New Digital Architecture of CNN for Pattern Recognition

Abstract

New Digital Architecture of CNN for Pattern RecognitionThe paper deals with the design of a new digital CNN (Cellular Neural Network) architecture for pattern recognition. The main parameters of the new design were the area consumption of the chip and the speed of calculation in one iteration. The CNN was designed as a digital synchronous circuit. The largest area of the chip belongs to the multiplication unit. In the new architecture we replaced the parallel multiplication unit by a simple AND gate performing serial multiplication. The natural property of this method of multiplication is rounding. We verified some basic properties of the proposed CNN such as edge detection, filling of the edges and noise removing. At the end we compared the designed network with other two CNNs. The new architecture allows to save till 86% gates in comparison with CNN with parallel multipliers.

Online Gear Wear Particle Detection and Categorization Using a Convolutional Neural Network Algorithm Integrated with Cascade Classifier

“…To hasten model convergence and raise classification accuracy, several techniques were used, including data augmentation, batch normalization, number and size modification of convolution kernels, and loss function optimization. A new digital CNN (Cellular Neural Network) architecture for pattern recognition was introduced by Raschman et al in their study [18]. The chip's area consumption and the computation speed per iteration were the two key design factors.…”

CNN-LSTM Prediction Method for Blood Pressure Based on Pulse Wave

“…Therefore, we consider introducing Convolutional Neural Networks (CNN) for features extraction. Generally, CNN can be used in the field of pattern recognition [20,21], natural language processing [22,23] and computer vision [24,25]. Furthermore, taking into account that PW is a time sequence, we can introduce the Long Short-Term Memory (LSTM) network to further process the features.…”