ScholarGate

探索

文库我的文库桌面预检 Review Studio 助手

工作区

打造您的书架

保存方法、整理合集，并将它们带到您的桌面。

文库 / 浏览

方法库

按方法、领域与证据探索科学。

一个汇集研究方法的目录——了解每种方法如何运作、何时使用以及它做不到什么。

6,575 方法11 领域7 方法家族40 语言

科学图谱在使用之前，先绘制科学的结构图。领域 · 方法 · 证据路径探索图谱

领域Health & Medicine716 Psychology570 Business & Finance410 Engineering330 Life Sciences263 Education261 Research Practice248 Natural Sciences

以内容为本的研究方法参考文库——每种方法是什么、如何运作、源自何处。

开放数据（CC-BY）

探索

文库
搜索方法…
按领域浏览
学科领域
历程
对比
该用哪种方法？

参考

学科
图集
术语表
方法论
哲学

工作区

我的文库
桌面
聊天

公司

关于
价格
联系我们
建议新方法

本词条系根据已发表文献整理，仅供参考。核实任何信息的准确性及其是否适用于您的具体用途，仍由您自行负责。

© 2026 ScholarGate · 研究方法参考文库

隐私
Cookie
条款
删除账户

236

Social Sciences185

Environment & Sustainability160

方法统计学1,836 人工智能与机器学习1,661 决策科学932 研究方法1,354 测量1,745 因果与证据532 研究实践118

1,522 种方法 · 人工智能与机器学习清除

与筛选条件匹配的真实方法。

排序热门程度 A–Z Z–A 最新

Seakeeping Strip Theory

Seakeeping strip theory is a method for predicting the dynamic motion of a ship in regular and irregular waves by decomposing the hull into two-dimensional transverse sections (strips) and computing the hydrodynamic forces on each strip. Developed by Salvesen, Tuck, and Faltinsen in 1970, the method efficiently estimat

3 个来源1970

Secure Multi-Party Computation

Secure Multi-Party Computation (SMPC) is a cryptographic paradigm that enables two or more parties to jointly compute a function over their private inputs without revealing those inputs to one another. Introduced by Andrew Yao in 1982 through his seminal garbled-circuit construction, SMPC provides provable privacy guar

1 个来源1982

SED Fitting

Spectral Energy Distribution (SED) fitting is the technique of comparing observed photometric measurements of galaxies across many wavelengths against theoretical predictions from stellar population synthesis models. By fitting models to observations, astronomers estimate galaxy properties including redshift, mass, age

3 个来源2003

Segment Anything Model

Segment Anything Model (SAM) is a foundation model introduced by Kirillov et al. in 2023 that can segment any object in an image given various forms of prompts. SAM is trained on a massive dataset of diverse images and learns to segment objects based on minimal user input such as points, boxes, or text descriptions.

1 个来源2023

SegRNN

SegRNN is a recurrent neural network architecture for long-term time series forecasting proposed by Shengsheng Lin et al. in 2023. Instead of processing one time step at a time, SegRNN partitions input sequences into fixed-length segments and feeds each segment as a single token into a GRU. This segment-based design dr

1 个来源2023

Seismic Full-Waveform Inversion

Seismic Full-Waveform Inversion (FWI) is a computational technique that reconstructs detailed subsurface velocity and impedance models by iteratively fitting synthetic seismic waveforms to observed data. Introduced by Albert Tarantola in 1984, FWI has become the leading method for high-resolution imaging in exploration

2 个来源1984

materials science

Selected Area Electron Diffraction

Selected Area Electron Diffraction (SAED) is a crystallographic technique in transmission electron microscopy that obtains electron diffraction patterns from micron-sized or sub-micron crystalline regions. Developed from fundamental principles of electron wave behavior and integrated into TEM instruments by the mid-20t

3 个来源1913

Selection Sweep (Tajima's D)

Tajima's D is a statistical test designed to detect selective sweeps—recent, rapid fixation of advantageous mutations—from patterns of genetic variation in DNA sequences. Developed by Fumio Tajima in 1989, this test measures deviations from neutrality by comparing different measures of DNA sequence diversity. A signifi

3 个来源1989

Self-Attention

Multi-head self-attention, introduced by Vaswani and colleagues in 2017, is the mechanism that lets every position in a sequence compute its relationship to all other positions in parallel. It is the core of the Transformer architecture and the foundation underneath BERT, GPT, and T5.

