How many parameters are present in the provided convolutional neural network architecture designed for digit recognition on MNIST, where the input consists of $32$x$32$ images, the first convolutional layer has $655$ filters with a stride of $1,$ followed by max pooling of size $22$ with a stride of $2,$ the second convolutional layer employs $1655$ filters with a stride of $1,$ followed by max pooling of size $22$ with a stride of $2,$ and the fully connected layers consist of $120,84,$ and $10$ neurons respectively in the subsequent layers?

Hint: Parameters of fully connected layers $=$ Input Size X Output Size of the layer

Write the final answer in the answer box.