Джерела

Кожне пояснювальне твердження на цьому сайті має посилання на джерело, і збірка відмовляється публікувати сторінку, що порушує правила нижче. Ця сторінка існує, щоб ви могли перевірити це самі, а не вірити на слово.

Збірка падає, якщо

• посилання вказує на джерело, яке не було оголошене
• оголошене джерело жодного разу не процитоване — жодних декоративних бібліографій
• джерело розміщене на хості, якого немає в списку нижче
• нечернеткова сторінка має менше ніж два джерела
• джерело-документація не має дати звірки, бо сторінки документації змінюються

Що вважається джерелом

Що не вважається

Перелічено явно, щоб правило ніколи не було справою смаку.

• medium.comAnyone can publish; no review, no stable authorship.
• towardsdatascience.comMedium publication — same problem, plus frequent factual errors.
• geeksforgeeks.orgContent farm; known to paraphrase textbooks inaccurately.
• w3schools.comTutorial site, not a specification or reference.
• tutorialspoint.comContent farm.
• javatpoint.comContent farm.
• stackoverflow.comFine as a 'see also', never as the authority for a claim.
• quora.comUnreviewed user answers.
• wikipedia.orgUse it to FIND the primary source, then cite that source directly.
• chat.openai.comLanguage model output is not a source.
• claude.aiLanguage model output is not a source.

Використані джерела (223)

Без повторів по всіх сторінках, із зазначенням, що на них посилається.

1. A Call for Clarity in Reporting BLEU Scores — Post (2018)paperЦитують: BLEU, Text metrics
2. A Random Forest Guided Tour — Biau, Scornet (2015)paperЦитують: Feature importance, Random forest
3. A Simple Framework for Contrastive Learning of Visual Representations — Chen, Kornblith, Norouzi, Hinton (2020)paperЦитують: Self-supervised learning
4. A systematic study of the class imbalance problem in convolutional neural networks — Buda, Maki, Mazurowski (2018)paperЦитують: Class imbalance
5. A Tutorial on Principal Component Analysis — Shlens (2014)paperЦитують: Eigenvectors and eigenvalues, PCA
6. Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour — Goyal, Dollár, Girshick, Noordhuis, Wesolowski, Kyrola, Tulloch, Jia, He (2017)paperЦитують: Mini-batch gradient descent
7. Adam: A Method for Stochastic Optimization — Kingma, Ba (2014)paperЦитують: Adam
8. ALBERT: A Lite BERT for Self-supervised Learning of Language Representations — Lan, Chen, Goodman, Gimpel, Sharma, Soricut (2019)paperЦитують: Transformer family
9. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale — Dosovitskiy, Beyer, Kolesnikov, Weissenborn, Zhai, Unterthiner, et al. (2021)paperЦитують: CLIP, Vision transformer, Transformer family
10. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale — Dosovitskiy et al. (2020)paperЦитують: Computer vision architectures
11. Are we done with ImageNet? — Beyer, Hénaff, Kolesnikov, Zhai, van den Oord (2020)paperЦитують: Image classification
12. Attention Is All You Need — Vaswani, Shazeer, Parmar, Uszkoreit, Jones, Gomez, Kaiser, Polosukhin (2017)paperЦитують: Attention, Natural language processing, Transformer
13. Attention is not Explanation — Jain, Wallace (2019)paperЦитують: Attention
14. Automatic Differentiation in Machine Learning: a Survey — Baydin, Pearlmutter, Radul, Siskind (2018)paperЦитують: Backpropagation
15. average_precision_score — scikit-learn developersdocsЦитують: Mean average precision
16. Baselines and Bigrams: Simple, Good Sentiment and Topic Classification — Wang, Manning (2012)paperЦитують: Bag of words
17. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift — Ioffe, Szegedy (2015)paperЦитують: Batch normalization
18. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding — Devlin, Chang, Lee, Toutanova (2019)paperЦитують: BERT, Named entity recognition, Natural language processing, Transformer family
19. BERTScore: Evaluating Text Generation with BERT — Zhang, Kishore, Wu, Weinberger, Artzi (2020)paperЦитують: BLEU, Text metrics
20. Chain-of-Thought Prompting Elicits Reasoning in Large Language Models — Wei, Wang, Schuurmans, Bosma, Ichter, Xia, Chi, Le, Zhou (2022)paperЦитують: Prompting
21. Computational reproducibility of Jupyter notebooks from biomedical publications — Samuel, Mietchen (2023)paperЦитують: Jupyter Notebook
22. Cross-validation: what does it estimate and how well does it do it? — Bates, Hastie, Tibshirani (2023)paperЦитують: Cross-validation, Validation strategies
23. Cyclical Learning Rates for Training Neural Networks — Leslie N. Smith (2017)paperЦитують: Learning rate
24. Deconvolution and Checkerboard Artifacts — Odena, Dumoulin, Olah (2016)paperЦитують: Transposed convolution
25. Decoupled Weight Decay Regularization — Loshchilov, Hutter (2019)paperЦитують: Adam
26. Deep Learning — Goodfellow, Bengio, Courville (2016)bookЦитують: Adam, BFGS, Conjugate gradient, Mini-batch gradient descent, SGD
27. Deep Learning — Goodfellow, Bengio, Courville (2016)bookЦитують: Bagging, Dropout, Early stopping, Elastic Net, Lasso regression, Regularization, Ridge regression, Linear model family
28. Deep Learning — Goodfellow, Bengio, Courville (2016)bookЦитують: Bayesian linear regression, Data augmentation, Eigenvectors and eigenvalues, Gradient, Gradient descent, Learning rate, Linear regression, Logistic regression, MAE, MSLE, Perceptron, Polynomial regression, ReLU, Softmax, Tanh, Сигмоїда, Activation functions, Computer vision architectures, Optimizers
29. Deep Learning — Goodfellow, Bengio, CourvillebookЦитують: Convolutional neural network
30. Deep Learning — Goodfellow, Bengio, Courville (2016)bookЦитують: Decision tree, KNN, SVM
31. Deep Learning — Goodfellow, Bengio, Courville (2016)bookЦитують: Leaky ReLU, Regression metrics
32. Deep Learning — Sequence Modeling, chapter 10 — Goodfellow, Bengio, CourvillebookЦитують: Recurrent neural network
33. Deep Residual Learning for Image Recognition — He, Zhang, Ren, Sun (2015)paperЦитують: Batch normalization, Convolutional neural network, Transfer learning, Computer vision architectures
34. Deep Residual Learning for Image Recognition — He, Zhang, Ren, Sun (2015)paperЦитують: Residual connection
35. Deep Sets — Zaheer, Kottur, Ravanbakhsh, Poczos, Salakhutdinov, Smola (2017)paperЦитують: PointNet
36. Deep Sparse Rectifier Neural Networks — Glorot, Bordes, Bengio (2011)paperЦитують: ReLU
37. Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification — He, Zhang, Ren, Sun (2015)paperЦитують: Leaky ReLU
38. Demystifying MMD GANs — Bińkowski, Sutherland, Arbel, Gretton (2018)paperЦитують: Fréchet Inception Distance
39. Denoising Diffusion Probabilistic Models — Ho, Jain, Abbeel (2020)paperЦитують: Diffusion model, Fréchet Inception Distance, Generative adversarial network, Vision tasks
40. DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter — Sanh, Debut, Chaumond, Wolf (2019)paperЦитують: Transformer family
41. Dive into Deep Learning — Zhang, Lipton, Li, SmolabookЦитують: Adam, Attention, BERT, Convolution, Convolutional neural network, Data augmentation, Feature engineering, Gradient, Gradient descent, Leaky ReLU, Mini-batch gradient descent, Natural language processing, Overfitting, Pooling, Receptive field, ReLU, SGD, Tanh, Tokenization, Transfer learning, Transformer, Word embeddings, Сигмоїда, Activation functions, Optimizers
