**Objective**: To classify images in the Caltech-256 dataset, which is an improvement over Caltech-101 dataset using a Convolutional Neural Network.


**Description**: Caltech-256 is an object recognition dataset containing 30,607 real-world images, of different sizes, spanning 257 classes (256 object classes and an additional clutter class). Each class is represented by at least 80 images. The dataset is a superset of the Caltech-101 dataset.


**Acknowledgements**
Original data source and banner image: http://www.vision.caltech.edu/Image_Datasets/Caltech256/

Here is a handy link to Kaggle's [competition documentation](https://www.kaggle.com/docs/competitions), which includes, among other things, instructions on [submitting predictions](https://www.kaggle.com/docs/competitions#making-a-submission).