4 papers
Stochastic Forward-Forward Learning through Representational Dimensionality Compression
Zhichao Zhu, Yang Qi, Hengyuan Ma +2
The Forward-Forward (FF) learning algorithm provides a bottom-up alternative to backpropagation (BP) for training neural networks, relying on a layer-wise "goodness" function with…
Optimal signal transmission and timescale diversity in a model of human brain operating near criticality
Yang Qi, Jiexiang Wang, Weiyang Ding +4
Cortical neurons exhibit a hierarchy of timescales across brain regions in response to input stimuli, which is thought to be crucial for information processing of different tempora…
Learn to integrate parts for whole through correlated neural variability
Zhichao Zhu, Yang Qi, Wenlian Lu +1
Sensory perception originates from the responses of sensory neurons, which react to a collection of sensory signals linked to various physical attributes of a singular perceptual o…
Probabilistic computation and uncertainty quantification with emerging covariance
Hengyuan Ma, Yang Qi, Li Zhang +2
Building robust, interpretable, and secure AI system requires quantifying and representing uncertainty under a probabilistic perspective to mimic human cognitive abilities. However…