In information theory , a description of how unpredictable a probability distribution is. Alternatively, entropy is also defined as how much information each example contains. A distribution has the highest possible entropy when all values of a random variable are equally likely.1
ToDo : 더 정리하기
목차 목차 관련 글 What 'Out-of-distribution' Is and Is Not “Researchers want to generalize robustly to 'out-of-distribution' (OOD) data.” ML crash course - Linear regression “In algebraic terms, the model would be defined as , where” Introduction to Machine Learning 관련 절: Definition of [[Machine learning|ML]] Machine Learning Systems “Machine Learning Systems provides a systematic framework for understanding and engineering machine learning (ML…” Recall (machine learning) 관련 절: See also Clipping (machine learning) “For example, suppose that <0.5% of values for a particular feature fall outside the range 40–60.” 기계학습 관련 절: Generalization and OOD Epoch (machine learning) “A full training pass over the entire training set such that each example has been processed once.” Downsampling (machine learning) “Reducing the amount of information in a feature in order to train a model more efficiently.” Self-training (machine learning) “A variant of self-supervised learning that is particularly useful when all of the following conditions are true:” 모델 (기계학습) “Unsupervised machine learning also generates models, typically a function that can map an input example to the …” Generalization (machine learning) “A model that can generalize is the opposite of a model that is overfitting.” Iteration (machine learning) “For instance, if the batch size is 20, then the model processes 20 examples before adjusting the parameters.” 지도 학습 “Supervised machine learning is analogous to learning a subject by studying a set of questions and their corresp…” Minority class (machine learning) “For example, given a dataset containing 99% negative labels and 1% positive labels, the positive labels are the…” Interpretability (machine learning) “Most linear regression models, for example, are highly interpretable.”