42. Dive into Deep Learning — Zhang, Lipton, Li, SmolabookЦитують: Backpropagation
43. Dive into Deep Learning — Zhang, Lipton, Li, SmolabookЦитують: Batch normalization
44. Dive into Deep Learning — Zhang, Lipton, Li, SmolabookЦитують: Bayes' theorem
45. Dive into Deep Learning — Zhang, Lipton, Li, SmolabookЦитують: Decoding
46. Dive into Deep Learning — Zhang, Lipton, Li, SmolabookЦитують: Eigenvectors and eigenvalues
47. Dive into Deep Learning — Zhang, Lipton, Li, SmolabookЦитують: Expectation and variance
48. Dive into Deep Learning — Zhang, Lipton, Li, SmolabookЦитують: Language model, Perplexity
49. Dive into Deep Learning — Zhang, Lipton, Li, SmolabookЦитують: Maximum likelihood
50. Dive into Deep Learning — Zhang, Lipton, Li, SmolabookЦитують: Recurrent neural network
51. Dive into Deep Learning — 12.3 Gradient Descent — Zhang, Lipton, Li, SmolabookЦитують: Learning rate
52. Dive into Deep Learning — 2.6 Probability and Statistics — Zhang, Lipton, Li, SmolabookЦитують: Bayes' theorem
53. Dive into Deep Learning — 3.1 Linear Regression — Zhang, Lipton, Li, SmolabookЦитують: Huber loss, Linear regression, MAE, MSE, RMSE
54. Dive into Deep Learning — 3.6 Generalization — Zhang, Lipton, Li, SmolabookЦитують: MSE, R², Train-test split
55. Dive into Deep Learning — 4.1 Softmax Regression — Zhang, Lipton, Li, SmolabookЦитують: Softmax
56. Dive into Deep Learning — Anchor Boxes — Zhang, Lipton, Li, SmolabookЦитують: Intersection over union, Mean average precision, Object detection
57. Dive into Deep Learning — Attention Pooling by Similarity — Zhang, Lipton, Li, SmolabookЦитують: Distance-weighted KNN
58. Dive into Deep Learning — Backpropagation Through Time — Zhang, Lipton, Li, SmolabookЦитують: Recurrent neural network
59. Dive into Deep Learning — Computer Vision — Zhang, Lipton, Li, SmolabookЦитують: Image classification, Vision tasks
60. Dive into Deep Learning — Dropout — Zhang, Lipton, Li, SmolabookЦитують: Dropout
61. Dive into Deep Learning — Fully Convolutional Networks — Zhang, Lipton, Li, SmolabookЦитують: Semantic segmentation
62. Dive into Deep Learning — Generalization in Deep Learning — Zhang, Lipton, Li, SmolabookЦитують: Early stopping
63. Dive into Deep Learning — Information Theory — Zhang, Lipton, Li, SmolabookЦитують: Cross-entropy, Entropy, Classification metrics
64. Dive into Deep Learning — Learning Rate Scheduling — Zhang, Lipton, Li, SmolabookЦитують: Early stopping
65. Dive into Deep Learning — Multiple Input and Multiple Output Channels — Zhang, Lipton, Li, SmolabookЦитують: Depthwise separable convolution
66. Dive into Deep Learning — Natural Language Processing: Applications — Zhang, Lipton, Li, SmolabookЦитують: NLP tasks
67. Dive into Deep Learning — Semantic Segmentation — Zhang, Lipton, Li, SmolabookЦитують: Semantic segmentation
68. Dive into Deep Learning — Sequence-to-Sequence Learning — Zhang, Lipton, Li, SmolabookЦитують: BLEU, Sequence-to-sequence, Text metrics
69. Dive into Deep Learning — Transformers for Vision — Zhang, Lipton, Li, SmolabookЦитують: Vision transformer
70. Dive into Deep Learning — Transposed Convolution — Zhang, Lipton, Li, SmolabookЦитують: Transposed convolution
71. Do Better ImageNet Models Transfer Better? — Kornblith, Shlens, Le (2019)paperЦитують: Transfer learning
72. Domain Adaptive Transfer Learning with Specialist Models — Ngiam, Peng, Vasudevan, Kornblith, Le, Pang (2018)paperЦитують: Transfer learning
