Training neural networks with ant colony optimization algorithms for pattern classification

Abstract

Feed-forward neural networks are commonly used for pattern classification. The classification accuracy of feed-forward neural networks depends on the configuration selected and the training process. Once the architecture of the network is decided, training algorithms, usually gradient descent techniques, are used to determine the connection weights of the feed-forward neural network. However, gradient descent techniques often get trapped in local optima of the search landscape. To address this issue, an ant colony optimization (ACO) algorithm is applied to train feed-forward neural networks for pattern classification in this paper. In addition, the ACO training algorithm is hybridized with gradient descent training. Both standalone and hybrid ACO training algorithms are evaluated on several benchmark pattern classification problems, and compared with other swarm intelligence, evolutionary and traditional training algorithms. The experimental results show the efficiency of the proposed ACO training algorithms for feed-forward neural networks for pattern classification.

Risk-Averse Caching Policies for YouTube Content in Femtocell Networks using Density Forecasting

“…For general transfer functions h(x f ), (17) is a non-convex and non-linear optimization problem that is commonly solved using stochastic gradient decent, ant-colony optimization, and simulated anealling methods [37], [38], [39].…”

Literature Review on Big Data Analytics Methods

“…The method has been created biologically from real ant behavior in food-seeking pattern. In other words, this bionic algorithm has been deployed for finding the optimal path [44]. The process is that when ants start to seek food they deposit a chemical material on the ground, which is known as pheromone while they are moving toward food source.…”

Evolving neural networks using bird swarm algorithm for data classification and regression applications

“…In [57,82], the authors introduced an Ant Colony Optimization algorithm (ACO) to solve the continuous optimization. The work was applied to learning of MLP networks, and evaluated using different data classification problems.…”

“…Meta-heuristic learning has the ability to estimate optimal or semi-optimal connection weights set for ANNs with less probability to be trapped into the many local optima in the search space [4,35,80]. Many meta-heuristic learning algorithms have been used to train ANNs such as Genetic Algorithm (GA) [66,76], Particle Swarm Optimization (PSO) [101], Evolutionary Strategies (ES) [90], Ant Colony Optimization (ACO) [57], Cuckoo Search (CS) [68,86], Krill Herd Optimization (KH) [25,48], Firefly Algorithm (FA) [19], Population-Based Incremental Learning (PBIL) [30], Differential Evolution (DE) [42,88], Artificial Bee Colony (ABC) [45], and many others.…”