Deep Neural Learning Adaptive Sequential Monte Carlo forAutomatic Image and Speech Recognition

To enhance the performance of image classification and speech recognition, the optimizer is considered an important factor forachieving high accuracy. (e state-of-the-art optimizer can perform to serve in applications that may not require very highaccuracy, yet the demand for high-precision image classification and speech recognition is increasing. (is study implements anadaptive method for applying the particle filter technique with a gradient descent optimizer to improve model learning per-formance. Using a pretrained model helps reduce the computational time to deploy an image classification model and uses a simple deep convolutional neural network for speech recognition. (e applied method results in a higher speech recognition accuracy score—89.693% for the test dataset—than the conventional method, which reaches 89.325%. (e applied method also performs well on the image classification task, reaching an accuracy of 89.860% on the test data set, better than the conventional method, which has an accuracy of 89.644%. Despite a slight difference in accuracy, the applied optimizer performs well in this data set overall.