Pages with the fewest revisions

Showing below up to 100 results in range #1 to #100.

1. Bidirectional language model‏‎ (1 revision)
2. Positive class‏‎ (1 revision)
3. Neuron‏‎ (1 revision)
4. Pipelining‏‎ (1 revision)
5. Meta-learning‏‎ (1 revision)
6. GitHub Copilot‏‎ (1 revision)
7. Decision tree‏‎ (1 revision)
8. Sparse representation‏‎ (1 revision)
9. L1 regularization‏‎ (1 revision)
10. Softmax‏‎ (1 revision)
11. Loss function‏‎ (1 revision)
12. Condition‏‎ (1 revision)
13. Transformer‏‎ (1 revision)
14. Output layer‏‎ (1 revision)
15. L2 loss‏‎ (1 revision)
16. Bagging‏‎ (1 revision)
17. L2 regularization‏‎ (1 revision)
18. L1 loss‏‎ (1 revision)
19. Numerical data‏‎ (1 revision)
20. ROC (receiver operating characteristic) Curve‏‎ (1 revision)
21. BLEU (Bilingual Evaluation Understudy)‏‎ (1 revision)
22. One-vs.-all‏‎ (1 revision)
23. Prediction‏‎ (1 revision)
24. Negative class‏‎ (1 revision)
25. Modality‏‎ (1 revision)
26. Decision forest‏‎ (1 revision)
27. Synthetic feature‏‎ (1 revision)
28. Crash blossom‏‎ (1 revision)
29. Bag of words‏‎ (1 revision)
30. Sentiment analysis‏‎ (1 revision)
31. Denoising‏‎ (1 revision)
32. Regression model‏‎ (1 revision)
33. Post-processing‏‎ (1 revision)
34. Proxy labels‏‎ (1 revision)
35. Model hubs‏‎ (1 revision)
36. Parameter‏‎ (1 revision)
37. Fine-tune ChatGPT with Perplexity, Burstiness, Professionalism, Randomness and Sentimentality Guide‏‎ (1 revision)
38. Sequence-to-sequence task‏‎ (1 revision)
39. Logistic regression‏‎ (1 revision)
40. Sparse vector‏‎ (1 revision)
41. Sparse feature‏‎ (1 revision)
42. Staged training‏‎ (1 revision)
43. Loss‏‎ (1 revision)
44. BERT (Bidirectional Encoder Representations from Transformers)‏‎ (1 revision)
45. Log Loss‏‎ (1 revision)
46. Model parallelism‏‎ (1 revision)
47. Stochastic gradient descent (SGD)‏‎ (1 revision)
48. Multimodal model‏‎ (1 revision)
49. Multi-head self-attention‏‎ (1 revision)
50. Binary condition‏‎ (1 revision)
51. Axis-aligned condition‏‎ (1 revision)
52. Nonlinear‏‎ (1 revision)
53. Node (neural network)‏‎ (1 revision)
54. Normalization‏‎ (1 revision)
55. Nonstationarity‏‎ (1 revision)
56. One-hot encoding‏‎ (1 revision)
57. Offline‏‎ (1 revision)
58. Online inference‏‎ (1 revision)
59. Entropy‏‎ (1 revision)
60. Feature importances‏‎ (1 revision)
61. Webb Schools‏‎ (1 revision)
62. Overfitting‏‎ (1 revision)
63. Pandas‏‎ (1 revision)
64. Causal language model‏‎ (1 revision)
65. Confusion matrix‏‎ (1 revision)
66. Confident Learning (CL)‏‎ (1 revision)
67. Label‏‎ (1 revision)
68. Rater‏‎ (1 revision)
69. Decoder‏‎ (1 revision)
70. Embedding space‏‎ (1 revision)
71. Embedding vector‏‎ (1 revision)
72. Lambda‏‎ (1 revision)
73. Regularization‏‎ (1 revision)
74. Large language model‏‎ (1 revision)
75. Linear‏‎ (1 revision)
76. Linear regression‏‎ (1 revision)
77. Log-odds‏‎ (1 revision)
78. Labeled example‏‎ (1 revision)
79. Model‏‎ (1 revision)
80. LaMDA (Language Model for Dialogue Applications)‏‎ (1 revision)
81. Sigmoid function‏‎ (1 revision)
82. Encoder‏‎ (1 revision)
83. GPT (Generative Pre-trained Transformer)‏‎ (1 revision)
84. Non-profit Organizations‏‎ (1 revision)
85. Masked language model‏‎ (1 revision)
86. Loss curve‏‎ (1 revision)
87. Squared loss‏‎ (1 revision)
88. Static inference‏‎ (1 revision)
89. Regularization rate‏‎ (1 revision)
90. Linear model‏‎ (1 revision)
91. NLU‏‎ (1 revision)
92. Static‏‎ (1 revision)
93. Transformers‏‎ (1 revision)
94. Supervised machine learning‏‎ (1 revision)
95. Root Mean Squared Error (RMSE)‏‎ (1 revision)
96. Bidirectional‏‎ (1 revision)
97. Multi-class classification‏‎ (1 revision)
98. Rectified Linear Unit (ReLU)‏‎ (1 revision)
99. Natural language understanding‏‎ (1 revision)
100. Self-attention (also called self-attention layer)‏‎ (1 revision)