UCB icon indicating copy to clipboard operation
UCB copied to clipboard

Original PyTorch implementation of Uncertainty-guided Continual Learning with Bayesian Neural Networks, ICLR 2020

Results 8 UCB issues
Sort by recently updated
recently updated
newest added

Change .cuda to .to(device) to make it compatible with GPUs other than cuda:0

First, thank you for the great work! I really like the ideas you presented with UCB, which is why I looked at your code in detail and stumbled across the...

Hello, I was trying to find out the code to reproduce the results from Table 3, specifically the implementation for single-head results, but it doesn't look like it is available...

Hi, congrats on the paper! I was trying to re-run the code with UCB method on cifar10/cifar100 test case, but it seems like the testing on cifar10 is much higher...

amazing network btw

Thanks for the great work! Do you think that your work can also be applied to deep reinforcement learning? And if so, do you have an idea what would be...

Congrats on the awesome work, you really present a useful and yet simple method. However, I still have an question regarding the algorithm : Since the update is based on...

Is there any Tensorflow Probability-based implementation of the uncertainty based change in learning rates, that uses Flipout layers?