Artificial Intelligence
AI Tools & Frameworks; Search Algorithms in AI; Knowledge Representation
C-CAT
AI Tools & Frameworks
Machine Learning Frameworks
| Framework | Developer | Language | Use Case |
|---|---|---|---|
| TensorFlow | Python, JS, C++ | Production ML/DL | |
| PyTorch | Facebook/Meta | Python | Research, Dynamic graphs |
| Keras | (on TensorFlow) | Python | High-level deep learning |
| Scikit-learn | Open source | Python | Classical ML algorithms |
| XGBoost | Community | Python, R | Gradient boosting |
| LightGBM | Microsoft | Python | Fast gradient boosting |
NLP Tools
| Tool | Description |
|---|---|
| NLTK | Natural Language Toolkit — Python |
| spaCy | Industrial-strength NLP library |
| Hugging Face | Pre-trained transformer models hub |
| Gensim | Topic modeling, word embeddings |
Computer Vision Tools
| Tool | Description |
|---|---|
| OpenCV | Real-time computer vision library |
| YOLO | Real-time object detection |
| Detectron2 | Facebook's object detection framework |
| MediaPipe | Google's ML solution for live/streaming media |
Cloud AI Platforms
| Platform | Provider | Services |
|---|---|---|
| SageMaker | AWS | Complete ML workflow |
| Vertex AI | Google Cloud | ML/AI platform |
| Azure ML | Microsoft | Enterprise ML |
| IBM Watson | IBM | Enterprise AI and NLP |
| Databricks | Databricks | Spark-based ML |
Search Algorithms in AI
AI uses search algorithms to find solutions to problems by exploring a state space.
28.1 Uninformed Search (Blind Search)
No domain knowledge — explores states systematically.
| Algorithm | Strategy | Complete? | Optimal? | Time | Space |
|---|---|---|---|---|---|
| BFS | Explore level by level | Yes | Yes (unit cost) | O(b^d) | O(b^d) |
| DFS | Explore deep first | No | No | O(b^m) | O(bm) |
| IDDFS | DFS with increasing depth limit | Yes | Yes | O(b^d) | O(bd) |
| UCS | Explore cheapest path first | Yes | Yes | O(b^d) | O(b^d) |
b = branching factor, d = solution depth, m = maximum depth
28.2 Informed Search (Heuristic Search)
Uses a heuristic function h(n) estimating distance to the goal.
| Algorithm | Evaluation Function | Optimal? |
|---|---|---|
| Greedy Best-First | f(n) = h(n) | No |
| A Search* | f(n) = g(n) + h(n) | Yes (admissible h) |
A Search:*
- g(n) = actual cost from start to node n
- h(n) = estimated cost from n to goal (heuristic)
- f(n) = g(n) + h(n) = total estimated path cost
- A* is optimal when h(n) is admissible (never overestimates) and consistent
Example heuristics:
- Straight-line distance (Euclidean) for navigation problems
Manhattan distance for grid-based problems
Knowledge Representation
AI systems need to represent knowledge about the world to reason and make decisions.
Forms of Knowledge Representation
| Type | Description | Example |
|---|---|---|
| Logical Rules (Propositional/Predicate) | IF-THEN rules | IF temperature > 100 THEN fever |
| Semantic Networks | Graph of concepts and relationships | "Dog" IS-A "Animal"; "Dog" HAS "Fur" |
| Frames | Object-oriented knowledge structures | Frame STUDENT {name, age, subject, grade} |
| Ontologies | Formal knowledge hierarchies | Medical ontology (diseases, symptoms) |
| Production Rules | Expert system rules | MYCIN medical diagnosis rules |
| Bayesian Networks | Probabilistic graphical models | P(Disease |
Knowledge Base vs Database
| Feature | Database | Knowledge Base |
|---|---|---|
| Content | Raw data (facts) | Structured knowledge + inference rules |
| Query | SQL | Inference engine / reasoning |
| Reasoning | No | Yes |
| Examples | MySQL, PostgreSQL | Prolog, OWL/RDF, Neo4J |
Continue learning
Related notes
Definition of AI; Need of AI
Artificial Intelligence
Introduction to Data Engineering; Big Data — The 5 V's; Types of Data
Big Data and Data Engineering
Introduction to C Programming; C Program Structure; Data Types and Variables
C Programming
What Is a Computer?; Machine Cycle: Fetch–Decode–Execute; CPU Organization
Computer Architecture
Put this topic into timed practice
Open mock tests when you want full-exam pacing, or keep drilling in practice mode.