Faster method for Deep Belief Network based Object classification using DWT
This work addresses efficiency issues for researchers and practitioners using DBNs in image classification, though it appears incremental as it combines existing techniques.
The paper tackled the problem of high training time and computational complexity in Deep Belief Networks (DBNs) for object classification by integrating DBN with Discrete Wavelet Transform (DWT), resulting in a method that is faster and maintains competent performance compared to traditional DBNs.
A Deep Belief Network (DBN) requires large, multiple hidden layers with high number of hidden units to learn good features from the raw pixels of large images. This implies more training time as well as computational complexity. By integrating DBN with Discrete Wavelet Transform (DWT), both training time and computational complexity can be reduced. The low resolution images obtained after application of DWT are used to train multiple DBNs. The results obtained from these DBNs are combined using a weighted voting algorithm. The performance of this method is found to be competent and faster in comparison with that of traditional DBNs.