Activity

This page provides an interactive recap of the key concepts covered in the "Introduction to AI" module. Use these activities to test your understanding and see how the core ideas connect.

Core Concepts

• Cognitive Computing: Mimics human thought processes (Adaptive, Interactive, Contextual).
• AI Terminologies:
  • Artificial Intelligence (Broadest Field)
  • Machine Learning (Subset of AI)
  • Deep Learning (Subset of ML)
  • Neural Networks (Core of DL)

Machine Learning In-Depth

• ML Process: Data Prep -> Training -> Evaluation -> Deployment
• ML Techniques:
  • Supervised Learning: Uses labeled data.
    • Classification (e.g., Spam vs. Not Spam)
    • Regression (e.g., Predicting House Prices)
  • Unsupervised Learning: Uses unlabeled data.
    • Clustering (e.g., Grouping Customers)
    • Association (e.g., Market Basket Analysis)
  • Reinforcement Learning: Learns from actions and rewards.

Deep Learning & Neural Networks

• Key Idea: Uses multi-layered neural networks to learn from vast data.
• Structure: Input Layer -> Hidden Layers -> Output Layer
• Training: Backpropagation
• ML vs. DL: DL automates feature engineering but requires more data and computation.

Advanced Models

• Generative AI: Creates new content.
  • Contrasted with Discriminative AI (classifies data).
  • Large Language Models (LLMs): A type of Generative AI for text.
    • Based on Transformer Architecture.

An Interactive Quiz

Test your knowledge with these quick questions. Click the spoiler tag to reveal the answer.

• Question 1: Which AI technique is most suitable for a task where you have a large dataset of emails, each labeled as “spam” or “not spam”?

  > **Answer:** Supervised Learning (specifically, Classification). This technique is ideal for learning from labeled data to make predictions. >

• Question 2: True or False- Deep Learning models require manual feature engineering, where a data scientist has to carefully craft the input features for the model.

  > **Answer:** False. One of the key advantages of Deep Learning is its ability to automatically learn relevant features from raw data (like images or text) through its layered neural network structure. >

• Question 3: What is the primary difference between Generative AI and Discriminative AI?

  > **Answer:** Discriminative AI learns to _distinguish_ between different categories of data (e.g., classifying an image as a cat or a dog). Generative AI learns to _create_ new data that resembles the data it was trained on (e.g., generating a new image of a cat). >

• Question 4: What is the difference between Narrow AI, General AI, Super AI, and Machine Learning AI?

Connect the Dots A Matching Puzzle

Match the term on the left with the correct description on the right.

(1-D:)- (2-C:)- (3-B:) - (4-A:)