FIELD: data processing.
SUBSTANCE: invention relates to the field of artificial intelligence, and in particular, to recurrent neural networks (RNN). Disclosed is a new Bayesian rarefaction method for recurrent architectures with gateways, which take into account their recurrence features and a gate mechanism. In the proposed method, neurons are removed from the associated model and the gates are made constant, which provides not only network compression, but considerable acceleration of forward passage. On discriminating tasks, this method provides maximum LSTM compression, so that only a small amount of input and hidden neurons remains with insignificant reduction of quality. Such small model is easy to interpret.
EFFECT: high compression ratio.
19 cl, 2 dwg, 2 tbl
| Title | Year | Author | Number |
|---|---|---|---|
| METHOD OF TRAINED RECURRENT NEURAL NETWORK DEBUGGING | 2019 |
|
RU2715024C1 |
| ADAPTIVE AUDIO ENHANCEMENT FOR MULTICHANNEL SPEECH RECOGNITION | 2016 |
|
RU2698153C1 |
| METHOD OF CALCULATING CLIENT CREDIT RATING | 2019 |
|
RU2723448C1 |
| METHOD OF SYNTHESIS OF A TWO-DIMENSIONAL IMAGE OF A SCENE VIEWED FROM A REQUIRED VIEW POINT AND ELECTRONIC COMPUTING APPARATUS FOR IMPLEMENTATION THEREOF | 2020 |
|
RU2749749C1 |
| METHOD AND DEVICE FOR STRAP DOWN INERTIAL NAVIGATION | 2018 |
|
RU2685767C1 |
| METHOD FOR OBTAINING LOW-DIMENSIONAL NUMERIC REPRESENTATIONS OF SEQUENCES OF EVENTS | 2020 |
|
RU2741742C1 |
| ANALOGUE HARDWARE IMPLEMENTATION OF NEURAL NETWORKS | 2020 |
|
RU2796649C2 |
| THEMATIC MODELS WITH A PRIORI TONALITY PARAMETERS BASED ON DISTRIBUTED REPRESENTATIONS | 2018 |
|
RU2719463C1 |
| RECOGNITION OF EVENTS ON PHOTOGRAPHS WITH AUTOMATIC SELECTION OF ALBUMS | 2020 |
|
RU2742602C1 |
| METHOD FOR PREDICTION OF DIAGNOSIS BASED ON DATA PROCESSING CONTAINING MEDICAL KNOWLEDGE | 2019 |
|
RU2723674C1 |
