Summary - AI(OCS351)

ARTIFICIAL INTELLIGENCE

1. **Introduction to Artificial Intelligence (AI)**
**Definition**: AI refers to the simulation of human intelligence in machines that are programmed
to think and mimic human actions.

**Applications**: Natural language processing, image and speech recognition, robotics, autonomous
vehicles, etc.



2. **Types of AI**
**Narrow AI**: AI that specializes in one task (e.g., Siri, Google Translate).

**General AI**: AI with human-like abilities across various tasks (currently theoretical).

**Strong vs. Weak AI**: Strong AI can perform any intellectual task that a human can, while weak AI
is designed for specific tasks.



3. **Machine Learning (ML) Basics**
**Definition**: Subset of AI that enables machines to learn from data without explicit programming.

**Types**: Supervised learning, unsupervised learning, reinforcement learning.

**Algorithms**: Linear regression, decision trees, neural networks, etc.



4. **Deep Learning**
**Definition**: Subset of ML based on neural networks with multiple layers (deep neural networks).

**Applications**: Image and speech recognition, natural language processing, autonomous driving.

**Frameworks**: TensorFlow, PyTorch, Keras.



5. **Natural Language Processing (NLP)**
**Definition**: AI technique enabling machines to understand, interpret, and generate human
language.

**Applications**: Chatbots, sentiment analysis, language translation.

**Techniques**: Tokenization, POS tagging, named entity recognition, sentiment analysis.



6. **Computer Vision**
**Definition**: Field of AI focusing on enabling machines to interpret and understand visual
information.

**Applications**: Object detection, facial recognition, medical imaging.