paper-with-me

Papers

Recurrent knowledge distillation

2018-05-18 · Silvia L. Pintea, Yue Liu, Jan C. van Gemert

Knowledge distillation compacts deep networks by letting a small student network learn from a large teacher network. The accuracy of knowledge distillation recently benefited from adding residual layers. We propose to reduce the size of the student network even further by recasting multiple residual layers in the teacher network into a single recurrent student layer. We propose three variants of adding recurrent connections into the student network, and show experimentally on CIFAR-10, Scenes and MiniPlaces, that we can reduce the number of parameters at little loss in accuracy.

📄 PDF Abstract BibTeX arXiv:1805.07170

Code (0)

등록된 구현이 없습니다.

Tasks

Knowledge Distillation

Similar Papers 제목 키워드 기반

Knowledge Distillation Applied to Optical Channel Equalization: Solving the Parallelization Problem of Recurrent Connection

2022-12-08 · Sasipim Srivallapanondh, Pedro J. Freire, Bernhard Spinnler, Nelson Costa 외

To circumvent the non-parallelizability of recurrent neural network-based equalizers, we propose knowledge distillation to recast the RNN into a parallelizable feedforward structure. The latter shows 38\% latency decreas…

Knowledge Distillation

Knowledge Distillation For Recurrent Neural Network Language Modeling With Trust Regularization

2019-04-08 · Yangyang Shi, Mei-Yuh Hwang, Xin Lei, Haoyu Sheng

Recurrent Neural Networks (RNNs) have dominated language modeling because of their superior performance over traditional N-gram based models. In many applications, a large Recurrent Neural Network language model (RNNLM) …

Knowledge DistillationLanguage ModelingLanguage Modellingspeech-recognition+1

Data Efficient Any Transformer-to-Mamba Distillation via Attention Bridge

2025-10-22 · Penghao Wang, Yuhao Zhou, Mengxuan Wu, Panpan Zhang 외 arxiv

State-space models (SSMs) have emerged as efficient alternatives to Transformers for sequence modeling, offering superior scalability through recurrent structures. However, their training remains costly and the ecosystem…

Knowledge Distillation

Robust Knowledge Distillation from RNN-T Models With Noisy Training Labels Using Full-Sum Loss

2023-03-10 · Mohammad Zeineldeen, Kartik Audhkhasi, Murali Karthick Baskar, Bhuvana Ramabhadran

This work studies knowledge distillation (KD) and addresses its constraints for recurrent neural network transducer (RNN-T) models. In hard distillation, a teacher model transcribes large amounts of unlabelled speech to …

Knowledge Distillation

Multi-stage Distillation Framework for Cross-Lingual Semantic Similarity Matching

2022-09-13 · Findings (NAACL) 2022 7 · Kunbo Ding, Weijie Liu, Yuejian Fang, Zhe Zhao 외

Previous studies have proved that cross-lingual knowledge distillation can significantly improve the performance of pre-trained models for cross-lingual similarity matching tasks. However, the student model needs to be l…

Contrastive LearningKnowledge DistillationSemantic SimilaritySemantic Textual Similarity+1