Caterpillar Net represents maxima with two hidden layers
The nonrecursive construction uses hidden-layer widths O(N squared) and 2 to the O(N log N).
Stories per day · 30 days
Relatedchua1dynamical-systems1expressivity1fixed-points1model-reduction1neural-networks1recurrent-neural-networks1relu-networks1
2 stories, newest first · one card per story
Stories tagged #piecewise-linear
From Redundancy to Minimality: Fixed-Point-Guided Hierarchical Reduction of Learned Piecewise-Linear Dynamics
Fixed-point-guided reduction turns redundant AL-RNNs into minimal dynamics, lifting Chua success from 20% to 71%.