🌐1. Machine Learning (ML)
Definition:
Machine Learning is a subset of AI where systems learn from data and improve performance without being explicitly programmed.
Subtypes:
- Supervised Learning – Trained on labeled data (e.g., spam detection).
- Unsupervised Learning – Finds patterns in unlabeled data (e.g., customer segmentation).
- Reinforcement Learning – Learns through trial and error by receiving rewards/punishments (e.g., game-playing bots, robotics).
Applications:
Email filtering, recommendation systems, fraud detection, self-driving cars.
🧠 2. Deep Learning
Definition:
A specialized subset of Machine Learning that uses artificial neural networks with many layers (hence "deep").
Key Concepts:
- Mimics the human brain’s structure.
- Works well with massive amounts of data and complex patterns.
Applications:
Speech recognition, image classification, natural language processing, facial recognition.
🗣️ 3. Natural Language Processing (NLP)
Definition:
NLP enables machines to understand, interpret, and generate human language.
Subdomains:
- Text Analysis – Sentiment analysis, topic modeling.
- Machine Translation – Language translation (e.g., Google Translate).
- Speech Recognition & Generation – Converting voice to text and vice versa.
Applications:
Chatbots, voice assistants, translation services, spam filters.
👀 4. Computer Vision
Definition:
Enables machines to "see" and interpret visual data like images and videos.
Key Capabilities:
- Object detection
- Image classification
- Facial recognition
- Scene reconstruction
Applications:
Autonomous vehicles, medical imaging, security surveillance, quality inspection in manufacturing.
🕹️ 5. Robotics
Definition:
Combines AI with mechanical engineering to build intelligent machines capable of performing physical tasks.
Key Areas:
- Perception – Understanding surroundings using sensors.
- Planning – Making decisions based on environment.
- Control – Executing movements/actions precisely.
Applications:
Autonomous robots, drones, robotic arms in factories, surgical robots.
🔉 6. Speech Recognition & Processing
Definition:
Converts spoken language into text and vice versa.
Processes:
- Speech-to-Text (STT) – Dictation software, virtual assistants.
- Text-to-Speech (TTS) – Used in accessibility tools and voice responses.
Applications:
Voice-controlled devices (e.g., Alexa, Siri), transcription services.
🎮 7. Reinforcement Learning (RL)
Definition:
An AI agent learns by interacting with its environment and receiving rewards or penalties.
Key Concepts:
- Agent, Environment, Actions, Rewards
- Goal is to maximize cumulative reward over time.
Applications:
Game-playing (AlphaGo), robotics, finance, real-time decision systems.
