arXiv:1905.13568

Quantization Loss Re-Learning Method

Kunping Li

제출 2019-05-30

원문 초록

In order to quantize the gate parameters of the LSTM (Long Short-Term Memory) neural network model with almost no recognition performance degraded, a new quantization method named Quantization Loss Re-Learn Method is proposed in this paper. The method does lossy quantization on gate parameters during training iterations, and the weight parameters learn to offset the loss of gate parameters quantization by adjusting the gradient in back propagation during weight parameters optimization. We proved the effectiveness of this method through theoretical derivation and experiments. The gate parameters had been quantized to 0, 0.5, 1 three values, and on the Named Entity Recognition dataset, the F1 score of the model with the new quantization method on gate parameters decreased by only 0.7% compared to the baseline model.

함께 살펴볼 논문

공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.

arXiv:2504.16007공통 태그 Named Entity Recognition (NER), named-entity-recognition, Named Entity Recognition공식 코드 · Papers with Code

Methods for Recognizing Nested Terms

토론

이 논문과 연결된 포럼 글이 아직 없습니다.