1 Challenges in AI/ML Project

2 Data augmentation can be done only for images

3 What do we use when data is too little?

4 Which of the following are reasons why do we dimensionality reduction

5 dataset with large number of features

6 PCA is an unsupervised learning process

7 Time-series data imputation

8 Which of the data augment techniques are okay for images of people for gender prediction?

9 Data Augmentation for human voice to text?

10 Should we feed zero variance features to algorithm for training?

11 Dimensionality Reduction

12 Will PCA remove the common border from images?

13 Do we lose information in Dimensionality Reduction?

14 Advantages of Dimensionality Reduction

15 What to do in case of missing values?

16 Overfitting or Underfitting?

17 Methods to avoid over-fitting

18 Regularization adds the penalty as model complexity increases

19 Model gets trained with limited data

20 Pre-trained neural network models