Single-parameter Monte Carlo mutation-selection trains deep networks and a simple Transformer on MNIST and Tiny Shakespeare without backpropagation.
A Global Algorithm for Training Multilayer Neural Networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
We present a global algorithm for training multilayer neural networks in this Letter. The algorithm is focused on controlling the local fields of neurons induced by the input of samples by random adaptations of the synaptic weights. Unlike the backpropagation algorithm, the networks may have discrete-state weights, and may apply either differentiable or nondifferentiable neural transfer functions. A two-layer network is trained as an example to separate a linearly inseparable set of samples into two categories, and its powerful generalization capacity is emphasized. The extension to more general cases is straightforward.
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Beyond Backpropagation: Monte Carlo Method Can Train Deep Neural Networks
Single-parameter Monte Carlo mutation-selection trains deep networks and a simple Transformer on MNIST and Tiny Shakespeare without backpropagation.