Artificial Intelligence
- Definitions and History:
  - What is AI? (Mimicking human intelligence, problem-solving, etc.)
  - Who coined the term “Artificial Intelligence” (John McCarthy)?
  - Turing Test (Purpose).

Types of AI:
- Strong AI vs. Weak AI (Narrow AI): Understanding the fundamental difference (human-level vs. task-specific).
- Reactive Machines, Limited Memory, Theory of Mind, Self-Aware AI (conceptual differentiation).

Core AI Branches/Components:
- Machine Learning: What it is in relation to AI (subset).
- Natural Language Processing (NLP): Its goal (understanding/generating human language).
- Computer Vision (CV): Its goal (interpreting visual data).
- Robotics (basic idea).

Problem Solving & Search:
- Informed vs. Uninformed Search: A* search, BFS, DFS (basic understanding of when to use which).
- Heuristics.

AI Agents:
- Basic components of an intelligent agent (Percepts, Actions, Environment).

Ethical Considerations (Conceptual):
- Bias, fairness, privacy (awareness of these issues).

Natural Language Processing
- Fundamental Concepts:
  - Tokenization: Splitting text into words/units.
  - Stemming vs. Lemmatization: Differences and purpose (text normalization).
  - Stop Words: What they are and why removed.

Text Representation:
- Bag-of-Words (BoW): Basic concept.
- TF-IDF: Term Frequency-Inverse Document Frequency (purpose).
- Word Embeddings: Concept of representing words as vectors, capturing semantic similarity (e.g., Word2Vec, GloVe, BERT – focus on their function).

Core NLP Tasks:
- Part-of-Speech (POS) Tagging: Assigning grammatical tags.
- Named Entity Recognition (NER): Identifying specific entities (persons, locations, organizations).
- Sentiment Analysis: Determining emotional tone.
- Machine Translation: Converting language.
- Text Summarization: Condensing text.

Architectures (Conceptual):
- RNNs/LSTMs: Used for sequential data.
- Transformers & Attention: Revolutionary for NLP (understanding the concept of attention).

Machine Learning
- Core ML Paradigms:
  - Supervised Learning: Definition, examples (Regression, Classification).
  - Unsupervised Learning: Definition, examples (Clustering, Dimensionality Reduction).
  - Reinforcement Learning: Definition (agent-environment interaction, rewards).

Key Terminology:
- Features/Attributes: Input variables.
- Labels/Targets: Output variables.
- Training Data, Test Data, Validation Data: Their roles.
- Overfitting & Underfitting: How to identify, basic mitigation.
- Bias-Variance Trade-off: Conceptual understanding.
- Hyperparameters: Tunable parameters.

Common Algorithms (Focus on how they work at a high level and their primary use case):
- Regression: Linear Regression (basic equation).
- Classification:
  - Logistic Regression (binary classification).
  - Decision Trees (tree structure, simple rules).
  - K-Nearest Neighbors (KNN) (instance-based, lazy learner).
  - Support Vector Machines (SVM) (finding optimal hyperplane).
  - Naive Bayes (probabilistic, based on Bayes’ theorem).
- Clustering: K-Means (grouping data into ‘k’ clusters).
- Dimensionality Reduction: Principal Component Analysis (PCA) (reducing features).

Model Evaluation Metrics (Crucial for MCQs):
- Classification: Accuracy, Precision, Recall, F1-Score (definitions and what they measure), Confusion Matrix (components).
- Regression: Mean Squared Error (MSE), Root Mean Squared Error (RMSE).
- Cross-Validation: Purpose (robust evaluation).

Deep Learning Basics (as part of ML):
- Neural Networks: Basic structure, Activation Functions (purpose).
- Backpropagation (conceptual): How weights are updated.
- CNNs: For images.
- RNNs: For sequences.

Blockchain Technology
- Fundamental Principles:
  - Decentralization: No central authority.
  - Immutability: Data cannot be altered after recording.
  - Transparency: Transactions are visible to participants.
  - Cryptographic Hashing: Securing blocks, creating links.
- Distributed Ledger Technology (DLT): The underlying concept.
- Core Components:
  - Blocks: Data, timestamp, hash of previous block.
  - Chain: How blocks are linked.
  - Nodes: Participants in the network.

Consensus Mechanisms (Key for MCQs):
- Proof of Work (PoW): How it works (mining, computational puzzle), key characteristics (energy consumption).
- Proof of Stake (PoS): How it works (staking), advantages over PoW.

Smart Contracts:
- Definition: Self-executing agreements.
- Decentralized Applications (DApps): Applications built on smart contracts.
- Ethereum as the platform for smart contracts.

Types of Blockchains:
- Public Blockchain: (e.g., Bitcoin, Ethereum) – open, permissionless.
- Private/Permissioned Blockchain: (e.g., Hyperledger Fabric) – restricted access.
- Consortium Blockchain (basic idea).

Key Use Cases:
- Cryptocurrencies (Bitcoin, Ethereum).
- Supply Chain.
- Digital Identity.
- Decentralized Finance (DeFi).
- Non-Fungible Tokens (NFTs).

Emerging Technologies Unveiled: AI, ML, Blockchain & More