AI P Flashcards
Supervised Learning
Uses labeled data to train models for tasks like classification and spam detection.
Unsupervised Learning
Uses unlabeled data to detect patterns, useful for customer segmentation and anomaly detection.
Self-Supervised Learning
Generates its own labels to predict and infer missing information, useful for NLP tasks.
Semi-Supervised Learning
Uses a mix of labeled and unlabeled data to learn and cluster data.
Reinforcement Learning
Learns from interacting with the environment and receiving feedback, ideal for recommendation systems and self-driving cars.
Underfitting
Occurs when a model doesn’t learn enough from the training data, leading to poor performance.
Overfitting
Occurs when a model learns too many details, including noise and outliers, leading to poor performance on new data.
Foundation Models
Super large models trained on vast amounts of data, adaptable for various tasks.
Fine-Tuning
Customizing a pre-trained model for a specific task or dataset by training it further.
Exploratory Data Analysis (EDA)
Examining and understanding a dataset before complex analysis or modeling.
Feature Engineering
Transforming raw data into meaningful features to enhance model predictions.
Hyperparameters
Settings selected before training a model, such as learning rate, batch size, and number of epochs.
Parameters
Values automatically learned by the model during training, such as weights and biases in neural networks.
Classification Metrics
Metrics used to evaluate classification models, including accuracy, precision, recall, and F1 score.
Regression Metrics
Metrics used to evaluate regression models, including mean absolute error, root mean squared error, and R squared.
Amazon Rekognition
Allows machines to interpret images and videos using machine learning. Can be customized for content moderation and specific object detection.
Amazon Textract
“Automatically extracts text and data from scanned documents for digitization and analysis.
Amazon Comprehend
Understands and analyzes the meaning and sentiment behind text.
Amazon Translate
Automatically translates text between multiple languages.
Amazon Polly
Converts text into natural sounding speech.
Amazon Transcribe
Converts spoken language into written text, with options for custom vocabularies and transcripts.
Amazon Lex
Builds conversational interfaces using NLP and automatic speech recognition.
Amazon Forecast
Predicts future trends by identifying historical patterns.
Amazon Kendra
Builds a search engine by crawling documents and understanding context for relevant results.