What is Data Augmentation?

What is the common confusion about Data Augmentation?

An augmentation must preserve the target label or behavior you want the model to learn.

Learn Data Augmentation in the course

Lessons that name Data Augmentation in a title or section

• Regularization

  Your model gets 99% on training data and 60% on test data. It memorized instead of learning. Regularization is the tax you impose on complexity to force generalization.

  Phase 03: Deep Learning Core

Covered in Phase 03: Deep Learning Core.

Related terms

• OverfittingA generalization gap in which performance on training data is substantially better than performance on representative unseen data.
• EpochOne traversal of the defined training dataset. In distributed or sampled training, the exact implementation of an epoch depends on the…
• Eval SetA versioned collection of inputs, expected properties, scoring rules, and metadata used to measure an AI system against a defined…

More terms in Math & training

• Activation Checkpointing
• Activation Function
• Adam (Optimizer)
• AdamW
• Autograd
• Backpropagation
• Batch Size
• Contrastive Learning
• Cross-Entropy
• DPO (Direct Preference Optimization)
• Dropout
• Eigenvalue
• Epoch
• Fine-tuning
• Gradient
• Gradient Accumulation
• Gradient Clipping
• Gradient Descent
• Hyperparameter
• JAX
• Knowledge Distillation
• Learning Rate
• Learning Rate Schedule
• LoRA (Low-Rank Adaptation)
• Loss Function
• Mixed Precision
• NaN (Not a Number)
• Normalization
• Optimizer
• Overfitting
• QLoRA
• ReLU
• RLHF (Reinforcement Learning from Human Feedback)
• SFT (Supervised Fine-Tuning)
• Softmax
• Stochastic Gradient Descent (SGD)
• Transfer Learning
• Underfitting
• Warmup
• Weight
• Weight Decay

Open the Math & training list in the glossary