Search Results
4 results for “overfitting”
Data Augmentation
A set of techniques that expand a training dataset by creating modified copies of existing examples, helping deep learning models generalise better and reducing overfitting.
Dropout
A regularisation technique in deep learning that randomly deactivates neurons during training, preventing co-adaptation and improving generalisation. Introduced by Hinton and colleagues in 2012 and formalised in 2014.
Random Forest
Random forest is an ensemble machine learning algorithm that builds many decision trees on bootstrapped samples and aggregates their predictions to improve accuracy and reduce overfitting.
Regularisation (Machine Learning)
Regularisation is a collection of techniques in machine learning that constrain models during training to reduce overfitting and improve generalisation to unseen data.