Pages with the fewest revisions
Showing below up to 100 results in range #1 to #100.
- Bidirectional language model (1 revision)
- Positive class (1 revision)
- Neuron (1 revision)
- Pipelining (1 revision)
- Meta-learning (1 revision)
- GitHub Copilot (1 revision)
- Decision tree (1 revision)
- Sparse representation (1 revision)
- L1 regularization (1 revision)
- Softmax (1 revision)
- Loss function (1 revision)
- Condition (1 revision)
- Transformer (1 revision)
- Output layer (1 revision)
- L2 loss (1 revision)
- Bagging (1 revision)
- L2 regularization (1 revision)
- L1 loss (1 revision)
- Numerical data (1 revision)
- ROC (receiver operating characteristic) Curve (1 revision)
- BLEU (Bilingual Evaluation Understudy) (1 revision)
- One-vs.-all (1 revision)
- Prediction (1 revision)
- Negative class (1 revision)
- Modality (1 revision)
- Decision forest (1 revision)
- Synthetic feature (1 revision)
- Crash blossom (1 revision)
- Bag of words (1 revision)
- Sentiment analysis (1 revision)
- Denoising (1 revision)
- Regression model (1 revision)
- Post-processing (1 revision)
- Proxy labels (1 revision)
- Model hubs (1 revision)
- Parameter (1 revision)
- Fine-tune ChatGPT with Perplexity, Burstiness, Professionalism, Randomness and Sentimentality Guide (1 revision)
- Sequence-to-sequence task (1 revision)
- Logistic regression (1 revision)
- Sparse vector (1 revision)
- Sparse feature (1 revision)
- Staged training (1 revision)
- Loss (1 revision)
- BERT (Bidirectional Encoder Representations from Transformers) (1 revision)
- Log Loss (1 revision)
- Model parallelism (1 revision)
- Stochastic gradient descent (SGD) (1 revision)
- Multimodal model (1 revision)
- Multi-head self-attention (1 revision)
- Binary condition (1 revision)
- Axis-aligned condition (1 revision)
- Nonlinear (1 revision)
- Node (neural network) (1 revision)
- Normalization (1 revision)
- Nonstationarity (1 revision)
- One-hot encoding (1 revision)
- Offline (1 revision)
- Online inference (1 revision)
- Entropy (1 revision)
- Feature importances (1 revision)
- Webb Schools (1 revision)
- Overfitting (1 revision)
- Pandas (1 revision)
- Causal language model (1 revision)
- Confusion matrix (1 revision)
- Confident Learning (CL) (1 revision)
- Label (1 revision)
- Rater (1 revision)
- Decoder (1 revision)
- Embedding space (1 revision)
- Embedding vector (1 revision)
- Lambda (1 revision)
- Regularization (1 revision)
- Large language model (1 revision)
- Linear (1 revision)
- Linear regression (1 revision)
- Log-odds (1 revision)
- Labeled example (1 revision)
- Model (1 revision)
- LaMDA (Language Model for Dialogue Applications) (1 revision)
- Sigmoid function (1 revision)
- Encoder (1 revision)
- GPT (Generative Pre-trained Transformer) (1 revision)
- Non-profit Organizations (1 revision)
- Masked language model (1 revision)
- Loss curve (1 revision)
- Squared loss (1 revision)
- Static inference (1 revision)
- Regularization rate (1 revision)
- Linear model (1 revision)
- NLU (1 revision)
- Static (1 revision)
- Transformers (1 revision)
- Supervised machine learning (1 revision)
- Root Mean Squared Error (RMSE) (1 revision)
- Bidirectional (1 revision)
- Multi-class classification (1 revision)
- Rectified Linear Unit (ReLU) (1 revision)
- Natural language understanding (1 revision)
- Self-attention (also called self-attention layer) (1 revision)