In supervised training, the model is provided with labeled data, meaning each input in the training dataset has a corresponding target output (label). The model learns by comparing its predictions to the correct labels and adjusting its weights based on the error (loss). Supervised learning is commonly used for tasks like classification, regression, and object detection.
Unsupervised training, on the other hand, involves using data without labeled outputs. The goal is for the model to find hidden patterns or structures within the data, such as clustering similar data points together or reducing the dimensionality of the input space. Common applications of unsupervised learning include clustering, anomaly detection, and generative models.
The main difference lies in the availability of labeled data: supervised learning requires labeled data for training, while unsupervised learning works with unlabeled data to discover patterns autonomously.