2 个来源2017

complex systems

Self-Organized Criticality

Self-Organized Criticality (SOC) is a dynamical systems framework introduced by Per Bak, Chao Tang, and Kurt Wiesenfeld in 1987 to explain how large, dissipative systems spontaneously evolve toward a critical state without external fine-tuning. At the critical state, the system produces scale-invariant fluctuations — a

1 个来源1987

machine learning

Self-Organizing Map

A self-organizing map is an unsupervised neural network, introduced by Teuvo Kohonen in 1982, that projects high-dimensional data onto a low-dimensional (usually two-dimensional) grid of prototype vectors while preserving the data's topology — nearby inputs map to nearby grid cells. It is used for visualization, cluste

2 个来源1982

machine learning

Self-supervised Active Learning

Self-supervised Active Learning (SSL-AL) is a label-efficient machine-learning paradigm that pre-trains a model on unlabeled data using self-supervised objectives, then strategically queries a human oracle for the most informative labels using an active-learning acquisition function. The result is strong predictive per

2 个来源2020

machine learning

Self-supervised Autoencoder Anomaly Detection

Self-supervised autoencoder anomaly detection trains an autoencoder using self-supervised pretext tasks — such as predicting geometric transformations or solving jigsaw puzzles — on unlabeled normal data, then flags as anomalous any input whose reconstruction error or pretext-task score deviates substantially from the

2 个来源2018

Self-supervised BERT-based classification

Self-supervised BERT-based classification uses Google's Bidirectional Encoder Representations from Transformers (BERT), pretrained on massive unlabelled text via masked-language modelling, and fine-tunes it on labelled examples to assign text into categories. It consistently achieves state-of-the-art accuracy on sentim

2 个来源2019

machine learning

Self-supervised Boosting

Self-supervised boosting integrates self-supervised pretext tasks into the boosting framework — covering AdaBoost, gradient boosting, and their modern variants — to leverage large pools of unlabeled data. By first learning feature representations from unlabeled samples and then running sequential weak-learner ensembles

2 个来源2010

Self-supervised convolutional neural network

A self-supervised convolutional neural network (CNN) learns powerful visual representations from unlabeled images by solving pretext tasks — such as contrastive instance discrimination or masked-patch prediction — and then fine-tunes on a small labeled set. This approach dramatically reduces dependence on large annotat

2 个来源2018

machine learning

Self-supervised DBSCAN

Self-supervised DBSCAN is a two-stage unsupervised pipeline that first trains a neural encoder on a pretext task — such as contrastive learning or masked reconstruction — to produce compact, semantically meaningful embeddings from unlabeled data, and then applies DBSCAN in the resulting embedding space to discover arbi

2 个来源2018

machine learning

Self-supervised Decision Tree

Self-supervised Decision Tree learning combines the interpretability of classical decision trees with the ability to exploit large quantities of unlabeled data through self-supervised pretext tasks. The model learns useful feature representations or node-split criteria from unlabeled samples before refining predictions

2 个来源2015

Self-supervised Diffusion Model

A self-supervised diffusion model couples the iterative noise-and-denoise generative process of denoising diffusion probabilistic models with a self-supervised representation learning objective — such as contrastive or masked prediction loss — so that the model simultaneously learns to generate realistic data and to pr

2 个来源2020

machine learning

Self-supervised Federated learning

Self-supervised Federated Learning combines federated training — where data never leaves local devices — with self-supervised pretext tasks such as contrastive learning or masked prediction. Clients learn general-purpose representations from their own unlabeled data and share only model updates, not raw data, with a ce

2 个来源2021

machine learning

Self-supervised Few-shot Learning

Self-supervised Few-shot Learning (SSL-FSL) combines self-supervised pretraining on large unlabeled corpora with few-shot meta-learning so that a model can recognize new categories from only a handful of labeled examples. By learning rich, transferable representations without expensive annotation, SSL-FSL addresses the

