Parallel Synapses with Transmission Nonlinearities Enhance Neuronal Classification Capacity
This paper shows that neurons with multiple nonlinear synapses can classify data better than a Perceptron and improve test accuracy in MNIST classification.
Author
University of California San DiegoORCID 0000-0002-4897-6956Unclaimed ORCID profile · follow to get notified of new preprints
3 papers
Recent·Most cited
This paper shows that neurons with multiple nonlinear synapses can classify data better than a Perceptron and improve test accuracy in MNIST classification.
Qiurui Zeng, Wei Tian, Amit Klein…·Joseph R. Ecker
The paper maps epigenetic and spatial transcriptomic changes in aging mouse brain using single-cell multi-omic data and develops deep-learning models to predict age-related gene expression changes.
Yuru Song, Mingchen Yao, Helen Kemprecos…·Zhe Sage Chen
This paper develops predictive coding models to study pain perception by analyzing neural activity in rats, revealing insights into how expectation and chronic pain influence neural dynamics.