Comments (2)
Ok. Thanks for letting me know. My understanding is that the chaser loss encourages the MAML models to be diverse which leads the predicted uncertainty to be meaningful. Basically, modifying the loss function to encourage diverse MAML models is important. This might not have been fair to Bayesian MAMl.
Still, great work and thanks for sharing the code.
Deep
from few_shot_meta_learning.
Hi Deep,
You are right. I only implemented the simple cross-entropy loss for BMAML. I cannot recall exactly, but I think the chaser loss can be implemented for other meta-learning methods. Hence, I decided to use cross-entropy loss to fairly compare BMAML to other meta-learning algorithms.
from few_shot_meta_learning.
Related Issues (15)
- Some questions about this code. HOT 1
- Loss is NaN in PLATIPUS HOT 2
- Platipus loss function potentially doesn't match paper HOT 2
- Question about the implementation of VAMPIRE HOT 4
- test in Platius model HOT 2
- NaN loss when training with sine HOT 4
- error in Platipus model with sineline data source
- Models not training HOT 4
- Potential Problem of the loss function in ABML HOT 2
- Question about the initialization of theta0 in abml HOT 4
- First order approximate typo? HOT 1
- getting NaN's in ABML at about epoch 14 HOT 4
- Consultation about the code HOT 1
- Regression code HOT 3
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 few_shot_meta_learning.