2 个来源2019

Self-supervised GAN

Self-supervised GAN augments a standard Generative Adversarial Network with one or more self-supervised auxiliary tasks — such as predicting image rotation or patch position — that stabilise adversarial training and yield a discriminator that learns rich, transferable representations from unlabeled data without requiri

2 个来源2019

machine learning

Self-supervised Gaussian Mixture Model

A Self-supervised Gaussian Mixture Model (SS-GMM) combines self-supervised representation learning with a probabilistic Gaussian mixture prior to discover meaningful clusters in unlabeled or partially labeled data. By leveraging pretext tasks to learn rich embeddings before fitting a GMM, it achieves cluster quality th

2 个来源2010

machine learning

Self-supervised Gaussian Process

Self-supervised Gaussian Process (SSL-GP) combines the principled uncertainty quantification of Gaussian processes with self-supervised pretraining, learning expressive kernels or latent representations from unlabeled data before fitting a GP on a small labeled set. This makes the approach especially powerful in low-la

2 个来源2019

machine learning

Self-supervised Gradient Boosting

Self-supervised gradient boosting extends the classic gradient boosting framework by incorporating self-supervised pretext tasks to exploit unlabeled data. The model first learns useful feature representations from unannotated samples, then uses those representations to guide the sequential ensemble of weak learners, a

2 个来源2020

Self-supervised GRU

Self-supervised GRU trains a Gated Recurrent Unit network using automatically constructed supervision signals — such as next-step prediction or masked token recovery — derived from the unlabeled data itself. The learned sequence representations are then fine-tuned on small labeled datasets, making high-quality sequenti

2 个来源2014

Self-supervised Image Classification

Self-supervised image classification trains a deep visual encoder on large unlabeled image datasets by solving proxy tasks — such as predicting which two augmented views of the same image are similar — and then fine-tunes only a lightweight classifier head on labeled examples. Pioneered by frameworks such as SimCLR and

2 个来源2018

Self-supervised Instance Segmentation

Self-supervised instance segmentation learns to detect and delineate individual object instances in images without any human-annotated masks or bounding boxes. Instead of relying on costly pixel-level labels, it exploits self-supervised pretraining, multi-view consistency, and pseudo-label generation to discover and se

2 个来源2021

machine learning

Self-supervised Isolation Forest

Self-supervised Isolation Forest augments the classic Isolation Forest anomaly detector with a self-supervised pre-training stage. A pretext task — such as predicting rotation, masked features, or contrastive pairs — is solved without labels to learn a richer feature representation, which is then used when building the

2 个来源2008

machine learning

Self-supervised K-means

Self-supervised K-means is a clustering technique that combines K-means assignment with self-supervised representation learning. The model alternates between clustering unlabeled data points into K groups and using those cluster assignments as pseudo-labels to refine an underlying feature representation, yielding incre

2 个来源2018

machine learning

Self-supervised K-nearest neighbors

Self-supervised K-nearest neighbors (SSL-kNN) combines representation learning without labels with a non-parametric k-NN classifier. A neural encoder is first trained via a self-supervised objective — such as contrastive or masked prediction — so that semantically similar samples cluster together in the embedding space

2 个来源2018

Self-supervised LDA Topic Model

Self-supervised LDA combines the probabilistic generative framework of Latent Dirichlet Allocation with self-supervised pretraining signals — such as masked-word prediction or contrastive document objectives — to guide topic discovery without requiring hand-labeled training data. The result is topic representations tha

2 个来源2003

machine learning

Self-supervised Learning

Self-supervised learning (SSL) is a machine-learning paradigm that generates its own supervisory signal directly from unlabeled data by defining an auxiliary pretext task — such as predicting masked words, rotating images, or contrasting augmented views — and uses the learned representations as a powerful starting poin

2 个来源2018

machine learning

Self-supervised LightGBM

Self-supervised LightGBM combines the self-supervised learning paradigm with the LightGBM gradient boosting framework to exploit large volumes of unlabeled tabular data. A self-supervised pretext task — such as masked feature prediction or contrastive corruption — generates rich feature representations or pseudo-labels

