Neural Network Machine Learning Algorithm

Introduction

Our dataset consisted of 101 different zoo animals with 16 different boolean attributes.

From these attributes, animals were then placed in 1 of 7 categories such as mammal, fish, or insect. The neural network was trained to detect patterns across those attributes placing an animal within its class.

Training Set

neural_net_epochs
  • The neural network passed through the training dataset 50 times.
  • The model was able to achieve an accurary rating of 98.67% on the training set.

Testing Set

poly_kernel_svm
  • The neural network correctly placed an animal its class 96% of the time on the test dataset.
  • Loss was calculated to be .19.