GitHub - mikeg5/concrete-strength-prediction-keras-NN: This project uses a dataset of over 1000 concrete samples with 9 predictor variables and tries to predict the strength using a neural network in keras. The model uses 1 hidden layer with 10 nodes, a ReLU activation function with ADAM optimizer, and trains the data using 50 epochs then 100 epochs and then 3 hidden layers.

mikeg5 / concrete-strength-prediction-keras-NN Public

Notifications You must be signed in to change notification settings
Fork 0
Star 1

This project uses a dataset of over 1000 concrete samples with 9 predictor variables and tries to predict the strength using a neural network in keras. The model uses 1 hidden layer with 10 nodes, a ReLU activation function with ADAM optimizer, and trains the data using 50 epochs then 100 epochs and then 3 hidden layers.