GXNOR-Net: training deep neural networks with ternary weights and activations without full-precision memory under a unified discretization framework (Q2179802): Difference between revisions
From MaRDI portal
Changed an Item |
ReferenceBot (talk | contribs) Changed an Item |
||
| Property / cites work | |||
| Property / cites work: Q4558516 / rank | |||
Normal rank | |||
| Property / cites work | |||
| Property / cites work: Efficient Associative Computation with Discrete Synapses / rank | |||
Normal rank | |||
| Property / cites work | |||
| Property / cites work: Memory Capacities for Synaptic and Structural Plasticity / rank | |||
Normal rank | |||
| Property / cites work | |||
| Property / cites work: Q2934059 / rank | |||
Normal rank | |||
Revision as of 15:59, 22 July 2024
scientific article
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | GXNOR-Net: training deep neural networks with ternary weights and activations without full-precision memory under a unified discretization framework |
scientific article |
Statements
GXNOR-Net: training deep neural networks with ternary weights and activations without full-precision memory under a unified discretization framework (English)
0 references
13 May 2020
0 references
GXNOR-Net
0 references
discrete state transition
0 references
ternary neural networks
0 references
sparse binary networks
0 references
