Comparing Neural Network Architectures

After reading François Chollet's wonderful book Deep Learning with Python I became curious about the different neural network architectures and which one is the best for various tasks. I had already thought of getting some practice with word data so I decided to take on the project of classifying the language that a word is written in. The first direction that I think of when working with words is to use recurrent neural networks. Chollet's book also suggests that a series of 1D convolutions could be appropriate. Finally, I found a nice blog post that achieved a similar task using a simple fully connected network. This was the best opportunity to try each of these nice networks on the same project!