Classification involves obtaining a sample and determining to which class the sample belongs (from a finite set of classes). The simplest form of classification is binary classification, where you must determine whether it is of class A or class B. The task ultimately boils down to determining identifying features of each class that are distinct from each other, then using those features to define a selection or classification policy. Here, we will explore different ways to generate or discover the identifying features, also known as the feature descriptor or feature vector of the sample.

/* (2) bag-of-words classifier: http://people.csail.mit.edu/fergus/iccv2005/bagwords.html They were short courses on ICCV 2005. */

/* Andrew Ng */

Classification on digits using neural networks

1. Check UFLDL provided by Andrew Ng
2. In this module, you are requires to do the followings:
3. First, implement the 'sparse autoencoder' section.
4. Second, get 'Vectorized implementation', 'Preprocessing: PCA and Whitening' and 'Softmax Regression' sections done.
5. Third, implement 'Self-Taught Learning and Unsupervised Feature Learning' section for digit classification.

Classification on digits using DEEP neural networks

1. Once you finish module 2, you should have a nice classification system on digit with 98% accuracy.
2. Now, the advanced task would require you to extend it to be deep neural networks
3. In this module, based on your module 1, please continue to work on 'Building Deep Networks for Classification'

Classification on characters using DEEP neural networks

1. Now you have a very nice classification system on digit. Can we classify on other similar data?
2. In module 3, take your neural networks and train it with characters instead of digits. For characters, we would like to use Omniglot dataset.
3. Report your results and comparison. Also please test if the sparse code learned from digits can be used to test on characters?

/* Other related material, maybe more classic. */

ECE4580 Learning Modules