Abstract
The most popular technique for classifying images now is the convolutional neural network. During its training, it is crucial to adjust two factors: the learning rate and gradient. The pre-processing phases involve the fuzzy clustering approach. To change the learning rate, two Event-Based control loops called E (Exponential) and PD (Proportional Derivative)-Control are used. An exponential control loop is employed to prevent an abrupt decline in learning rate as the model gets closer to its ideal state. The learning rate is used by the proportional derivative control loop to determine when to move on to the subsequent data batch. The weight is updated using the back propagation approach based on the loss value that was determined. The proposed method improves the performance with an Accuracy of 96.8%.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
