Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Scribd
Upload
2 views

Module 04 - Learners Guide

The document discusses the application of deep learning in computer vision, highlighting the transition from hand-crafted features to end-to-end neural network training. It emphasizes the importance of processing data to ensure linear separability of classes in the final output. Additionally, it includes a confidentiality notice regarding the proprietary nature of the content.

Uploaded by

blackythekarpie
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
2 views

Module 04 - Learners Guide

The document discusses the application of deep learning in computer vision, highlighting the transition from hand-crafted features to end-to-end neural network training. It emphasizes the importance of processing data to ensure linear separability of classes in the final output. Additionally, it includes a confidentiality notice regarding the proprietary nature of the content.

Uploaded by

blackythekarpie
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 101

Deep Learning and Usage in Computer Vision

•
•
•
•
–

•
•
–

–
–
•
•
•
•
•
•

•
•
•
•
•
•

•
•
–

–
Ans

Input Extract Concatenate into Linear


Pixels Hand-Crafted a vector x Classifier
Features

Figure: Karpathy 2016


Slide from Karpathy 2016
This piece is just a linear classifier

Ans
(GoogLeNet)

Input Perform everything with a big neural


Pixels network, trained end-to-end

Key: perform enough processing so that by the time you get


to the end of the network, the classes are linearly separable
Linear
Classifier

(2D visualization using t-SNE) [Donahue, “DeCAF: DeCAF: A Deep Convolutional …”, arXiv 2013]
•
–
–
–
•

•
•

–
–

–
•

•
–
•

•
•

•
•
–
–
–
–

•
–
THANK YOU
FIND OUT MORE
www.tataelxsi.com

Confidentiality Notice
This document and all information contained herein is the sole property of Tata Elxsi Ltd.
No intellectual property rights are granted by the delivery of this document or the disclosure of its content.
This document shall not be reproduced or disclosed to a third party without the express written consent of Tata Elxsi Ltd.
This document and its content shall not be used for any purpose other than that for which it is supplied.

You might also like