Thanks to visit codestin.com
Credit goes to www.scribd.com

Scribd
Upload
20 views1 page

Deep Learning Paper 3 Solutions

Uploaded by

Abhishek Banaj
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
20 views1 page

Deep Learning Paper 3 Solutions

Uploaded by

Abhishek Banaj
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 1

Deep Learning and Neural Networks:

Exam Paper 3 Solutions


SECTION III

3(a) What is Transfer Learning in Deep Learning?


Transfer Learning is a machine learning technique where a model trained on one task is
reused (in whole or part) for another task. This technique is especially useful when you
have limited data for the new task but the tasks are related. Transfer learning leverages the
learned features from a pre-trained model (like ImageNet) and fine-tunes it for a new,
similar task.

3(b) Explain the Concept of Batch Normalization


Batch Normalization is a technique to improve the training of deep neural networks by
normalizing the inputs to each layer. By reducing internal covariate shift, it improves the
training speed and performance. It normalizes inputs for each mini-batch, ensuring a mean
of zero and variance of one, followed by scaling and shifting operations.

3(c) Use Cases of Autoencoders in Deep Learning


Autoencoders are neural networks designed for learning efficient representations of data
(encoding). They are commonly used in:
1. Data Compression
2. Noise Reduction
3. Anomaly Detection
4. Image Generation
5. Feature Extraction.

You might also like