Machine Learning Methods with Noisy, Incomplete or Small Datasets

• その他の著者: Solé-Casals, Jordi (編集者), Sun, Zhe (編集者), Caiafa, Cesar F. (編集者), Marti-Puig, Pere (編集者), Tanaka, Toshihisa (編集者)
• フォーマット: 電子媒体 図書の章
• 言語: 英語
• 出版事項: Basel, Switzerland MDPI - Multidisciplinary Digital Publishing Institute 2021
• 主題: Information technology industries; open contours; similarly shaped fish species; Discrete Cosine Transform (DCT); Discrete Fourier Transform (DFT); Extreme Learning Machines (ELM); feature engineering; small data-sets; optimization; machine learning; preprocessing; image generation; weighted interpolation map; binarization; single sample per person; root canal measurement; multifrequency impedance; data augmentation; neural network; functional magnetic resonance imaging; independent component analysis; deep learning; recurrent neural network; functional connectivity; episodic memory; small sample learning; feature selection; noise elimination; space consistency; label correlations; empirical mode decomposition; sparse representations; tensor decomposition; tensor completion; machine translation; pairwise evaluation; educational data; small datasets; noisy datasets; smart building; Internet of Things (IoT); Markov Chain Monte Carlo (MCMC); ontology; graph model; Artificial Neural Network; Discriminant Analysis; dengue; feature extraction; sound event detection; non-negative matrix factorization; ultrasound images; shadow detection; shadow estimation; auto-encoders; semi-supervised learning; prediction; feature importance; feature elimination; hierarchical clustering; Parkinson's disease; few-shot learning; permutation-variable importance; topological data analysis; persistent entropy; support-vector machine; data science; intelligent decision support; social vulnerability; gender-gap; digital-gap; COVID19; policy-making support; artificial intelligence; imperfect dataset
• オンライン･アクセス: DOAB: download the publication; DOAB: description of the publication

In many machine learning applications, available datasets are sometimes incomplete, noisy or affected by artifacts. In supervised scenarios, it could happen that label information has low quality, which might include unbalanced training sets, noisy labels and other problems. Moreover, in practice, i...