paper-with-me

Papers

The unreasonable effectiveness of the forget gate

2018-04-13 · Jos van der Westhuizen, Joan Lasenby

Given the success of the gated recurrent unit, a natural question is whether all the gates of the long short-term memory (LSTM) network are necessary. Previous research has shown that the forget gate is one of the most important gates in the LSTM. Here we show that a forget-gate-only version of the LSTM with chrono-initialized biases, not only provides computational savings but outperforms the standard LSTM on multiple benchmark datasets and competes with some of the best contemporary models. Our proposed network, the JANET, achieves accuracies of 99% and 92.5% on the MNIST and pMNIST datasets, outperforming the standard LSTM which yields accuracies of 98.5% and 91%.

📄 PDF Abstract BibTeX arXiv:1804.04849

Code (1)

JosvanderWesthuizen/janet 공식 구현 tf

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

The unreasonable effectiveness of Batch-Norm statistics in addressing catastrophic forgetting across medical institutions

2020-11-16 · Sharut Gupta, Praveer Singh, Ken Chang, Mehak Aggarwal 외

Model brittleness is a primary concern when deploying deep learning models in medical settings owing to inter-institution variations, like patient demographics and intra-institution variation, such as multiple scanner ty…

Deep Learning

The Unreasonable Effectiveness of Randomized Representations in Online Continual Graph Learning

2025-10-08 · Giovanni Donghi, Daniele Zambon, Luca Pasa, Cesare Alippi 외 arxiv

Catastrophic forgetting is one of the main obstacles for Online Continual Graph Learning (OCGL), where nodes arrive one by one, distribution drifts may occur at any time and offline training on task-specific subgraphs is…

Graph Learning

On the Unreasonable Effectiveness of Last-layer Retraining

2025-12-01 · John C. Hill, Tyler LaBonte, Xinchen Zhang, Vidya Muthukumar arxiv

Last-layer retraining (LLR) methods -- wherein the last layer of a neural network is reinitialized and retrained on a held-out set following ERM training -- have garnered interest as an efficient approach to rectify depe…

The Unreasonable Effectiveness of Word Representations for Twitter Named Entity Recognition

2015-05-01 · HLT 2015 5 · Colin Cherry, Hongyu Guo
Domain AdaptationEntity Linkingnamed-entity-recognitionNamed Entity Recognition+3

The unreasonable effectiveness of pattern matching

2026-01-16 · Gary Lupyan, Blaise Agüera y Arcas arxiv

We report on an astonishing ability of large language models (LLMs) to make sense of "Jabberwocky" language in which most or all content words have been randomly replaced by nonsense strings, e.g., translating "He dwushe…