Fuzzy String Matching with a Deep Neural Network

A deep learning neural network for character-level text classification is described in this work. The system spots keywords in the text output of an optical character recognition system using memoization and by encoding the text into feature vectors related to letter frequency. Recognizing error messages in a set of generated images, dictionary and spell-check-based approaches achieved 69% to 88% accuracy, while various deep learning approaches achieved 91% to 96% accuracy, and a combination of deep learning with a dictionary achieved 97% accuracy. The contribution of this work to the state of the art is to describe a new approach for character-level deep neural network classification of noisy text.     

A Multiple Resampling Method for Learning from Imbalanced Data Sets

Resampling methods are commonly used for dealing with the class-imbalance problem. Their advantage over other methods is that they are external and thus, easily transportable. Although such approaches can be very simple to implement, tuning them most effectively is not an easy task. In particular, it is unclear whether oversampling is more effective than undersampling and which oversampling or undersampling rate should be used. This paper presents an experimental study of these questions and concludes that combining different expressions of the resampling approach is an effective solution to the tuning problem. The proposed combination scheme is evaluated on imbalanced subsets of the Reuters-21578 text collection and is shown to be quite effective for these problems.     

Nonlinear autoassociation is not equivalent to PCA

A common misperception within the neural network community is that even with nonlinearities in their hidden layer, autoassociators trained with backpropagation are equivalent to linear methods such as principal component analysis (PCA). Our purpose is to demonstrate that nonlinear autoassociators actually behave differently from linear methods and that they can outperform these methods when used for latent extraction, projection, and classification. While linear autoassociators emulate PCA, and thus exhibit a flat or unimodal reconstruction error surface, autoassociators with nonlinearities in their hidden layer learn domains by building error reconstruction surfaces that, depending on the task, contain multiple local valleys. This interpolation bias allows nonlinear autoassociators to represent appropriate classifications of nonlinear multimodal domains, in contrast to linear autoassociators, which are inappropriate for such tasks. In fact, autoassociators with hidden unit nonlinearities can be shown to perform nonlinear classification and nonlinear recognition.