Showing 2026Show all
2 papers · 1 filter
cs.AI2026
Neural networks are more modular than single neurons suggest
Shreya Saha, Benjamin Bergen, Meenakshi Khosla
Neural networks routinely develop representations in which individual neurons contribute to multiple distinct functions, leading to the widespread view that such networks lack modu…
cs.LG2026
Barycentric alignment for instance-level comparison of neural representations
Shreya Saha, Zoe Wanying He, Meenakshi Khosla
Comparing representations across neural networks is challenging because representations admit symmetries, such as arbitrary reordering of units or rotations of activation space, th…