A hip-actuated monoped can stabilize pitch and energize its hop with the same torque, and its steady-state gait has closed-form fixed points and eigenvalues from hybrid averaging, validated on the Penn Jerboa robot.
Learning representations in Bayesian Confidence Propagation neural networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Unsupervised learning of hierarchical representations has been one of the most vibrant research directions in deep learning during recent years. In this work we study biologically inspired unsupervised strategies in neural networks based on local Hebbian learning. We propose new mechanisms to extend the Bayesian Confidence Propagating Neural Network (BCPNN) architecture, and demonstrate their capability for unsupervised learning of salient hidden representations when tested on the MNIST dataset.
fields
cs.RO 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Hip Energized Monopedal Hopping
A hip-actuated monoped can stabilize pitch and energize its hop with the same torque, and its steady-state gait has closed-form fixed points and eigenvalues from hybrid averaging, validated on the Penn Jerboa robot.