News for hackers. Stuff that matters.
Re:The Computational Power of Biological Dendritic Trees by bionhoward on Tuesday September 08, 2020 @11:08AM (#24409157)
Nice paper, this could motivate more sophisticated ANN models vs multiply-add-activation paradigm
Re:The Computational Power of Biological Dendritic Trees by cblconfederate on Tuesday September 08, 2020 @01:15PM (#24410463)
In reality, this itself is an ANN with multiply-add-activation. They basically model an imaginary dendritic tree as a hierarchy of convolutional networks which converge to the dendrite trunk. It's however very far from biological plausibility.