no code implementations • 6 Oct 2017 • Son N. Tran, Srikanth Cherla, Artur Garcez, Tillman Weyde
Also, the experimental results on optical character recognition, part-of-speech tagging and text chunking demonstrate that our model is comparable to recurrent neural networks with complex memory gates while requiring far fewer parameters.
no code implementations • 6 Apr 2016 • Srikanth Cherla, Son N. Tran, Tillman Weyde, Artur d'Avila Garcez
Results show that each of the three compared models outperforms the remaining two in one of the three datasets, thus indicating that the proposed theoretical generalisation of the DRBM may be valuable in practice.