Your company built a TensorFlow neural-network model with a large number of neurons and layers. The model fits well for the training data. However, when tested against new data, it performs poorly. Wh

The correct answer is C. Dropout Methods. Explanation/Reference: Bad performance of a model is either due to lack of relationship between dependent and independent variables used, or just overfit due to having used too many features and/or bad features. Dropout Methods can show which features are bad. E.g. if it is one f

Submitted by miguelv· Mar 30, 2026Operationalizing machine learning models

Question

Your company built a TensorFlow neural-network model with a large number of neurons and layers. The model fits well for the training data. However, when tested against new data, it performs poorly. What method can you employ to address this?

Options

AThreading
BSerialization
CDropout Methods
DDimensionality Reduction

How the community answered

(37 responses)

A
8% (3)
B
3% (1)
C
73% (27)
D
16% (6)

Explanation

Explanation/Reference: Bad performance of a model is either due to lack of relationship between dependent and independent variables used, or just overfit due to having used too many features and/or bad features. Dropout Methods can show which features are bad. E.g. if it is one feature causing bad performance, then the dropout method will show it, so you can remove it from the model and retrain it.

Topics

#overfitting#dropout regularization#neural networks#model generalization

Community Discussion

No community discussion yet for this question.

Full PROFESSIONAL-DATA-ENGINEER Practice