Training a model on data where some of the training examples have labels but others don’t. One technique for semi-supervised learning is to infer labels for the unlabeled examples , and then to train on the inferred labels to create a new model. Semi-supervised learning can be useful if labels are expensive to obtain but unlabeled examples are plentiful. Self-training is one technique for semi-supervised learning.1
목차 목차 관련 글 지도 학습 “Supervised machine learning is analogous to learning a subject by studying a set of questions and their corresp…” Example (machine learning) “Examples in supervised learning fall into two general categories:” Introduction to Machine Learning “Understand the key concepts of supervised machine learning.” ML crash course - Linear regression “The goal of training a model is to minimize the loss, reducing it to its lowest possible value.” A simple way to prevent neural networks from overfitting “We show that dropout improves the performance of neural networks on supervised learning tasks in vision, speech…” Labeled example “In supervised machine learning, models train on labeled examples and make predictions on unlabeled examples” TabNet: Attentive Interpretable Tabular Learning “Finally, for the first time to our knowledge, we demonstrate self-supervised learning for tabular data, signifi…” Machine Learning Systems “Machine Learning Systems provides a systematic framework for understanding and engineering machine learning (ML…” Clipping (machine learning) “Outliers can damage models, sometimes causing weights to overflow during training.” Epoch (machine learning) “An epoch represents N/batch size training iterations, where N is the total number of examples.” Generalization (machine learning) “You train a model on the examples in the training set.” Downsampling (machine learning) “Training on a disproportionately low percentage of over-represented class examples in order to improve model tr…” Iteration (machine learning) “A backward pass (backpropagation) to adjust the model's parameters based on the loss and the learning rate.” Minority class (machine learning) “A training set with a million examples sounds impressive.” 기계학습 관련 절: Generalization and OOD 분류 모델 “Use as a rough indicator of model training progress/convergence for balanced datasets.” 배치 크기 “Full batch, in which the batch size is the number of examples in the entire training set.” Learning rate “If you set the learning rate too low, training will take too long.” Hyperparameter “You could set the learning rate to 0.01 before one training session.” Parameter (machine learning) “For example, learning rate is a hyperparameter.”