paper-with-me

홈 › Papers

Low-Complexity LSTM Training and Inference with FloatSD8 Weight Representation

2020-01-23 · Yu-Tung Liu, Tzi-Dar Chiueh

The FloatSD technology has been shown to have excellent performance on low-complexity convolutional neural networks (CNNs) training and inference. In this paper, we applied FloatSD to recurrent neural networks (RNNs), specifically long short-term memory (LSTM). In addition to FloatSD weight representation, we quantized the gradients and activations in model training to 8 bits. Moreover, the arithmetic precision for accumulations and the master copy of weights were reduced from 32 bits to 16 bits. We demonstrated that the proposed training scheme can successfully train several LSTM models from scratch, while fully preserving model accuracy. Finally, to verify the proposed method's advantage in implementation, we designed an LSTM neuron circuit and showed that it achieved significantly reduced die area and power consumption.

📄 PDF Abstract BibTeX arXiv:2001.08450

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Sigmoid Activation 설명 없음
Tanh Activation 설명 없음
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…

Similar Papers 제목 키워드 기반

A comparison of LSTM and GRU networks for learning symbolic sequences

2021-07-05 · Roberto Cahuantzi, Xinye Chen, Stefan Güttel

We explore the architecture of recurrent neural networks (RNNs) by studying the complexity of string sequences it is able to memorize. Symbolic sequences of different complexity are generated to simulate RNN training and…

Memorization

Distilling BERT for low complexity network training

2021-05-13 · Bansidhar Mangalwedhekar

This paper studies the efficiency of transferring BERT learnings to low complexity models like BiLSTM, BiLSTM with attention and shallow CNNs using sentiment analysis on SST-2 dataset. It also compares the complexity of …

Sentiment AnalysisSST-2

xLSTM Scaling Laws: Competitive Performance with Linear Time-Complexity

2025-10-02 · Maximilian Beck, Kajetan Schweighofer, Sebastian Böck, Sebastian Lehner 외 arxiv

Scaling laws play a central role in the success of Large Language Models (LLMs), enabling the prediction of model performance relative to compute budgets prior to training. While Transformers have been the dominant archi…

Hardware-Guided Symbiotic Training for Compact, Accurate, yet Execution-Efficient LSTM

2019-01-30 · Hongxu Yin, Guoyang Chen, Yingmin Li, Shuai Che 외

Many long short-term memory (LSTM) applications need fast yet compact models. Neural network compression approaches, such as the grow-and-prune paradigm, have proved to be promising for cutting down network complexity by…

Language ModelingLanguage ModellingNeural Network Compressionspeech-recognition+1

xLSTM 7B: A Recurrent LLM for Fast and Efficient Inference

2025-03-17 · Maximilian Beck, Korbinian Pöppel, Phillip Lippe, Richard Kurle 외

Recent breakthroughs in solving reasoning, math and coding problems with Large Language Models (LLMs) have been enabled by investing substantial computation budgets at inference time. Therefore, inference speed is one of…

MambaMath