Investigation of Effectiveness of Shuffled Frog-Leaping Optimizer in Training a Convolution Neural Network

Abstract

One of the leading algorithms and architectures in deep learning is Convolution Neural Network (CNN). It represents a unique method for image processing, object detection, and classification. CNN has shown to be an efficient approach in the machine learning and computer vision fields. CNN is composed of several filters accompanied by nonlinear functions and pooling layers. It enforces limitations on the weights and interconnections of the neural network to create a good structure for processing spatial and temporal distributed data. A CNN can restrain the numbering of free parameters of the network through its weight-sharing property. However, the training of CNNs is a challenging approach. Some optimization techniques have been recently employed to optimize CNN’s weight and biases such as Ant Colony Optimization, Genetic, Harmony Search, and Simulated Annealing. This paper employs the well-known nature-inspired algorithm called Shuffled Frog-Leaping Algorithm (SFLA) for training a classical CNN structure (LeNet-5), which has not been experienced before. The training method is investigated by employing four different datasets. To verify the study, the results are compared with some of the most famous evolutionary trainers: Whale Optimization Algorithm (WO), Bacteria Swarm Foraging Optimization (BFSO), and Ant Colony Optimization (ACO). The outcomes demonstrate that the SFL technique considerably improves the performance of the original LeNet-5 although using this algorithm slightly increases the training computation time. The results also demonstrate that the suggested algorithm presents high accuracy in classification and approximation in its mechanism.

Deep learning health management diagnostics applied to the NIST smoke experiments

“…However, the jump to three rooms worth of data results in a significant jump in accuracy, getting much closer to the acceptable levels. The main steps of this work have been revised due to these references (Ranjbarzadeh et al, 2021;Anari et al, 2022;Ranjbarzadeh et al, 2022;Saadi et al, 2022;Ranjbarzadeh et al, 2023a;Ranjbarzadeh et al, 2023b).…”

Point-of-Interest Preference Model Using an Attention Mechanism in a Convolutional Neural Network

“…In the context of data mining and analysis, deep learning models (DLs) are currently paving new avenues for POI recommendation systems. Unlike the earlier shallow neural network approaches, such as artificial neural networks (ANNs) that have been under exploration for many years, DL-based structures are characterized using a considerably amplified number of continuously linked neural layers [ 48 , 49 , 50 , 51 ]. This amplified number of layers is able to mine hidden patterns and higher-level features and can discover more difficult and hierarchical relationships.…”

Knowledge Graph Completion Based on Entity Descriptions in Hyperbolic Space

“…In order to explore the influence of E 1 , E 2 , E 3 , and E 4 on the energy function E, the score functions Φ 1 , Φ 2 , Φ 3 , and Φ 4 are defined. The DMuRPss without containing entity descriptions is used as the baseline, and the DMuRPss score function is defined as Φ 1 , Equation (12). It is worth noting that Φ 1 is also the definition of the MuRP [18] score function.…”

“…For translation models and bilinear models, the models are relatively simple, and it is difficult to fully explore the relationship between triple entities. Neural network models and rotation models often need to spend more memory space to express the embeddings of entities to obtain more semantic information [12][13][14]. In order to reduce the demand for memory space, in recent years, hyperbolic models have gradually attracted attention in hyperbolic space [15,16].…”