Skip to content
View dngfra's full-sized avatar

Highlights

  • Pro

Organizations

@tml-epfl

Block or report dngfra

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Showing results

Experiments on continual learning from temporally correlated streams: Markov chain gradient descent during the day, generative replay at night.

1 Updated Nov 1, 2026

Presentation Slides for Developers

TypeScript 49,530 2,279 Updated Nov 5, 2026

The fullstack MCP framework to develop MCP Apps for ChatGPT / Claude & MCP Servers for AI Agents.

TypeScript 10,984 1,551 Updated Nov 17, 2026

Mix and merge spotify playlists

Python 2 Updated Oct 12, 2024

GoodbyeDPI — Deep Packet Inspection circumvention utility (for Windows)

C 28,869 2,262 Updated Jan 19, 2026

Why Do We Need Weight Decay in Modern Deep Learning? [NeurIPS 2024]

Python 74 2 Updated Sep 25, 2024

Continual learning of task-specific approximations of the parameter posterior distribution via a shared hypernetwork.

Python 16 3 Updated Nov 1, 2024

Continual Learning in Recurrent Neural Networks

Python 37 7 Updated Oct 12, 2021

Continual Learning with Hypernetworks. A continual learning approach that has the flexibility to learn a dedicated set of parameters, fine-tuned for every task, that doesn't require an increase in …

Python 172 19 Updated Apr 11, 2022