1/15
These flashcards cover key vocabulary and concepts related to supervised learning, classification, regression, neural networks, and validation techniques.
Supervised Learning
A type of learning where the model learns from labeled data consisting of input-output pairs (x, y) to predict correct outputs for unseen data.
Classification
A supervised learning task where the output consists of discrete labels, such as 'spam' or 'not spam'.
Regression
A supervised learning task where the output consists of continuous values, such as predicting house prices.
Binary Classification
A type of classification where there are only two exclusive classes.
Multiclass Classification
Classification tasks where each sample belongs to exactly one out of more than two possible classes.
Multilabel Classification
A classification task where each sample can have multiple labels, with varying numbers of labels per sample.
Vector Regression
A type of regression that predicts multiple continuous values, represented as a vector.
Softmax Activation
A function that converts scores from the neural network into probabilities that sum to 1.
Binary Cross-Entropy
A loss function used for binary classification problems, measuring the difference between predicted probabilities and actual classes.
Mean Squared Error (MSE)
A common loss function used in regression that measures the average squared difference between predicted and actual values.
Overfitting
A modeling error that occurs when a neural network starts to learn noise in the training data, leading to worse performance on unseen data.
K-fold Cross-Validation
A validation technique that divides the dataset into K partitions to train and validate the model multiple times for robust performance evaluation.
Neural Network
A computational model that consists of layers of interconnected nodes, used for various tasks including classification and regression.
Input Layer
The first layer in a neural network that receives the input data.
Output Layer
The final layer in a neural network that produces the output predictions.
Activation Function
A mathematical function applied to a node's output in a neural network to introduce non-linearity into the model.