Explore the behaviors of five supervised learning techniques on the MNIST dataset and a toy dataset.

• 1). decision trees (DT),
• 2). neural networks (NN),
• 3). boosted trees (BST-DT),
• 4). support vector machines (SVM),
• 5). k-nearest neighbors (kNN).

• To run experiments, run MNIST_ML.py

• Trained and tested on:

Python 2.7
NumPy 1.16.4
tensorflow 1.14.0
scikit-learn 0.20.3