Current Mode Euclidean Distance Calculation Circuit for Kohonen's Neural Network Implemented in CMOS 0.18�m Technology

2007 ◽  
Author(s):  
Tomasz Talaska ◽  
Rafal Dlugosz
Keyword(s):  
Neural Network ◽  
Euclidean Distance ◽  
Current Mode ◽  
Distance Calculation ◽  
Kohonen’S Neural Network

An Event-Based Neural Network Architecture with Content Addressable Memory

2020 ◽  
Vol 11 (1) ◽  
pp. 23-40 ◽  
Author(s):  
Sivaganesan S ◽  
Maria Antony S ◽  
Udayakumar E
Keyword(s):  
Neural Network ◽  
Network Architecture ◽  
Large Scale ◽  
Synaptic Weight ◽  
Current Mode ◽  
Spike Timing ◽  
Event Representation ◽  
Content Addressable Memory ◽  
Neural Computations ◽  
Scale Integration

A hybrid analog/digital very large-scale integration (VLSI) implementation of a spiking neural network with programmable synaptic weights was designed. The synaptic weight values are stored in an asynchronous module, which is interfaced to a fast current-mode event-driven DAC for producing synaptic currents with the appropriate amplitude values. It acts as a transceiver, receiving asynchronous events for input, performing neural computations with hybrid analog/digital circuits on the input spikes, and eventually producing digital asynchronous events in output. Input, output, and synaptic weight values are transmitted to/from the chip using a common communication protocol based on the address event representation (AER). Using this representation, it is possible to interface the device to a workstation or a microcontroller and explore the effect of different types of spike-timing dependent plasticity (STDP) learning algorithms for updating the synaptic weights values in the CAM module.

Simulation of a novel, optically addressable, switched-current/continuous-time, current-mode cellular neural network

1995 ◽  
Vol 31 (7) ◽  
pp. 563-564 ◽  
Author(s):  
G. O'Sullivan ◽  
E. McCabe ◽  
J. Hegarty ◽  
P. Horan ◽  
B. Kelly ◽  
...  
Keyword(s):  
Neural Network ◽  
Continuous Time ◽  
Current Mode ◽  
Cellular Neural Network ◽  
Switched Current

Plant Disease Detection and Classification Using Bacteria Foraging Optimization Algorithm Through Convolution Neural Network

2020 ◽  
Vol 17 (8) ◽  
pp. 3567-3576
Author(s):  
Venigalla Sai Teja ◽  
Chilakapati Srinivas ◽  
P. Radhika
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Euclidean Distance ◽  
Plant Diseases ◽  
Prompt Action ◽  
The Right ◽  
Measurement Metric ◽  
Bacteria Foraging Optimization Algorithm ◽  
Advanced Model

Humans can recognize the plants infected by diseases but separated from our visual perception it is hard to recognize plant diseases. In croplands without taking the right care and prompt action, the entire field may become a region afflicted by diseases. So we identify the plant diseases ahead of time with the assistance of present-day computer technologies. An advanced model was introduced to accurately recognize and classification plant diseases. Here we proposed an approach that can use the Convolutional Neural Network (CNN) based on BFOA for distinguishing diseases in plants. The input picture for the extraction of features is divided into 3 clusters by the Euclidean distance measurement metric of the k-mean algorithm and from the ROI, parameters of the GLCM matrix are calculated in the same cluster prior to BFOA. Assigning matrix parameters as BFOA input improves the network’s accuracy and efficiency in determining. In classification, we proposed a Convolutional Neural Network (CNN) using ResNet50 as a pre-trained network in deep learning toolbox which classifies from a given dataset. The approach is more reliable as the detection and classification of plant diseases are more precise.

Sign in / Sign up

Export Citation Format

Share Document