AIF-Partitioner exam cert

 

AIF Practitioner Exam - 1 Line Revision Sheet

Machine Learning Basics

• Ensemble Learning → Combine multiple models to improve accuracy.
• Gradient Descent → Algorithm that minimizes the error (loss function).
• Epoch → One complete pass through the training data.
• Curse of Dimensionality → Too many features make learning harder.
• Normalization → Scale features so all contribute equally.
• Imputation → Fill missing values in data.
• Validation Set → Used for hyperparameter tuning.
• Confusion Matrix → Shows actual vs predicted classifications.
• ROC Curve → Trade-off between sensitivity and specificity.
• Activation Function → Adds non-linearity to neural networks.

Machine Learning Types

• Supervised Learning → Learn from labeled data.
• Unsupervised Learning → Find patterns without labels.
• Reinforcement Learning → Learn by rewards and penalties.
• Classification → Predict categories.
• Regression → Predict numbers.
• Clustering → Group similar records.

Algorithms

• Decision Tree → Used for classification and regression.
• Random Forest → Multiple decision trees combined.
• Gradient Boosting/XGBoost → Powerful ensemble for structured data.
• K-Means → Clustering algorithm.
• Naive Bayes → Probability-based classifier.
• Neural Network → Learns complex patterns using layers.

Model Quality

• Good Model → Low Bias + Low Variance.
• Imbalanced Dataset → Use Oversampling, Undersampling, or SMOTE.
• Precision-Recall Curve → Best metric for imbalanced data.

---

Amazon Bedrock

• Amazon Bedrock → Managed service for foundation models.
• Bedrock Runtime API → Used for inference requests.
• Bedrock Agent Runtime API → Invoke agents and knowledge bases.
• Agents → Execute multi-step tasks.
• Playgrounds → Test prompts and model settings.
• Guardrails → Block harmful or unwanted responses.
• Bedrock Studio → Rapid prototyping environment.
• Model Customization → Creates private customized model copies.
• Fine-Tuning → Train model with domain-specific data.
• Grounding/RAG → Reduces hallucinations using enterprise data.

---

Amazon Q

• Amazon Q Business → Enterprise AI assistant.
• Q Business Responses → Based on company data and permissions.
• Q Apps → Create and share AI-powered apps.
• Guardrails + Keywords → Control Q Business behavior.
• RAG in Q Business → Provides factual and traceable answers.

---

SageMaker

• Data Wrangler → Data preparation and feature engineering.
• Feature Store → Central repository for ML features.
• Ground Truth → Data labeling service.
• JumpStart → Pre-trained models and solutions.
• Studio Lab → Free ML experimentation environment.
• Debugger → Real-time training diagnostics.
• Experiments → Track and compare ML experiments.
• Clarify → Detect bias and explain model predictions.

---

AWS AI Services

• Rekognition → Image and video analysis.
• Textract → Extract text from documents.
• Translate → Language translation.
• Polly → Text-to-speech.
• Lex → Build chatbots.

---

Responsible AI

• Fairness → Treat users equally.
• Privacy → Protect personal data.
• Safety → Prevent harmful outputs.
• Explainability → Understand model decisions.
• Transparency → Be clear about AI usage.
• AI Service Cards → Explain AI capabilities and limitations.
• Watermarking → Identify AI-generated content.

---

Prompt Engineering

• Context → Relevant information improves answers.
• Specific Instructions → Better prompts = better results.
• Feedback Loop → Continuously improve prompts.
• Prompt Robustness → Use dynamic, context-aware templates.

---

AWS Security

• IAM Identity Center → Secure enterprise access.
• AWS Shield → DDoS protection.
• Step Functions → Orchestrate AI/ML workflows.
• Lambda → Run serverless AI tasks.

---

Last Minute Exam Crib Sheet (20 Must Remember)

1. Ensemble = Multiple models.
2. Gradient Descent = Minimize loss.
3. Epoch = One full training pass.
4. Classification = Predict category.
5. Regression = Predict number.
6. K-Means = Clustering.
7. Decision Tree = Classification/Regression.
8. Validation Set = Tune hyperparameters.
9. ROC = Sensitivity vs Specificity.
10. Data Wrangler = Prepare data.
11. Feature Store = Store features.
12. Ground Truth = Label data.
13. JumpStart = Prebuilt models.
14. Debugger = Training diagnostics.
15. Clarify = Bias detection.
16. Bedrock Runtime = Inference API.
17. Agents = Multi-step tasks.
18. Guardrails = Safe responses.
19. RAG = Reduce hallucinations.
20. Q Business = Enterprise AI assistant.

Tenerife Trip

🌅 18 Dec — Arrival Evening (Playa Paraíso)

Short walk around the area after dinner.

• 
• 
• 
• 

🐬 19 Dec — Dolphin & Whale Catamaran (Puerto Colón)

Morning boat trip + Costa Adeje promenade in the evening.

