1 citations · 1 across the 4 of their papers we have counts for
4 papers
Continual-learning rules shape representational drift
Yikai Si, Shanshan Qin
Lifelong learning requires acquiring new knowledge without erasing the old. Yet neural population codes for familiar stimuli and behaviors change over days and weeks. This coexiste…
A Network of Biologically Inspired Rectified Spectral Units (ReSUs) Learns Hierarchical Features Without Error Backpropagation
Shanshan Qin, Joshua L. Pughe-Sanford, Alexander Genkin +4
We introduce a biologically inspired, multilayer neural architecture composed of Rectified Spectral Units (ReSUs). Each ReSU projects a recent window of its input history onto a ca…
The Principle of Isomorphism: A Theory of Population Activity in Grid Cells and Beyond
Maoshen Xu, Fei Song, Bailu Si +1
Neural population activity organizes into low-dimensional manifolds embedded within high-dimensional state spaces, yet the principles governing the topology and geometry of these m…
Contrastive Similarity Matching for Supervised Learning
Shanshan Qin, Nayantara Mudur, Cengiz Pehlevan
We propose a novel biologically-plausible solution to the credit assignment problem motivated by observations in the ventral visual pathway and trained deep neural networks. In bot…