-Architected machine learning lifecycle - Machine Learning Lens ↗Data processing - Machine Learning Lens ↗
Building a foundation model from scratch is expensive, needs enormous resources and can take months, so the usual path is to start from a pre-trained FM. SageMaker JumpStart offers publicly available and proprietary third-party FMs, each under its own license that the customer must review; Bedrock Marketplace extends the catalog, and Custom Model Import brings models customized elsewhere into Bedrock.
What are Foundation Models? ↗Model sources and license agreements - Amazon SageMaker AI ↗
A model can be consumed as a managed API service such as Amazon Bedrock (serverless, per-token billing, with Provisioned Throughput for a fixed level of throughput) or self-hosted. SageMaker AI managed endpoints give more control than Bedrock with less overhead than EC2; full self-hosting gives the most control but the owner must maintain endpoints and model performance.
GENPERF03-BP01 Use managed solutions for model hosting - Generative AI Lens ↗Amazon Bedrock or Amazon SageMaker AI? - AWS Decision Guides ↗
Amazon Bedrock gives serverless access to foundation models; SageMaker AI covers building, training and deploying your own models (Feature Store, Pipelines, Model Registry). Kiro is a spec-driven agentic development environment for developers, and Amazon Quick gives business users AI-powered dashboards, research and automations with no infrastructure to manage.
What is Amazon Quick? - Amazon Quick ↗Pipelines - Amazon SageMaker AI ↗
MLOps applies DevOps principles to ML: it automates training and deployment in CI/CD pipelines, versions code and data so results are reproducible and auditable, and limits technical debt by starting from a simple baseline model. In production, teams monitor for drift and retrain when metrics fall below defined KPIs rather than on a fixed schedule.
What is MLOps? ↗MLSUS06-BP02 Retrain only when necessary - Machine Learning Lens ↗
Precision, TP/(TP+FP), matters when false positives are costly; recall, TP/(TP+FN), when false negatives are; F1 is their harmonic mean, and accuracy is misleading with imbalanced classes. Alongside them, teams track business metrics such as ROI, cost per user or customer satisfaction, tied to the project's business objectives.
Metrics and validation - Amazon SageMaker AI ↗MLOPS01-BP03 Monitor model adherence to business requirements - Machine Learning Lens ↗