Puerto Colón Marina

• 
• 
• 
• 

Dolphin & Whale Watching

Costa Adeje Promenade

• 
• 
• 
• 

🎢 20 Dec — Siam Park (Full Day)

Europe’s #1 waterpark.

Siam Park — Tenerife’s #1 Waterpark

Main Entrance & Theme

• 
• 
• 
• 

The Big Rides (your son will LOVE these)

• 
• 
• 
• 

Wave Palace (huge artificial wave)

🏔️ 21 Dec — Teide Mountain Walk + Scenic Viewpoints

Roques de García + Mirador viewpoints + optional cable car.

Teide National Park

• 
• 
• 
• 

Roques de García

Teide Cable Car

• 
• 
• 
• 

🌊 22 Dec — Turtle Bay + Jungle Park + La Caleta Lunch

🌊 Turtle Bay (Playa El Puertito)

Calm water, snorkelling, turtles.

• 
• 

🐒 Jungle Park

Rope bridges, bird shows, tropical setting.

• 
• 
• 
• 

🍽️ La Caleta Village

Beautiful seaside restaurants.

• 
• 
• 
• 

🌞 23 Dec — Departure Day

Relax by the pool, short walk, airport.

1. Car Rental Cost (6 Days)

Typical Tenerife rate:

• £30–38/day × 6 days = £180–228

• Fuel for all 6 days = £20–30

• Parking everywhere = FREE (Teide, beaches, Siam Park, Jungle Park, La Caleta)

✅ Total car cost for 6 days:

£200–260

💷 2. Activity Costs (Tickets Only)

These stay the same whether you use taxis or a car.

🐬 Dolphin & Whale Catamaran

• £86–106 for 3 people

🎢 Siam Park

• £97 for 3 people

• Locker: £4–8

🏔️ Teide Cable Car (optional)

• £85 for 3 people

🐒 Jungle Park

• £65 for 3 people

🐢 Turtle Bay

• Snorkel rental: £8–12

🍽️ La Caleta Lunch

• £38–60

🛬 Airport taxi (arrival + departure)**

Even with a rental, you still take a taxi on arrival day:

• £30–34 (If you pick up the car at the airport, this becomes £0.)

AWS certificates

DAY 1 — Cloud Concepts + Global Infrastructure

Cloud Computing Cloud computing means renting servers, storage, and databases from AWS instead of buying your own hardware. AWS handles maintenance, power, cooling, and security. You get resources instantly and only pay for what you use.

Remember: • Rent, don’t buy • No hardware maintenance • Pay‑as‑you‑go

Benefits of Cloud Computing AWS lets you scale up when traffic increases and scale down when it’s quiet. You can launch servers in minutes. AWS spreads your application across multiple data centers so it stays online even if one fails.

Remember: • Scalability = grow • Elasticity = grow + shrink • High availability = stays online

AWS Shared Responsibility Model AWS and customers share security. AWS protects the infrastructure (data centers, hardware). You protect your data, IAM, OS patches, and configurations.

Remember: • AWS = security OF the cloud • You = security IN the cloud • EC2 → you patch OS • S3 → you set permissions

Cloud Service Models • IaaS – You manage OS and apps (EC2) • PaaS – You manage code only (Elastic Beanstalk) • SaaS – You just use the software (Gmail, Salesforce)

Remember: • IaaS = control • PaaS = code only • SaaS = ready‑to‑use

Deployment Models • Public cloud – AWS • Private cloud – your data center • Hybrid cloud – mix of both

Remember: • Public = AWS • Private = your DC • Hybrid = both

AWS Global Infrastructure AWS has Regions (geographic areas), each with multiple Availability Zones (separate data centers). Edge Locations deliver content faster.

Remember: • Region = location • AZ = data centers • Edge = fast content

DAY 2 — EC2, S3, IAM

EC2 (Virtual Servers) EC2 is like renting a computer in the cloud. You choose OS, size, storage, and network. You manage updates and security.

Remember: • Virtual machine • You manage OS • Auto Scaling + Load Balancer

AWS Fargate (Serverless Containers) Fargate runs Docker containers without servers. No EC2 needed. AWS handles scaling and infrastructure.

Remember: • Run containers serverlessly • Works with ECS/EKS • Pay only for runtime

S3 (Object Storage) S3 stores files like images, videos, logs, and backups. It’s extremely durable and scalable.

Remember: • Stores files • 11 nines durability • Unlimited storage

S3 Storage Classes • Standard – frequent • Intelligent‑Tiering – auto‑optimize • IA – infrequent • One Zone‑IA – cheaper • Glacier – archive • Deep Archive – long‑term

Remember: • Standard = everyday • IA = rare • Glacier = archive

EBS (Disk for EC2) EBS is a persistent block storage volume attached to EC2.

Remember: • Block storage • Persistent • Snapshots

EFS (Shared File System) EFS is a shared drive for multiple EC2 instances.

Remember: • Shared • Auto‑scaling • Multi‑EC2

IAM (Security & Access Control) IAM controls who can access what in AWS.

