# Equivalent Neural Network in Keras to Multinomial Logistic Regression Using VGG16 Bottleneck features

In the Kaggle Dog Breed Identification kernel:

https://www.kaggle.com/gaborfodor/dog-breed-pretrained-keras-models-lb-0-3

The bottleneck features from the VGG16 model (using Keras) are feed into a multinomial logistic regression in order to achieve a validation accuracy of 91.8%. How would I make the equivalent Neural Network to this multinomial logistic regression. I have tried the following:

model = Sequential()