Detection and removal of biases from brain MRI using adversarial architectures. This was my final project for CS 231n (Convolutional Neural Networks for Visual Recognition) at Stanford.
-
Updated
Nov 12, 2018 - Jupyter Notebook
#
bias-removal
Here are 2 public repositories matching this topic...
Neural patching of Mistral models via MLP.down_proj to bypass RLHF constraints – without touching the LM_HEAD.
reverse-engineering torch transformer neurons mistral redteaming ai-security open-source-intelligence bias-removal neural-engineering prompt-tuning llm rlhf ai-security-tool neuropatching tokenrouting downproj decoder-routing
-
Updated
Jul 5, 2025 - HTML
Improve this page
Add a description, image, and links to the bias-removal topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the bias-removal topic, visit your repo's landing page and select "manage topics."