Comments (2)
Interesting question. IMHO there a few things that may affect this behavior.
First of all, the NTM is trying to learn a "for loop" and showing only short examples makes it hard for the NTM to generalize.
Second, the parameters of the networks are used more frequently with larger sequence lengths, yielding more stable gradients and making it harder for the network to converge to a local minima that basically memorize the patterns.
Third, the capacity of the network (the number of parameters) plays a role in this as well, in the extreme, with a sequence length of 1 and large capacity, the easiest thing for network to learn is to memorize the inputs instead of learning the rule.
I increased the batch size and decreased the NTM's memory size, and the network with sequence lengths of 1 to 5 converged in less than 30K training samples. There are still fluctuations since the gradients are not stable enough.
./train.py -psequence_max_len=5 -pbatch_size=2 -pmemory_n=20
from pytorch-ntm.
Thank you for your reply.
from pytorch-ntm.
Related Issues (16)
- register_buffer HOT 1
- Strange fluctuation on curves even after large #seqs have been trained with HOT 6
- Why to create a new tensor? HOT 2
- Different results between testing in the mid terms of training and at the end of training HOT 3
- It would be nice if you can add the cuda option HOT 1
- What's the meaning of using memory? HOT 1
- How to change code when each sequence length is different HOT 1
- Why use vague storage
- error in copy-task-plots.ipynb HOT 2
- Cannot reproduce README.md graphs/results on copy task [Commit: 5c5ce66] HOT 1
- Why it runs so slowly?
- Why did each batch has a memory? HOT 1
- How could u write down beta, gamma in your source code? HOT 1
- How to visual the training process and draw these animation? HOT 1
- why need to initialize read vector and memory? HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from pytorch-ntm.