TviNet

I tried averaging subtokens and then an LSTM+CRF which gave decent results for Hindi ( 13k train sentences, 96.3% accuracy) but not for Tamil (400 train sentences, 87% accuracy). Other...

Hey, is this issue about replacing the CCNOT gates with ApplyAnd in RippleCarryAdderD or implementing the circuit given in Fig. 1 which does not compute the Carry out bit?