2 个来源2017

machine learning

Self-supervised Metric learning

Self-supervised metric learning trains a neural encoder to embed inputs so that semantically similar items lie close together in vector space, using automatically generated pseudo-labels instead of human annotations. By combining self-supervised pretext tasks with contrastive or triplet-based metric objectives, it prod

2 个来源2020

Self-supervised named entity recognition

Self-supervised named entity recognition (NER) combines large-scale self-supervised pretraining — such as masked language modeling — with token-level fine-tuning to identify and classify named entities in text. By learning general linguistic representations before seeing any entity labels, the model achieves strong per

2 个来源2018

Self-supervised NMF Topic Model

The Self-supervised NMF Topic Model extends classical Non-negative Matrix Factorization for topic discovery by incorporating self-supervised learning signals — such as masked-word reconstruction or contrastive objectives — into the NMF optimization, yielding more coherent and semantically meaningful topics from text co

2 个来源2020

Self-supervised Object Detection

Self-supervised object detection uses unlabeled image data to pre-train a visual backbone through pretext tasks such as contrastive learning or masked image modeling, then fine-tunes the backbone with a detection head on a smaller labeled dataset. This approach dramatically reduces reliance on expensive bounding-box an

2 个来源2019

machine learning

Self-supervised One-class SVM

Self-supervised One-class SVM combines pretext-task-based representation learning with One-class SVM to detect anomalies and novelties without requiring labeled anomaly examples. The model first learns expressive feature embeddings from normal data alone, then fits an OC-SVM boundary in the learned feature space to fla

2 个来源2018

Self-supervised Question Answering

Self-supervised Question Answering (SSQA) is a training paradigm that automatically generates question-answer pairs from unlabeled text — using cloze translation, span masking, or neural question generation — to train QA models without any human-labeled data. It enables high-quality reading comprehension systems even w

2 个来源2019

machine learning

Self-supervised Random Forest

Self-supervised Random Forest (SSL-RF) extends the classic random forest to settings where labeled examples are scarce. The forest is first trained using automatically generated pseudo-labels derived from a self-supervised pretext task — such as predicting data transformations or masked features — and then refined on w

2 个来源2012

Self-supervised Reinforcement Learning

Self-supervised Reinforcement Learning (SSL-RL) augments standard RL training with self-supervised auxiliary objectives — such as contrastive, predictive, or data-augmentation-based tasks — applied to the agent's own experience. These objectives improve the quality of learned representations without requiring extra hum

2 个来源2020

Self-supervised RoBERTa-based classification

Self-supervised RoBERTa-based classification combines the RoBERTa transformer's powerful language representations — learned from large unlabeled corpora through masked-language modeling — with self-supervised objectives to perform text classification with little or no human-labeled data. The approach leverages abundant

2 个来源2019

Self-supervised Semantic Segmentation

Self-supervised semantic segmentation learns to assign a class label to every pixel of an image without relying on manually annotated segmentation masks. A backbone network is first trained on large quantities of unlabeled images using self-supervised objectives such as contrastive learning or masked image modeling, an

2 个来源2020

Self-supervised Sentence Embeddings

Self-supervised sentence embeddings train a neural encoder to map sentences into a dense vector space without requiring manually labeled pairs. By constructing positive examples automatically — for instance by passing the same sentence through dropout twice — and using contrastive objectives, the model learns semantica

2 个来源2019

Self-supervised Sentiment Analysis

Self-supervised sentiment analysis combines large-scale unsupervised pre-training — through objectives such as masked language modeling or contrastive prediction — with fine-tuning on a small labeled sentiment corpus. The approach, popularized by BERT and its variants, dramatically reduces the need for hand-labeled dat

2 个来源2019

machine learning

Self-supervised Stacking Ensemble

Self-supervised Stacking Ensemble combines stacked generalization — the classic two-level ensemble architecture introduced by Wolpert (1992) — with self-supervised pretraining, allowing base models to learn rich representations from unlabeled data before being fine-tuned and stacked. This hybrid strategy is especially

