A model has more parameters than it needs to fit the training data.
Overparameterization is a giant box of crayons for one tiny drawing. The page is tiny, but a good kid can still make the dog look great.
Big deep models use this a lot to train more easily. But they need good data and regularization.
Parameter
Overparameterization means the model has more parameters than it needs.
Regularization
Regularization controls the extra freedom and reduces overfitting.
Deep Learning
Deep Learning often uses huge parameter counts to make training easier.
Bias-Variance Tradeoff
It makes the old "more parameters means overfitting" rule less simple.