목차
(In Machine learning ) 온라인 러닝
“
An algorithm is an online learning algorithm if it can not only process data one piece at a time, but can also provide provisional results of its analysis after each piece of data is seen. —Bandit algorithms for website optimization
목차 관련 글 Nested Learning: The Illusion of Deep Learning Architectures “Over the last decades, developing more powerful neural architectures and simultaneously designing optimization …” 경험 기계: 마음은 어떻게 현실을 예측하고 조각하는가 이 글을 인용: “(기계 학습의 Online learning과 Active learning을 합쳐놓은 느낌. --ak)” Introduction to machine learning problem framing “Introduction to Machine Learning Problem Framing is a course provided by Google.” Machine Learning Systems “Unlike resources that focus primarily on algorithms and model architectures, this book highlights the broader c…” Introduction to Machine Learning 관련 절: Definition of [[Machine learning|ML]] ML crash course - Linear regression “In an ML context, linear regression finds the relationship between features and a label.” 액티브 러닝 “Most traditional machine learning algorithm are not active: they passively accept the data we feed them and do …” Self-training (machine learning) “A variant of self-supervised learning that is particularly useful when all of the following conditions are true:” 지도 학습 “Supervised machine learning is analogous to learning a subject by studying a set of questions and their corresp…” Learning rate “For example, a learning rate of 0.3 would adjust weights and biases three times more powerfully than a learning…” Epoch (machine learning) “An epoch represents N/batch size training iterations, where N is the total number of examples.” Iteration (machine learning) “For instance, if the batch size is 20, then the model processes 20 examples before adjusting the parameters.” Generalization (machine learning) “A model's ability to make correct predictions on new, previously unseen data.” Downsampling (machine learning) “For example, before training an image recognition model, downsampling high-resolution images to a lower-resolut…” 모델 (기계학습) “Unsupervised machine learning also generates models, typically a function that can map an input example to the …” Convex optimization “A great deal of research in machine learning has focused on formulating various problems as convex optimization…” Semi-supervised learning “Self-training is one technique for semi-supervised learning.” Example (machine learning) “The row of a dataset is typically the raw source for an example.” Interpretability (machine learning) “(You merely need to look at the trained weights for each feature.)” Parameter (machine learning) “For example, learning rate is a hyperparameter.”