ML concepts Flashcards
What is machine learning (ML)?
Machine learning is a computational process that enables systems to learn from data and make predictions or decisions.
How does machine learning improve performance over time?
Machine learning improves performance through experience and data by learning patterns and relationships.
What principles does machine learning combine?
Machine learning combines computer science (algorithms, data structures) and mathematics (statistics, linear algebra).
What does inferencing mean in ML?
Inferencing is the process of using a trained model to generate predictions on new, unseen data.
What are the main types of machine learning?
Supervised learning, unsupervised learning, semi-supervised learning, and reinforcement learning.
What is supervised learning?
Supervised learning trains models on labeled data, where inputs are paired with correct outputs.
What is unsupervised learning?
Unsupervised learning analyzes unlabeled data to identify patterns and structures without explicit guidance.
What is semi-supervised learning?
Semi-supervised learning combines labeled and unlabeled data to improve model performance while reducing labeling costs.
What is reinforcement learning?
Reinforcement learning trains agents to maximize cumulative rewards through interactions with an environment.
What are common supervised learning methods?
Classification (predicting categories) and regression (predicting continuous values).
What algorithms are used in supervised learning?
Regression, logistic regression, decision trees, support vector machines, and neural networks.
What is clustering in unsupervised learning?
Clustering partitions data into meaningful subsets based on similarity.
What is anomaly detection?
Anomaly detection identifies unusual patterns or outliers in data to detect abnormalities or threats.
What is pattern identification?
Pattern identification finds similarities, differences, or relationships among data points.
How does reinforcement learning work?
Agents interact with an environment, receive feedback (rewards or penalties), and learn optimal strategies.
What is an example of reinforcement learning?
Training an AI to drive a car by rewarding good turns and penalizing crashes.
What are some applications of machine learning?
Anomaly detection, computer vision, natural language processing, and conversational AI.
How is machine learning used in computer vision?
It enables tasks like object detection, image classification, and facial recognition.
What is natural language processing (NLP)?
NLP allows machines to understand, interpret, and generate human language.
What are examples of NLP applications?
Sentiment analysis, language translation, and text summarization.
What is conversational AI?
Conversational AI enables human-like interactions through chatbots and virtual assistants.