Introduction to Machine Learning and Computer Vision

Study Notes

A subset of Artificial Intelligence (AI) that enables machines to learn from data without being explicitly programmed
Types:
- Supervised Learning: Trained on labeled data to make predictions
- Unsupervised Learning: Finds patterns or structure in unlabeled data
- Reinforcement Learning: Learns from interactions with an environment to make decisions

Enables machines to interpret and understand visual data from images and videos
Applications:
- Image Classification: Identifying objects within images
- Object Detection: Locating objects within images
- Image Segmentation: Dividing images into regions of interest
- Image Generation: Creating new images from existing data

A machine learning model inspired by the structure and function of the human brain
Composed of interconnected nodes (neurons) that process and transmit information
Types:
- Feedforward Networks: Data flows only in one direction
- Recurrent Neural Networks (RNNs): Data flows in a loop, allowing information to persist

A subset of Machine Learning that uses Neural Networks with multiple layers to analyze data
Enables machines to learn complex patterns and relationships in data
Applications:
- Image Recognition
- Speech Recognition
- Natural Language Processing

Enables machines to understand, interpret, and generate human language
Applications:
- Sentiment Analysis: Determining the emotional tone of text
- Language Translation: Translating text from one language to another
- Text Summarization: Condensing large texts into concise summaries

A subset of Artificial Intelligence (AI) that enables machines to learn from data without being explicitly programmed
Uses types of learning:
- Supervised Learning: Trained on labeled data to make predictions on new unseen data
- Unsupervised Learning: Finds patterns or structure in unlabeled data to identify hidden relationships
- Reinforcement Learning: Learns from interactions with an environment to make decisions that maximize rewards

Enables machines to interpret and understand visual data from images and videos
Applications include:
- Image Classification: Identifying objects within images through classification models
- Object Detection: Locating objects within images using bounding boxes and classification
- Image Segmentation: Dividing images into regions of interest for further analysis
- Image Generation: Creating new images from existing data using generative models

A machine learning model inspired by the structure and function of the human brain
Composed of interconnected nodes (neurons) that process and transmit information through activation functions
Types of Neural Networks:
- Feedforward Networks: Data flows only in one direction, from input layer to output layer
- Recurrent Neural Networks (RNNs): Data flows in a loop, allowing information to persist over time

A subset of Machine Learning that uses Neural Networks with multiple layers to analyze data
Enables machines to learn complex patterns and relationships in data through hierarchical representations
Applications include:
- Image Recognition: Identifying objects within images using convolutional neural networks
- Speech Recognition: Transcribing spoken language into text using recurrent neural networks
- Natural Language Processing: Enabling machines to understand and generate human language

Enables machines to understand, interpret, and generate human language
Applications include:
- Sentiment Analysis: Determining the emotional tone of text through machine learning models
- Language Translation: Translating text from one language to another using machine learning models
- Text Summarization: Condensing large texts into concise summaries using natural language processing algorithms