In this project, we use a Deep Learning approach to predict Iris species. It is a multi-class classification problem where each class corresponds to a species of Iris (Iris Setosa, Iris Versicolour and Iris Virginica). The dataset for this project is the famous Iris dataset from UCI Machine Learning Repository.
The final model is a 3-layer neural network that predicts an Iris species with 96.6% accuracy.
Toolkit: Python, TensorFlow, Neural network, Adam optimizer