Overfitting

فرط التخصيص

حين يحفظ النموذج بيانات التدريب بدل تعلم أنماط قابلة للتعميم، فيؤدي جيداً على بيانات التدريب لكنه يفشل على بيانات لم يرها من قبل.

When a model memorizes training data instead of learning generalizable patterns, performing well on training data but failing on unseen data.

Also translated asالإفراط في التخصيص، التعلم المُفرط، التكيف الحرفي المقيد مع معطيات التدريب، التلقين الأعمى للنموذج

First appears in this corpus in: The Organization of Behavior: A Neuropsychological Theory (1949)

Appears in these papers

A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting1997 in the sky ✦
Intriguing Properties of Neural Networks2014 in the sky ✦
Intriguing Properties of Neural Networks2014 in the sky ✦
ImageNet Classification with Deep Convolutional Neural Networks2012 in the sky ✦
Mastering the Game of Go with Deep Neural Networks and Tree Search2016 in the sky ✦
Bagging Predictors1996 in the sky ✦
Bagging Predictors1996 in the sky ✦
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift2015 in the sky ✦
BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer2019 in the sky ✦
Neural Networks and the Bias/Variance Dilemma1992 in the sky ✦
Neural Networks and the Bias/Variance Dilemma1992 in the sky ✦
BPR: Bayesian Personalized Ranking from Implicit Feedback2009 in the sky ✦
C4.5: Programs for Machine Learning1993 in the sky ✦
C4.5: Programs for Machine Learning1993 in the sky ✦
Classification and Regression Trees1984 in the sky ✦
Evaluating Large Language Models Trained on Code2021 in the sky ✦
Unsupervised Visual Representation Learning by Context Prediction2015 in the sky ✦
Gradient-Based Learning Applied to Document Recognition1998 in the sky ✦
DeBERTa: Decoding-Enhanced BERT with Disentangled Attention2020 in the sky ✦
Reducing the Dimensionality of Data with Neural Networks2006 in the sky ✦
Deep Learning2015 in the sky ✦
Deep Reinforcement Learning from Human Preferences2017 in the sky ✦
Densely Connected Convolutional Networks2017 in the sky ✦
Deep Interest Network for Click-Through Rate Prediction2018 in the sky ✦
Deep Interest Network for Click-Through Rate Prediction2018 in the sky ✦
Reconciling Modern Machine-Learning Practice and the Classical Bias–Variance Trade-Off2019 in the sky ✦
Reconciling Modern Machine-Learning Practice and the Classical Bias–Variance Trade-Off2019 in the sky ✦
Dropout: A Simple Way to Prevent Neural Networks from Overfitting2014 in the sky ✦
Explaining and Harnessing Adversarial Examples2015 in the sky ✦
Finetuned Language Models Are Zero-Shot Learners2022 in the sky ✦
Gaussian Processes for Machine Learning2006 in the sky ✦
Gaussian Error Linear Units (GELUs)2016 in the sky ✦
GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding2018 in the sky ✦
Going Deeper with Convolutions2014 in the sky ✦
Improving Language Understanding by Generative Pre-Training2018 in the sky ✦
Language Models Are Unsupervised Multitask Learners2019 in the sky ✦
Greedy Function Approximation: A Gradient Boosting Machine2001 in the sky ✦
Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets2022 in the sky ✦
Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets2022 in the sky ✦
The Organization of Behavior: A Neuropsychological Theory1949 in the sky ✦
Induction of Decision Trees1986 in the sky ✦
Induction of Decision Trees1986 in the sky ✦
Distilling the Knowledge in a Neural Network2015 in the sky ✦
When Does Label Smoothing Help?2019 in the sky ✦
When Does Label Smoothing Help?2019 in the sky ✦
Regression Shrinkage and Selection via the Lasso1996 in the sky ✦
Regression Shrinkage and Selection via the Lasso1996 in the sky ✦
Latent Dirichlet Allocation2003 in the sky ✦
LightGBM: A Highly Efficient Gradient Boosting Decision Tree2017 in the sky ✦
LightGBM: A Highly Efficient Gradient Boosting Decision Tree2017 in the sky ✦
LIMA: Less Is More for Alignment2023 in the sky ✦
LIMA: Less Is More for Alignment2023 in the sky ✦
"Why Should I Trust You?": Explaining the Predictions of Any Classifier2016 in the sky ✦
Visualizing the Loss Landscape of Neural Nets2018 in the sky ✦
Visualizing the Loss Landscape of Neural Nets2018 in the sky ✦
The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks2019 in the sky ✦
Matrix Factorization Techniques for Recommender Systems2009 in the sky ✦
Mixed Precision Training2018 in the sky ✦
mixup: Beyond Empirical Risk Minimization2018 in the sky ✦
mixup: Beyond Empirical Risk Minimization2018 in the sky ✦
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications2017 in the sky ✦
Nearest Neighbor Pattern Classification1967 in the sky ✦
No Free Lunch Theorems for Optimization1997 in the sky ✦
No Free Lunch Theorems for Optimization1997 in the sky ✦
Neural Tangent Kernel: Convergence and Generalization in Neural Networks2018 in the sky ✦
Neural Tangent Kernel: Convergence and Generalization in Neural Networks2018 in the sky ✦
Optimal Brain Damage1989 in the sky ✦
Optimal Brain Damage1989 in the sky ✦
A Time Series Is Worth 64 Words: Long-Term Forecasting with Transformers2023 in the sky ✦
Perceiver: General Perception with Iterative Attention2021 in the sky ✦
Textbooks Are All You Need2023 in the sky ✦
Prioritized Experience Replay2015 in the sky ✦
Forecasting at Scale2018 in the sky ✦
Random Forests2001 in the sky ✦
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation2014 in the sky ✦
Rectified Linear Units Improve Restricted Boltzmann Machines2010 in the sky ✦
Deep Residual Learning for Image Recognition2015 in the sky ✦
Scaling Laws for Neural Language Models2020 in the sky ✦
Squeeze-and-Excitation Networks2018 in the sky ✦
SGDR: Stochastic Gradient Descent with Warm Restarts2017 in the sky ✦
Sharpness-Aware Minimization for Efficiently Improving Generalization2021 in the sky ✦
Sharpness-Aware Minimization for Efficiently Improving Generalization2021 in the sky ✦
SQuAD: 100,000+ Questions for Machine Comprehension of Text2016 in the sky ✦
Support-Vector Networks1995 in the sky ✦
SwAV: Unsupervised Learning of Visual Features by Contrasting Cluster Assignments2020 in the sky ✦
Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity2022 in the sky ✦
Universal Language Model Fine-Tuning for Text Classification2018 in the sky ✦
Universal Language Model Fine-Tuning for Text Classification2018 in the sky ✦
On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities1971 in the sky ✦
On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities1971 in the sky ✦
Very Deep Convolutional Networks for Large-Scale Image Recognition2014 in the sky ✦
wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations2020 in the sky ✦
The Strength of Weak Learnability1990 in the sky ✦
Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision2023 in the sky ✦
Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision2023 in the sky ✦
Robust Speech Recognition via Large-Scale Weak Supervision2022 in the sky ✦
World Models2018 in the sky ✦
World Models2018 in the sky ✦
XGBoost: A Scalable Tree Boosting System2016 in the sky ✦