Exam AWS Certified Machine Learning - Specialty topic 1 question 95 discussion

Exam question from Amazon's AWS Certified Machine Learning - Specialty

Question #: 95
Topic #: 1

[All AWS Certified Machine Learning - Specialty Questions]

This graph shows the training and validation loss against the epochs for a neural network.
The network being trained is as follows:
✑ Two dense layers, one output neuron
✑ 100 neurons in each layer
✑ 100 epochs
Random initialization of weights

Which technique can be used to improve model performance in terms of accuracy in the validation set?

A. Early stopping
B. Random initialization of weights with appropriate seed
C. Increasing the number of epochs
D. Adding another layer with the 100 neurons

Show Suggested Answer

Suggested Answer: A 🗳️

by ahquiceno at Feb. 3, 2021, 4:24 p.m.

Disclaimers:

- ExamTopics website is not related to, affiliated with, endorsed or authorized by Amazon.
- Trademarks, certification & product names are used for reference only and belong to Amazon.

Comments

Submit Cancel

ahquiceno

Highly Voted 3 years, 3 months ago

Answer A.

upvoted 22 times

...

eganilovic

Highly Voted 3 years, 2 months ago

The answer is Early Stopping. Stopp the training before accuracy start do decrease.

upvoted 8 times

StelSen

3 years, 2 months ago

Appreciates your explanation. Cheers

upvoted 2 times

...

AIWave

Most Recent 10 months, 2 weeks ago

I will go with A Early stopping is a powerful technique to prevent overfitting. It involves monitoring the model’s performance on a validation dataset during training. If the validation loss starts increasing or plateaus, early stopping stops further training. This ensures that the model doesn’t overfit to the training data. Based on the graph, if the validation loss begins to stagnate or increase after a certain number of epochs, enabling early stopping could lead to better generalization.

upvoted 1 times

...