Overparameterization and overfitting are common concerns when designing and training deep neural networks. Network pruning is an effective strategy used to reduce or limit the network complexity, but often suffers from time and computational intensive procedures to identify the most important connections and best performing hyperparameters. We s…

Implementation of dichotomous search algorithm in MATLAB

This repository contains a collection of MATLAB scripts that implement some of the classical optimization methods for unconstrained optimization models: Steepest-Descent, Newton method, Gauss-Newton, Conjugate Gradient method, Fibonacci search, Golden-section search, Dichotomous search and Exhaustive search.