Neural Architecture Search
Automated methods for discovering optimal neural network architectures, using techniques like reinforcement learning or evolution.
Your route here
9 stops · basics first
- Machine Learning ✓ understood
Building systems that learn patterns from data instead of following hand-written rules, getting better at a task as they see more examples.
- Neural Network ✓ understood
A model built from layers of simple units, each taking a weighted sum of its inputs and applying a nonlinearity; training adjusts the weights so the whole stack maps inputs to useful outputs.
- Dataset ✓ understood
A collection of data examples used for training, validating, or testing machine learning models.
- Train-Test Split ✓ understood
Dividing a dataset into separate portions for training the model and evaluating its performance on unseen data.
- Validation Set ✓ understood
Data held back from training and used to choose hyperparameters and checkpoints, so those choices are judged on examples the model never fit.
- Training ✓ understood
The process of fitting a model to data by repeatedly measuring how wrong its outputs are and adjusting its parameters to reduce that error.
- Parameter ✓ understood
A number inside a model, a weight or a bias, that training adjusts to reduce the loss. Together, a model's parameters are everything it has learned.
- Hyperparameter ✓ understood
A setting chosen before training, such as the learning rate or batch size, that controls how a model learns but isn't itself learned from the data.
- Hyperparameter Tuning ✓ understood
The process of finding optimal hyperparameter values through techniques like grid search, random search, or Bayesian optimization.
- Neural Architecture Search · you are here ✓ understood
Where it sits
Leads to
Nothing yet: a destination in its own right.