73. e-Handbook of Statistical Methods — 1.3.3.1 Autocorrelation Plot — NIST/SEMATECHstandardЦитують: Autocorrelation
74. e-Handbook of Statistical Methods — 1.3.3.26 Scatter Plot — NIST/SEMATECHstandardЦитують: Correlation
75. e-Handbook of Statistical Methods — 1.3.5.17 Detection of Outliers — NIST/SEMATECHstandardЦитують: Huber loss, Outliers
76. e-Handbook of Statistical Methods — 1.3.6.6.3 Cauchy Distribution — NIST/SEMATECHstandardЦитують: Expectation and variance
77. e-Handbook of Statistical Methods — 4.1.4.1 Linear Least Squares Regression — NIST/SEMATECHstandardЦитують: Linear regression, Outliers
78. e-Handbook of Statistical Methods — 4.2.1 Typical underlying assumptions in process modeling — NIST/SEMATECHstandardЦитують: Linear regression
79. e-Handbook of Statistical Methods — 4.4.4 How can I tell if a model fits my data? — NIST/SEMATECHstandardЦитують: R²
80. e-Handbook of Statistical Methods — 6.4.4.6 Box-Jenkins Model Identification — NIST/SEMATECHstandardЦитують: Autocorrelation, Stationarity
81. Effectively Unbiased FID and Inception Score and where to find them — Chong, Forsyth (2020)paperЦитують: Fréchet Inception Distance
82. Efficient BackProp — LeCun, Bottou, Orr, Müller (1998)paperЦитують: Tanh, Сигмоїда
83. Efficient Estimation of Word Representations in Vector Space — Mikolov, Chen, Corrado, Dean (2013)paperЦитують: Word embeddings
84. ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators — Clark, Luong, Le, Manning (2020)paperЦитують: Transformer family
85. Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer — Raffel, Shazeer, Roberts, Lee, Narang, Matena, Zhou, Li, Liu (2020)paperЦитують: Transformer family
86. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks — Ren, He, Girshick, Sun (2016)paperЦитують: Mean average precision, Object detection
87. Finetuned Language Models Are Zero-Shot Learners — Wei, Bosma, Zhao, Guu, Yu, Lester, Du, Dai, Le (2022)paperЦитують: Instruction tuning
88. Focal Loss for Dense Object Detection — Lin, Goyal, Girshick, He, Dollár (2018)paperЦитують: Mean average precision, Object detection
89. Forecasting: Principles and Practice — Hyndman, AthanasopoulosbookЦитують: MAPE
90. Forecasting: Principles and Practice — Hyndman, AthanasopoulosbookЦитують: MSLE
91. Forecasting: theory and practice — Petropoulos, Apiletti, Assimakopoulos et al. (2022)paperЦитують: MAPE, Time series decomposition, Forecasting methods
92. GAIN: Missing Data Imputation using Generative Adversarial Nets — Yoon, Jordon, van der Schaar (2018)paperЦитують: Missing data
93. Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression — Rezatofighi, Tsoi, Gwak, Sadeghian, Reid, Savarese (2019)paperЦитують: Intersection over union
94. Generative Adversarial Nets — Goodfellow, Pouget-Abadie, Mirza, Xu, Warde-Farley, Ozair, Courville, Bengio (2014)paperЦитують: Diffusion model, Generative adversarial network
95. Group Normalization — Wu, He (2018)paperЦитують: Batch normalization, Mini-batch gradient descent
96. Hidden Technical Debt in Machine Learning Systems — Sculley, Holt, Golovin, Davydov, Phillips, Ebner, Chaudhary, Young, Crespo, Dennison (2015)paperЦитують: Feature engineering, Machine learning workflow
97. High-Resolution Image Synthesis with Latent Diffusion Models — Rombach, Blattmann, Lorenz, Esser, Ommer (2022)paperЦитують: Diffusion model, Generative adversarial network
98. How Does Batch Normalization Help Optimization? — Santurkar, Tsipras, Ilyas, Madry (2018)paperЦитують: Batch normalization
