Multilayer feedforward neural networks with single powers-of-two weights

By C. Tang, H. Kwan. 1993

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Marcel Keller
2. Assi Barak
3. Daniel E. Escudero
4. Anders Dalskov
5. Mehdi Rezagholizadeh
6. Gabriele Prato
7. Ella Charlaix
8. Yehuda Lindell

Citations in the corpus

• Secure Evaluation of Quantized Neural Networks (2019, background): “4 This is a long-standing research area, with initial works already dating back to the 1990s [5, 26, 49, 62], and this extensive research body have enabled modern quantized neural networks to have essentially the same accuracy as their full-precision counterparts [14, 29, 32, 53, 65].”
• Fixed-point feedforward deep neural network design using weights +1, 0, and −1 (2014, methodology): “Instead of direct weight quantization, retraining with backpropagation was developed in [7], [8].”
• Fully Quantized Transformer for Machine Translation (2019, background): “Consequently, numerical values can be represented using fewer bits (Tang and Kwan, 1993; March-esi et al., 1993).”