Efficient dendritic learning as an alternative to synaptic plasticity hypothesis

Synaptic plasticity is a long-lasting core hypothesis of brain learning that suggests local adaptation between two connecting neurons and forms the foundation of machine learning. The main complexity of synaptic plasticity is that synapses and dendrites connect neurons in series and existing experiments cannot pinpoint the significant imprinted adaptation location. We showed efficient backpropagation and Hebbian learning on dendritic trees, inspired by experimental-based evidence, for sub-dendritic adaptation and its nonlinear amplification. It has proven to achieve success rates approaching unity for handwritten digits recognition, indicating realization of deep learning even by a single dendrite or neuron. Additionally, dendritic amplification practically generates an exponential number of input crosses, higher-order interactions, with the number of inputs, which enhance success rates. However, direct implementation of a large number of the cross weights and their exhaustive manipulation independently is beyond existing and anticipated computational power. Hence, a new type of nonlinear adaptive dendritic hardware for imitating dendritic learning and estimating the computational capability of the brain must be built.

Automated summary

Synaptic plasticity is a core hypothesis in brain learning and forms the foundation of machine learning. By simulating experimental evidence, we demonstrate efficient backpropagation and Hebbian learning on dendritic trees, achieving deep learning and near-perfect recognition rates for handwritten digits. Dendritic amplification enhances success rates through increased input crosses and higher-order interactions. However, the manipulation of a large number of cross weights is beyond current computational capabilities, calling for the development of nonlinear adaptive dendritic hardware.