99. How to Use t-SNE Effectively — Wattenberg, Viégas, Johnson (2016)paperЦитують: Manifold learning
100. How transferable are features in deep neural networks? — Yosinski, Clune, Bengio, Lipson (2014)paperЦитують: Transfer learning
101. Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization — Li, Jamieson, DeSalvo, Rostamizadeh, Talwalkar (2018)paperЦитують: Hyperparameter tuning
102. ImageNet Large Scale Visual Recognition Challenge — Russakovsky, Deng, Su, Krause, Satheesh, Ma, Huang, Karpathy, Khosla, Bernstein, Berg, Fei-Fei (2015)paperЦитують: Image classification
103. Introduction to Information Retrieval — Manning, Raghavan, Schütze (2008)bookЦитують: Accuracy, Bag of words, Confusion matrix, Eigenvectors and eigenvalues, F1-score, Precision, Recall, ROC AUC, Specificity, TF-IDF
104. Introduction to Information Retrieval — Manning, Raghavan, Schütze (2008)bookЦитують: Sentence embeddings
105. Introduction to Information Retrieval — Manning, Raghavan, SchützebookЦитують: Classification metrics
106. Introduction to Information Retrieval — Support vector machines — Manning, Raghavan, Schütze (2008)bookЦитують: SVM
107. Language Models are Few-Shot Learners — Brown, Mann, Ryder, Subbiah, Kaplan, Dhariwal, et al. (2020)paperЦитують: Instruction tuning, Prompting, NLP tasks, Transformer family
108. Layer Normalization — Ba, Kiros, Hinton (2016)paperЦитують: Batch normalization, Transformer
109. Leakage and the Reproducibility Crisis in ML-based Science — Kapoor, Narayanan (2023)paperЦитують: Data leakage, Validation strategies
110. Learning Transferable Visual Models From Natural Language Supervision — Radford, Kim, Hallacy, Ramesh, Goh, Agarwal, Sastry, Askell, Mishkin, Clark, Krueger, Sutskever (2021)paperЦитують: CLIP, Self-supervised learning, Vision tasks
111. Learning Transferable Visual Models From Natural Language Supervision — Radford, Kim, Hallacy, Ramesh, Goh, Agarwal, Sastry, Askell, Mishkin, Clark, Krueger, Sutskever (2021)paperЦитують: Vision transformer
112. LightGBM: A Highly Efficient Gradient Boosting Decision Tree — Ke, Meng, Finley, Wang, Chen, Ma, Ye, Liu (2017)paperЦитують: Gradient boosting, Tree ensembles
113. Machine Learning Crash Course — Classification: accuracy, recall, precision, and related metrics — GooglecourseЦитують: Accuracy, Confusion matrix, F1-score, Precision, Recall, ROC AUC, Specificity, Classification metrics
114. Machine Learning Crash Course — ROC and AUC — GooglecourseЦитують: ROC AUC, Specificity
115. Machine Learning Crash Course — Thresholds and the confusion matrix — GooglecourseЦитують: Accuracy, Confusion matrix, Cross-entropy, Recall
116. Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings — Bolukbasi, Chang, Zou, Saligrama, Kalai (2016)paperЦитують: Word embeddings
117. Mask R-CNN — He, Gkioxari, Dollár, Girshick (2017)paperЦитують: Instance segmentation
118. Microsoft COCO: Common Objects in Context — Lin, Maire, Belongie, Bourdev, Girshick, Hays, Perona, Ramanan, Dollár, Zitnick (2014)paperЦитують: Instance segmentation, Vision tasks
119. minimize(method='L-BFGS-B')docsЦитують: BFGS
120. MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications — Howard, Zhu, Chen, Kalenichenko, Wang, Weyand, Andreetto, Adam (2017)paperЦитують: Depthwise separable convolution
121. Neural Architectures for Named Entity Recognition — Lample, Ballesteros, Subramanian, Kawakami, Dyer (2016)paperЦитують: Named entity recognition
122. Neural Machine Translation by Jointly Learning to Align and Translate — Bahdanau, Cho, Bengio (2015)paperЦитують: Attention, Sequence-to-sequence
