A subset of AI that involves training machines to learn from data and make predictions or decisions based on that data
Types of machine learning:
- Supervised learning: labeled data is used to train the machine
- Unsupervised learning: unlabeled data is used to identify patterns
- Reinforcement learning: machine learns through trial and error
Machine learning algorithms:
- Linear regression
- Decision trees
- Random forests
- Support vector machines (SVMs)

A subset of AI that deals with the interaction between computers and human language
Goals of NLP:
- Language understanding
- Language generation
- Language translation
NLP techniques:
- Tokenization: breaking down text into individual words or tokens
- Part-of-speech tagging: identifying the grammatical category of each word
- Named entity recognition: identifying named entities such as people, places, and organizations
- Sentiment analysis: determining the emotional tone of text

A subset of AI that deals with enabling computers to interpret and understand visual data from the world
Applications of computer vision:
- Image recognition
- Object detection
- Image segmentation
- Facial recognition
Computer vision techniques:
- Convolutional neural networks (CNNs)
- Edge detection
- Feature extraction
- Object recognition

A subset of machine learning that involves the use of neural networks with multiple layers
Types of deep learning:
- Feedforward neural networks
- Recurrent neural networks (RNNs)
- Convolutional neural networks (CNNs)
Deep learning applications:
- Image recognition
- Speech recognition
- Natural language processing
- Game playing

A type of machine learning model inspired by the structure and function of the human brain
Components of a neural network:
- Input layer
- Hidden layers
- Output layer
- Weights and biases
Types of neural networks:
- Feedforward neural networks
- Recurrent neural networks (RNNs)
- Convolutional neural networks (CNNs)
Neural network training:
- Backpropagation
- Gradient descent
- Activation functions

데이터를 통해 기계가 학습하고 예측 또는 의사 결정을 내리는 AI의 하위 집합
머신 러닝의 유형:
- 지도 학습: 레이블이 붙은 데이터를 사용하여 기계를 훈련
- 비지도 학습: 레이블이 없는 데이터를 사용하여 패턴을 확인
- 강화 학습: 기계가 실수를 통해 학습
머신 러닝 알고리즘:
- 선형 회귀
- 의사 결정 트리
- 랜덤 포레스트
- 서포트 벡터 머신(SVM)

컴퓨터와 인간 언어 간의 상호작용을 다루는 AI의 하위 집합
NLP의 목표:
- 언어 이해
- 언어 생성
- 언어 번역
NLP 기술:
- 토큰화: 텍스트를 개별 단어 또는 토큰으로 나누는 것
- 품사 태깅: 각 단 слова의 문법 카테고리를 확인
- Named Entity Recognition(NER): 사람, 장소, 조직 등의 개체를 확인
- 감정 분석: 텍스트의 감정 톤을 확인