Comments (2)
Hi @pi-tau, there exist many variations of Transformers, and you can indeed replace the MLP with a different layer like convolution. In Computer Vision, combining convolutional methods with Transformers was a hot topic for a while, e.g. https://arxiv.org/abs/2107.06263. But in general, when you go to scale, it is usually best to give the model full flexibility by only using MLPs, and have the attention as arbitrary ways of communicating. For very small datasets, such inductive biases are more important. This is why RNNs can still beat Transformers when you train them from scratch on very small NLP datasets.
from uvadlc_notebooks.
Update:
I found this paper on text-to-speech and for their FFT module (chap 3.1.) they use an encoder with two convolutional layers as non-linearity instead of the MLP (probably modelling a depthwise separable convolution idk?).
Their argument is that nearby sequence elements are more closely related in the character/phoneme sequence in speech tasks. But with byte pair encoding in language tasks wouldn't it make sense to also use this design?
from uvadlc_notebooks.
Related Issues (20)
- Not really a bug: images don't show well with dark background HOT 2
- Prototypical Network Clarification from Tutorial 16 HOT 2
- Example job script in Guide 1 is depricated on Snellius HOT 1
- [Question] Computing normalization stats for RGB image datasets (CIFAR10, etc.) HOT 2
- [Question] ResNet pre actiovation blocks HOT 2
- [Question] Evaluating the loss for Autoencoders HOT 3
- About the same amount of images in every class HOT 1
- A question about Tutorial 6 - Transformers HOT 2
- test_anom_dataset raised RuntimeError('DataLoader worker (pid(s) {}) exited unexpectedly' HOT 1
- Can PositionalEncoding used with position information? HOT 1
- [Question] Tutorial 11, Variational dequantization HOT 3
- Introduction_to_PyTorch.ipynb: Mean Sigma Formula HOT 1
- Introduction_to_PyTorch.ipynb: Typo HOT 1
- [Question]Tutorial 3(Pytorch, JAX) Test accuracy for the model with sigmoid activation function HOT 2
- Activation_Functions.ipynb : Learning rate Notation
- "Getting runtime error" HOT 2
- New tutorial request to extend Normalizing Flow HOT 1
- unable to use tensorboard in "Tutorial 16: Meta-Learning - Learning to Learn"
- [JAX] Meta Learning Tutorial? 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 uvadlc_notebooks.