123. Neural Machine Translation of Rare Words with Subword Units — Sennrich, Haddow, Birch (2016)paperЦитують: Tokenization
124. NIST/SEMATECH e-Handbook — How can we make multiple comparisons?docsЦитують: Multiple comparisons
125. NIST/SEMATECH e-Handbook of Statistical MethodsstandardЦитують: Autocorrelation
126. NIST/SEMATECH e-Handbook of Statistical MethodsstandardЦитують: Bootstrap
127. NIST/SEMATECH e-Handbook of Statistical MethodsstandardЦитують: Central limit theorem
128. NIST/SEMATECH e-Handbook of Statistical MethodsstandardЦитують: Confidence interval
129. NIST/SEMATECH e-Handbook of Statistical MethodsstandardЦитують: Hypothesis testing
130. NIST/SEMATECH e-Handbook of Statistical MethodsstandardЦитують: Stationarity
131. NIST/SEMATECH e-Handbook of Statistical MethodsstandardЦитують: Time series decomposition, Forecasting methods
132. NIST/SEMATECH e-Handbook of Statistical Methods — Product and Process ComparisonsstandardЦитують: A/B testing
133. On Calibration of Modern Neural Networks — Guo, Pleiss, Sun, Weinberger (2017)paperЦитують: Cross-entropy, Model calibration, Classification metrics
134. On Calibration of Modern Neural Networks — Guo, Pleiss, Sun, Weinberger (2017)paperЦитують: Сигмоїда
135. On Discriminative vs. Generative Classifiers: A comparison of logistic regression and naive Bayes — Ng, Jordan (2001)paperЦитують: Gaussian discriminant analysis
136. PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation — Qi, Su, Mo, Guibas (2017)paperЦитують: PointNet
137. PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space — Qi, Yi, Su, Guibas (2017)paperЦитують: PointNet
138. Project Jupyter documentationdocsЦитують: Jupyter Notebook
139. PyTorch documentation — torch.nn.Conv2ddocsЦитують: Convolution
140. Random Search for Hyper-Parameter Optimization — Bergstra, Bengio (2012)paperЦитують: Hyperparameter tuning
141. Reconciling modern machine learning practice and the bias-variance trade-off — Belkin, Hsu, Ma, Mandal (2019)paperЦитують: Bias-variance tradeoff
142. Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks — Lewis, Perez, Piktus, Petroni, Karpukhin, Goyal, Küttler, Lewis, Yih, Rocktäschel, Riedel, Kiela (2021)paperЦитують: Hallucination, Retrieval-augmented generation
143. RoBERTa: A Robustly Optimized BERT Pretraining Approach — Liu, Ott, Goyal, Du, Joshi, Chen, Levy, Lewis, Zettlemoyer, Stoyanov (2019)paperЦитують: Transformer family
144. Rules of Machine Learning: Best Practices for ML Engineering (Google) — ZinkevichdocsЦитують: Feature engineering, Machine learning workflow
145. scikit-learn — Common pitfalls in the interpretation of coefficients of linear modelsdocsЦитують: Confounding
146. scikit-learn — DecisionTreeClassifierdocsЦитують: Decision tree
147. scikit-learn — KMeansdocsЦитують: K-means
148. scikit-learn — KNeighborsClassifierdocsЦитують: Distance-weighted KNN, KNN
149. scikit-learn — KNNImputerdocsЦитують: KNN
150. scikit-learn — sklearn.linear_model.BayesianRidgedocsЦитують: Bayesian linear regression
151. scikit-learn — sklearn.linear_model.ElasticNetdocsЦитують: Elastic Net, Linear model family
152. scikit-learn — sklearn.linear_model.HuberRegressordocsЦитують: Huber loss, MAE
153. scikit-learn — sklearn.linear_model.LassodocsЦитують: Lasso regression
154. scikit-learn — sklearn.linear_model.RidgedocsЦитують: Regularization, Ridge regression
155. scikit-learn — sklearn.metrics.accuracy_scoredocsЦитують: Accuracy
156. scikit-learn — sklearn.metrics.confusion_matrixdocsЦитують: Confusion matrix, Specificity, Classification metrics
