A novel high-speed neural model for fast pattern recognition

Abstract

Neural networks have shown good results for detecting a certain pattern in a given image. In this paper, faster neural networks for pattern detection are presented. Such processors are designed based on cross-correlation in the frequency domain between the input matrix and the input weights of neural networks. This approach is developed to reduce the computation steps required by these faster neural networks for the searching process. The principle of divide and conquer strategy is applied through matrix decomposition. Each matrix is divided into smaller in size sub-matrices and then each one is tested separately using a single faster neural processor. Furthermore, faster pattern detection is obtained using parallel processing techniques to test the resulting submatrices at the same time using the same number of faster neural networks. In contrast to faster neural networks, the speed up ratio is increased with the size of the input matrix when using faster neural networks and matrix decomposition. Moreover, the problem of local sub-matrix normalization in the frequency domain is solved. The effect of matrix normalization on the speed up ratio of pattern detection is discussed. Simulation results show that local sub-matrix normalization through weight normalization is faster than sub-matrix normalization in the spatial domain. The overall speed up ratio of the detection process is increased as the normalization of weights is done off line.

Analog–Digital Hybrid Memristive Devices for Image Pattern Recognition with Tunable Learning Accuracy and Speed

“…High accuracy can eliminate disturbances, which helps to obtain correct detection and recognition of information . In contrast, the realization of high speed can greatly improve the efficiency of whole pattern recognition system, especially for the applications of real‐time systems such as mobile or highly variable objects (such as faces, cars, and doors) . In memristor‐based pattern recognition, its learning accuracy and speed are closely related to the changing behavior of the device's conductance, which can be classified into two types, analog and digital resistive switching (A‐RS and D‐RS), depending on whether the change in the resistance state is continuous or discrete.…”

Enhancing the Diagnosis of Depression and Anxiety Through Explainable Machine Learning Methods

“…Accurate diagnostic processes are crucial for treatment, in the realm of health given the challenges associated with precise psychiatric diagnoses owing to the overlapping symptoms of various mental illnesses making it difficult to differentiate or diagnose them accurately. This is to get the right psychiatric diagnosis before starting any treatment plan [31][32][33][34][35][36][37][38][39][40][41][42][43][44][45][46][47][48][49].…”