Table of contents

NaN.

TutorialDeep LearningLast updated

Pointer Networks[ Edit ]

- The paper introduces a novel architecture that generates an output sequence such that the elements of the output sequence are discrete tokens corresponding to positions in the input sequence.
- Such a problem can not be solved using Seq2Seq or Neural Turing Machines as the size of the output softmax is variable (as it depends on the size of the input sequence).
- Link to the paper

- Traditional attention-base sequence-to-sequence models compute an attention vector for each step of the output decoder and use that to blend the individual context vectors of the input into a single, consolidated attention vector. This attention vector is used to compute a fixed size softmax.
- In Pointer Nets, the normalized attention vector (over all the tokens in the input sequence) is normalized and treated as the softmax output over the input tokens.
- So Pointer Net is a very simple modification of the attention model.

- Any problem where the size of the output depends on the size of the input because of which fixed length softmax is ruled out.
- eg combinatorial problems such as planar convex hull where the size of the output would depend on the size of the input.

- The paper considers the following 3 problems:
- Convex Hull
- Delaunay triangulations
- Travelling Salesman Problem (TSP)
- Since some of the problems are NP hard, the paper considers approximate solutions whereever the exact solutions are not feasible to compute.
- The authors used the exact same architecture and model parameters of all the instances of the 3 problems to show the generality of the model.
- The proosed Pointer Nets outperforms LSTMs and LSTMs with attention and can generalise quite well for much larger sequences.
- Interestingly, the order in which the inputs are fed to the system affects its performance. The authors discussed this apsect in their subsequent paper titled Order Matters: Sequence To Sequence for Sets

Read more…(311 words)

About the contributor:

Shagun SodhaniAnalytics and Data Science team @ Adobe Systems

100%

Loading…

Join the discussion. Add a reply…

Post

Table of contents

- Introduction
- Architecture
- Application
- Evaluation

Contributor

Shagun SodhaniAnalytics and Data Science team @ Adobe Systems

100%

Ready to join our community?

Sign up below to automatically get notified of new courses, get **reminders** to finish ones you subscribe to, and **bookmark** lessons to read later.

Continue with Facebook

— OR —

Your Full Name

Email address

I have an account. Log in instead

By signing up, you agree to our Terms and our Privacy Policy.

Popular Courses

New Courses

About Us

Get in touch

Copyright 2016-18, Compose Labs Inc. All rights reserved.