157. scikit-learn — sklearn.metrics.f1_scoredocsЦитують: F1-score
158. scikit-learn — sklearn.metrics.mean_absolute_errordocsЦитують: MAE
159. scikit-learn — sklearn.metrics.mean_absolute_percentage_errordocsЦитують: MAPE
160. scikit-learn — sklearn.metrics.mean_squared_errordocsЦитують: MSE, Regression metrics
161. scikit-learn — sklearn.metrics.mean_squared_log_errordocsЦитують: MSLE
162. scikit-learn — sklearn.metrics.precision_scoredocsЦитують: Precision
163. scikit-learn — sklearn.metrics.r2_scoredocsЦитують: R²
164. scikit-learn — sklearn.metrics.recall_scoredocsЦитують: Recall
165. scikit-learn — sklearn.metrics.roc_auc_scoredocsЦитують: ROC AUC
166. scikit-learn — sklearn.metrics.root_mean_squared_errordocsЦитують: RMSE
167. scikit-learn — sklearn.preprocessing.PolynomialFeaturesdocsЦитують: Polynomial regression
168. scikit-learn — SplineTransformerdocsЦитують: Polynomial regression
169. scikit-learn — SVCdocsЦитують: SVM
170. scikit-learn User Guide — ClusteringdocsЦитують: K-means, PCA, Clustering methods
171. scikit-learn User Guide — Common pitfalls and recommended practicesdocsЦитують: Data leakage
172. scikit-learn User Guide — Cross-validationdocsЦитують: Autocorrelation, Cross-validation, Machine learning workflow, Overfitting, Train-test split, Validation strategies
173. scikit-learn User Guide — Decision TreesdocsЦитують: Decision tree, Entropy, Gradient
174. scikit-learn User Guide — Ensembles: Gradient boosting, random forests, bagging, voting, stackingdocsЦитують: Bagging, Boosting, Gradient boosting, Random forest, Tree ensembles
175. scikit-learn User Guide — Feature extraction from textdocsЦитують: Bag of words, TF-IDF
176. scikit-learn User Guide — Imputation of missing valuesdocsЦитують: Missing data
177. scikit-learn User Guide — Linear and Quadratic Discriminant AnalysisdocsЦитують: Gaussian discriminant analysis
178. scikit-learn user guide — Linear ModelsdocsЦитують: Elastic Net, Generalized linear models, Lasso regression, Linear regression, Perceptron
179. scikit-learn User Guide — Metrics and scoringdocsЦитують: Class imbalance, Cross-entropy, MAPE, MSE, MSLE, R², Recall, RMSE
180. scikit-learn user guide — Nearest NeighborsdocsЦитують: KNN
181. scikit-learn User Guide — Novelty and Outlier DetectiondocsЦитують: Outliers
182. scikit-learn User Guide — Permutation feature importancedocsЦитують: Feature importance
183. scikit-learn User Guide — Preprocessing datadocsЦитують: Feature engineering
184. scikit-learn User Guide — Probability calibrationdocsЦитують: Model calibration, Perceptron
185. scikit-learn User Guide — Stochastic Gradient DescentdocsЦитують: Perceptron
186. scikit-learn User Guide — Support Vector MachinesdocsЦитують: Perceptron
187. scikit-learn User Guide — Tuning the hyper-parameters of an estimatordocsЦитують: Bias-variance tradeoff, Hyperparameter tuning
188. SciPy — scipy.stats.false_discovery_controldocsЦитують: Multiple comparisons
189. SciPy reference — scipy.stats.bootstrapdocsЦитують: Bootstrap
190. scipy.optimize.minimizedocsЦитують: BFGS, Conjugate gradient
191. scipy.sparse.linalg.cgdocsЦитують: Conjugate gradient
192. Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks — Reimers, Gurevych (2019)paperЦитують: CLIP, Retrieval-augmented generation, Sentence embeddings, NLP tasks
193. SentencePiece: A simple and language independent subword tokenizer and detokenizer — Kudo, Richardson (2018)paperЦитують: Named entity recognition, Tokenization
194. sklearn.ensemble.GradientBoostingClassifierdocsЦитують: Early stopping
195. sklearn.linear_model.LogisticRegressiondocsЦитують: BFGS, Logistic regression
