Convergence of a New Learning Algorithm
This work addresses convergence analysis for a biologically plausible algorithm, but it is incremental as it builds on an existing method.
The paper investigates the convergence of a new neural network learning algorithm, deriving a necessary and sufficient condition for convergence and proposing a measure to assess its rate, with simulation studies exploring factors like neuron count and synapse strengths.
A new learning algorithm proposed by Brandt and Lin for neural network [1], [2] has been shown to be mathematically equivalent to the conventional back-propagation learning algorithm, but has several advantages over the backpropagation algorithm, including feedback-network-free implementation and biological plausibility. In this paper, we investigate the convergence of the new algorithm. A necessary and sufficient condition for the algorithm to converge is derived. A convergence measure is proposed to measure the convergence rate of the new algorithm. Simulation studies are conducted to investigate the convergence of the algorithm with respect to the number of neurons, the connection distance, the connection density, the ratio of excitatory/inhibitory synapses, the membrane potentials, and the synapse strengths.