Philosophiae Doctor - PhD / In this thesis, we present a novel hybrid architecture by combining the most popular
sequence recognition models such as Recurrent Neural Networks (RNNs) and Hidden Markov Models (HMMs). Though sequence recognition problems could be potentially modelled through well trained HMMs, they could not provide a reasonable solution to the complicated recognition problems. In contrast, the ability of RNNs to recognize the complex sequence recognition problems is known to be exceptionally good. It should be noted that in the past, methods for applying HMMs into RNNs have been developed by other researchers. However, to the best of our knowledge, no algorithm for processing HMMs through learning has been given. Taking advantage of the structural similarities of the architectural dynamics of the RNNs and HMMs, in this work we analyze the combination of these two systems into the hybrid architecture. To this end, the main objective of this study is to improve the sequence recognition/classi_cation performance by applying a hybrid neural/symbolic approach. In particular, trained HMMs are used as the initial symbolic domain theory and directly encoded into appropriate RNN architecture, meaning that the prior knowledge is processed through the training of RNNs. Proposed algorithm is then implemented on sample test beds and other real time biological applications.
| Identifer | oai:union.ndltd.org:netd.ac.za/oai:union.ndltd.org:uwc/oai:etd.uwc.ac.za:11394/4525 |
| Date | January 2013 |
| Creators | Rallabandi, Pavan Kumar |
| Contributors | Patidar, Kailash C. |
| Publisher | University of the Western Cape |
| Source Sets | South African National ETD Portal |
| Language | English |
| Detected Language | English |
| Type | Thesis |
| Rights | University of the Western Cape |
Page generated in 0.0016 seconds