Comments (5)
Hi, @JoyHuYY1412, just a average over all the tasks. No we havent used any normalizations.
See
Line 163 in e56e72b
from itaml.
Hi, @JoyHuYY1412, just a average over all the tasks. No we havent used any normalizations.
See
Line 163 in e56e72b
Thank you for your reply.
So if different tasks have parameters of different scales, e.g, A>>B, it seems the averaged network will be biased toward A. So when we try to recover the network for task B, we assume the memory samples of B can help fit? I don't know do I understand correctly.
from itaml.
Yes, that's one reason the classifier for a task is trained only in the inner loop. Also, to minimize the biased model we take a weighted average of the weights as we progress. Yes, finetuning with the memory samples helps to get a better model.
from itaml.
Yes, that's one reason the classifier for a task is trained only in the inner loop. Also, to minimize the biased model we take a weighted average of the weights as we progress.
Thank you so much. I have two more questions.
- I read the pseudo code (algorithm 1) in your paper, so after we update phi in line 14, does the theta used in line 7 for task 1 is initialized from the updated phi ? and then task 2 initialized its theta from task 1?
- If so, does this operation somehow relieve the imbalance between tasks? Since after each update in the outer loop, the backbone network is reset.
from itaml.
- No, in the inner loop theta for all tasks are initialized with last updated phi, and once we learned all thetas we combine them to get the new phi, which is later used to initialize thetas for the next batch.
- Yes, the outer loop meta updated tries to minimize the forgetting, while imbalance is minimized mostly because of the exponential averaging of the weights.
from itaml.
Related Issues (20)
- a few question about the implementation HOT 8
- AttributeError: type object 'args' has no attribute 'overflow' HOT 2
- something wrong happends in training cifar10 HOT 3
- Where to check task accuracy and class accuracy? HOT 2
- Fair comparison HOT 2
- sys.argv[1] is out of range HOT 2
- train_mnist loss go to nan at Sess 3
- about adding classes HOT 2
- Nan Loss during training MNIST dataset HOT 2
- Why BCE is used instead of CE with Softmax? HOT 1
- Something strange in the Algorithm 1.. HOT 4
- Something strange about the update of theta and psi in the inner loop HOT 6
- What is the difference between two output of model? -->outputs2, outputs = model(inputs) HOT 1
- Training script for ImageNet-100 HOT 2
- Running without CUDA HOT 2
- Code for other methods
- Obviously catastrophic forgetting HOT 3
- A question about theta and task-specific phi HOT 1
- Task prediction
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 itaml.