Check out the #NeuroAI projects from the Impact Scholars Program! https://airtable.com/appbxcAKe1D5c5xwY/tblA6aWdM4mVjXIqH/viwaYt2Hk85zFUyiM

🤓 Learn more about:

• Biological Connectivity Patterns as a Blueprint for Efficient Neural Architectures in Reinforcement Learning
• How #AI Learns to Move like Us
• Dynamical Similarity in Multitasking RNNs: Identifying Shared Motifs Across Task Periods
• How Machines Learn to Think in Order

#ImpactScholars #ComputationalNeuroscience #Innovation #Neuromatch #AIforGood #MachineLearningResearch

Has anyone conducted their own experiments with training data extraction from offline-LLMs via repeated words ala Nasr, et al.'s "Scalable Extraction of Training Data from (Production) Language Models"? I'd be interested in acquiring your code. I want to conduct a more formal mathematical analysis of the phenomenon, but I'd like to peek under the hood a bit more first.

Ref: https://arxiv.org/abs/2311.17035

#MachineLearning #DeepLearning #AdversarialAttacks #MachineLearningResearch #AIResearch #AI