2 个来源1992

machine learning

Self-supervised Support Vector Machine

A Self-supervised Support Vector Machine combines self-supervised pretraining — learning representations from unlabeled data via pretext tasks — with a Support Vector Machine classifier trained on the resulting features. This hybrid approach enables strong classification performance even when labeled data is scarce, by

2 个来源2019

Self-supervised topic modeling

Self-supervised topic modeling combines the interpretable topic discovery of classical topic models with self-supervised learning objectives — such as contrastive loss, masked language modeling, or reconstruction — to learn coherent, semantically rich topics from unlabeled text without human-annotated labels. It bridge

2 个来源2020

machine learning

Self-supervised Transfer learning

Self-supervised transfer learning combines two powerful paradigms: a model first learns rich representations from unlabeled data using self-supervised pretext tasks, then those learned representations are transferred and fine-tuned on a downstream task with limited labeled data. This approach underlies landmark systems

2 个来源2018

Self-supervised Transformer

A self-supervised Transformer is a Transformer network pretrained using automatically constructed supervision signals — such as masked token prediction or next-sentence prediction — rather than human-annotated labels. The resulting representations are then fine-tuned or probed on downstream tasks. BERT, GPT, and ViT (V

2 个来源2017

Self-supervised Variational Autoencoder

A Self-supervised Variational Autoencoder (SS-VAE) combines the generative latent-space learning of a standard VAE with self-supervised pretext tasks — such as contrastive augmentation, masked reconstruction, or rotation prediction — to learn richer, more disentangled representations from unlabeled data without any man

2 个来源2014

Self-supervised Vision Transformer

Self-supervised Vision Transformer (SSL-ViT) applies self-supervised pre-training objectives — such as masked patch prediction (MAE) or self-distillation with no labels (DINO) — to the Vision Transformer architecture, enabling powerful visual representations to be learned from large unlabeled image corpora before any t

2 个来源2021

Self-supervised Word2Vec

Word2Vec is a shallow neural network model introduced by Mikolov et al. (2013) that learns dense vector representations of words from large unlabeled text corpora using self-supervised objectives. By training a model to predict surrounding context words (Skip-gram) or a target word from its context (CBOW), it captures

2 个来源2013

Semantic Feature Analysis

Semantic Feature Analysis, or Componential Analysis, is a method for understanding word meaning by decomposing concepts into minimal meaningful units called semantic features or components. Developed by Ward Goodenough in 1956, this approach represents the meaning of words as bundles of features (e.g., 'woman' = [human

3 个来源1956

Semantic Parsing

Semantic parsing is a natural-language-processing task that converts free-text utterances into executable formal representations such as SQL queries, logical forms, or Abstract Meaning Representations (AMR). Established in its supervised learning form by Zelle and Mooney in 1996 and scaled to cross-domain settings by t

2 个来源1996

Semantic Role Labeling

Semantic role labeling, introduced by Gildea and Jurafsky in 2002, is a natural-language-processing task that assigns semantic roles — who did what to whom, where, when, and how — to the components around a verb (predicate) in a sentence. It turns plain text into structured predicate-argument representations and is a f

2 个来源2002

Semantic Segmentation

Semantic segmentation assigns a class label to every pixel in an image, producing a dense, category-annotated map of the scene. Unlike object detection, which draws bounding boxes, it delineates the exact spatial extent of each class, making it indispensable in medical imaging, autonomous driving, satellite analysis, a

2 个来源2015

Semantic Similarity

Semantic similarity analysis measures how close in meaning two texts are, rather than how many words they share on the surface. Building on the Sentence-BERT work of Reimers and Gurevych (2019), it represents each text as a vector and compares those vectors so that paraphrases score high even when their wording differs

2 个来源2019

machine learning

Semi-supervised Active Learning

Semi-supervised Active Learning (SSAL) is a hybrid learning paradigm that combines active learning's selective query strategy with semi-supervised learning's ability to exploit unlabeled data. The model iteratively selects the most informative unlabeled instances for expert annotation while simultaneously leveraging th

2 个来源2002

← 1819 / 2620 →