Automobile DataSet

to explore Regression algorithms:

• simple linear regression
• multiple linear regression
• neural net regression

Handwritten Digits - images with handwritten digits

to explore classification algorithms:

• linear classifiers
• k-nearest neighbors
• non-linear classifiers
• SVMs
• convolutional neural nets

Dataset Homepage - images of animals, planes and ground vehicles

• convolutional neural nets

• 60000 32x32 color images
• 10 classes, with 6000 images per class
• 50000 training images and 10000 test images

• 60000 32x32 color images
• 100 classes containing 600 images each

• 500 training images and 100 testing images per class

• 100 classes are grouped into 20 superclasses
• each image comes with a “fine” label (the class to which it belongs) and
• a “coarse” label (the superclass to which it belongs)