196. statsmodels — Generalized Linear ModelsdocsЦитують: Generalized linear models
197. statsmodels — multipletestsdocsЦитують: Multiple comparisons
198. Survey of Hallucination in Natural Language Generation — Ji, Lee, Frieske, Yu, Su, Xu, Ishii, Bang, Chen, Dai, Chan, Madotto, Fung (2023)paperЦитують: Hallucination
199. Tangled up in BLEU — Reevaluating the Evaluation of Automatic Machine Translation Evaluation Metrics — Mathur, Baldwin, Cohn (2020)paperЦитують: BLEU, Text metrics
200. Ten Simple Rules for Reproducible Research in Jupyter Notebooks — Rule, Birmingham, Zuniga, Altintas, Huang, Knight, Moshiri, Nguyen, Rosenthal, Pérez, Rose (2018)paperЦитують: Jupyter Notebook
201. tf.keras.optimizers.AdamdocsЦитують: Adam
202. The Curious Case of Neural Text Degeneration — Holtzman, Buys, Du, Forbes, Choi (2020)paperЦитують: Decoding, Hallucination, Language model, Perplexity
203. The Marginal Value of Adaptive Gradient Methods in Machine Learning — Wilson, Roelofs, Stern, Srebro, Recht (2017)paperЦитують: Adam
204. Theoretical Analysis of the k-Means Algorithm — A Survey — Blömer, Lammersen, Schmidt, Sohler (2016)paperЦитують: K-means, Clustering methods
205. Think Bayes — DowneybookЦитують: Bayes' theorem
206. Think Stats — DowneybookЦитують: Autocorrelation, Bootstrap, Central limit theorem, Confidence interval, Expectation and variance, Hypothesis testing, Maximum likelihood, Missing data, Outliers, Stationarity, Time series decomposition
207. Think Stats — 10. Linear least squares — Allen B. DowneybookЦитують: Correlation, R², RMSE
208. Think Stats — Ch. 11, Regression — DowneybookЦитують: Generalized linear models
209. Think Stats — Ch. 2, Distributions — DowneybookЦитують: Huber loss
210. Think Stats — Ch. 7, Relationships between variables — Allen B. DowneybookЦитують: A/B testing, Confounding, Correlation
211. Think Stats — Ch. 9, Hypothesis Testing — DowneybookЦитують: A/B testing, Multiple comparisons
212. torch.utils.data.DataLoaderdocsЦитують: Mini-batch gradient descent
213. Torchvision documentation — Transforming images, videos, boxes and moredocsЦитують: Data augmentation
214. Training Language Models to Follow Instructions with Human Feedback — Ouyang, Wu, Jiang, Almeida, Wainwright, Mishkin, et al. (2022)paperЦитують: Hallucination, Instruction tuning, Retrieval-augmented generation
215. Transfusion: Understanding Transfer Learning for Medical Imaging — Raghu, Zhang, Kleinberg, Bengio (2019)paperЦитують: Transfer learning
216. U-Net: Convolutional Networks for Biomedical Image Segmentation — Ronneberger, Fischer, Brox (2015)paperЦитують: Diffusion model, Semantic segmentation, Transposed convolution
217. UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction — McInnes, Healy, Melville (2020)paperЦитують: Manifold learning
218. Understanding Random Forests: From Theory to Practice — Louppe (2014)paperЦитують: Feature importance, Random forest
219. Understanding the Effective Receptive Field in Deep Convolutional Neural Networks — Luo, Li, Urtasun, Zemel (2017)paperЦитують: Pooling, Receptive field, Residual connection
220. XGBoost: A Scalable Tree Boosting System — Chen, Guestrin (2016)paperЦитують: Boosting, Tree ensembles
221. XGBoost: A Scalable Tree Boosting System — Chen, Guestrin (2016)paperЦитують: Gradient boosting
222. YOLO9000: Better, Faster, Stronger — Redmon, Farhadi (2017)paperЦитують: Object detection
223. You Only Look Once: Unified, Real-Time Object Detection — Redmon, Divvala, Girshick, Farhadi (2016)paperЦитують: Object detection