Remember: • Users = people • Roles = temporary • Policies = permissions

DAY 3 — Serverless (Lambda, API Gateway, DynamoDB)

Lambda (Run Code Without Servers) Lambda runs your code automatically when triggered. No servers to manage.

Remember: • No servers • Auto‑scaling • Pay per execution

API Gateway (Create APIs) API Gateway creates REST/HTTP APIs and handles authentication, throttling, and validation.

Remember: • Front door for APIs • Works with Lambda • Handles security

DynamoDB (NoSQL Database) DynamoDB is a fast, serverless NoSQL database.

Remember: • NoSQL • Millisecond speed • Auto‑scaling

Serverless Flow Client → API Gateway → Lambda → DynamoDB → Response

Remember: • Fully managed • No servers • Scales automatically

DAY 4 — Databases + VPC Basics

RDS (Managed SQL Database) RDS runs SQL databases like MySQL and PostgreSQL. AWS handles backups, patching, and failover.

Remember: • Managed SQL • AWS handles maintenance • Multi‑AZ

Aurora (High‑Performance Database) Aurora is AWS’s own database, compatible with MySQL/PostgreSQL but faster.

Remember: • Faster than MySQL • Auto‑replication • Highly available

DMS (Database Migration Service) DMS migrates databases to AWS with minimal downtime.

Remember: • Minimal downtime • Supports many DBs • Continuous sync

Snowball (Large Data Transfer) Snowball is a physical device AWS ships to you for transferring TBs of data.

Remember: • Huge data transfer • Faster than internet • Secure

VPC (Your Private Network) A VPC is your own private network inside AWS.

Remember: • Your network • Public + private subnets • Security groups = firewall

VPC Peering & Transit Gateway • Peering = connect 2 VPCs • Transit Gateway = connect many VPCs

Remember: • Peering = 1‑to‑1 • TGW = many‑to‑many • No transitive peering

CIDR (IP Addressing) CIDR defines IP ranges like 10.0.0.0/24.

Remember: • /24 = 256 IPs • /16 = 65,536 IPs • /8 = 16.7M IPs

IPv6 + Egress‑Only IGW IPv6 has globally unique addresses. No NAT needed.

Remember: • IPv6 = no NAT • Egress‑Only IGW = outbound only • Huge address space

DAY 5 — Billing, Pricing, Support Plans

Pricing Basics AWS charges for compute, storage, and data transfer OUT.

Remember: • Compute + storage cost • Data IN free • Region affects price

Cost Tools • Pricing Calculator – estimate • Cost Explorer – analyze • Budgets – alerts

Remember: • Calculator = estimate • Explorer = analyze • Budgets = alerts

Support Plans • Basic – free • Developer – email • Business – 24/7 • Enterprise – TAM

Remember: • Basic = free • Business = 24/7 • Enterprise = TAM

Python basic

 

Python Basics Summary

1. Hello World Program

   • Use print("Hello, World!") to display text.

2. Syntax Errors

   • Occur when Python can't understand your code due to incorrect structure.
   • Example: missing brackets, colons, or using wrong keywords.
   • print("Hello"  # ❌ SyntaxError: missing closing parenthesis
   
   
3. Variable Naming Rules
1. Must start with a letter or underscore (_)
2. Can include letters, numbers, and underscores
3. Cannot use Python keywords (like class, if, def)
4. Case-sensitive (Name ≠ name)

5. student_name = "Aisha"  # ✅ Valid
   1name = "Ben"           # ❌ Invalid

4. Using Variables

   • Variables store data like text, numbers, or results of calculations.

   • name = "Aisha"
     score = 85
     total = score + 10

5. Input from Command Prompt
1. Use input() to get user input.
2. Always returns a string, so convert to int or float if needed.

3. name = input("Enter your name: ")
   age = int(input("Enter your age: "))

6. Comments in Python

• Used to explain code or leave notes.
• Single-line: # This is a comment
• Multi-line: ''' This is a multi-line comment '''
• 

7. Data Types
1. str: text (e.g., "Hello")
2. int: whole numbers (e.g., 10)
3. float: decimal numbers (e.g., 3.14)

8. Assignment Statements

   • Use = to assign values to variables.

9. If-Else Statements

   • Make decisions using if, elif, and else.

   • score = 75
     if score >= 50:
         print("Pass")
     else:
         print("Fail")

10. BIDMAS Rule in Arithmetic

    • Python follows Brackets, Indices, Division, Multiplication, Addition, Subtraction.

    • result = (3 + 2) * 4 ** 2 / 2 - 5

11. Comparison Operators

    • ==, !=, >, <, >=, <= for comparing values.

12. Indentation

    • Python uses indentation to define blocks of code (e.g., inside if, for, def).

13. Types of Errors

    • Syntax Error: Code structure mistake
    • Runtime Error: Error during execution (e.g., divide by zero)
    • Logic Error: Code runs but gives wrong result

14. Loops

    • for loop: repeat a known number of times

    • for i in range(5):
          print(i)

    • while loop: repeat while a condition is true

    • count = 1
      while count <= 5:
          print(count)
          count += 1