Deep Learning Neural Network: Complex vs. Simple Model

Recently I wrote a blog titled "Pneumonia Detection From X-ray Images Using Deep Learning Neural Network" where I presented the results of what I chose to be the best out of 15 different model architectures that I created to solve a binary classification problem. For the readers not familiar with this, what it means is that my model will predict only a "0" or a "1". Before I continue, don't worry if you have not read my previous blog, you won't need it to understand this one as this will have all the necessary information to compare as the title says, a complex to a simple model. On my previous blog I described how I started with a simple 2-layer Convolutional Neural Network (CNN) model using minimal parameters to account for overfitting, and ended up with a more complex architecture made out of 5 convolutional blocks, each one, with dual layers and with some hyper-parameters to tune the model. This last model I called it Model_15, which resulted with a validation and Test accuracy of 94.83 and 90.84% respectively.