Curse of Dimensionality

#machine-learning #interview

When the number of features is larger than the number of instances, then ML systems struggle to train or fit the data. This is known as curse of dimensionality

Also, known as Dimensionally Sparse Data

To solve this we have to use Dimensionality Reduction

Related Notes

Support Vector Machine (SVM)
SentencePiece Tokenization
Softsign
Reinforcement Learning from Human Feedback (RLHF)
Skip Gram Model