paper-with-me

홈 › Papers

Breaking the Activation Function Bottleneck through Adaptive Parameterization

2018-05-22 · NeurIPS 2018 12 · Sebastian Flennerhag, Hujun Yin, John Keane, Mark Elliot

Standard neural network architectures are non-linear only by virtue of a simple element-wise activation function, making them both brittle and excessively large. In this paper, we consider methods for making the feed-forward layer more flexible while preserving its basic structure. We develop simple drop-in replacements that learn to adapt their parameterization conditional on the input, thereby increasing statistical efficiency significantly. We present an adaptive LSTM that advances the state of the art for the Penn Treebank and WikiText-2 word-modeling tasks while using fewer parameters and converging in less than half as many iterations.

📄 PDF Abstract BibTeX arXiv:1805.08574

Code (1)

flennerhag/alstm 공식 구현 pytorch

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

Sigsoftmax: Reanalysis of the Softmax Bottleneck

2018-05-28 · NeurIPS 2018 12 · Sekitoshi Kanai, Yasuhiro Fujiwara, Yuki Yamanaka, Shuichi Adachi

Softmax is an output activation function for modeling categorical probability distributions in many applications of deep learning. However, a recent study revealed that softmax can be a bottleneck of representational cap…

Language ModelingLanguage Modelling

Physics-informed neural network for ultrasound nondestructive quantification of surface breaking cracks

2020-05-07 · Khemraj Shukla, Patricio Clark Di Leoni, James Blackshire, Daniel Sparkman 외

We introduce an optimized physics-informed neural network (PINN) trained to solve the problem of identifying and characterizing a surface breaking crack in a metal plate. PINNs are neural networks that can combine data a…

Adaptive Activation Network For Low Resource Multilingual Speech Recognition

2022-05-28 · Jian Luo, Jianzong Wang, Ning Cheng, Zhenpeng Zheng 외

Low resource automatic speech recognition (ASR) is a useful but thorny task, since deep learning ASR models usually need huge amounts of training data. The existing models mostly established a bottleneck (BN) layer by pr…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition

Breaking the Attention Bottleneck

2024-06-16 · Kalle Hilsenbek

Attention-based transformers have become the standard architecture in many deep learning fields, primarily due to their ability to model long-range dependencies and handle variable-length input sequences. However, the at…

Decoder

Adaptive Estimators Show Information Compression in Deep Neural Networks

2019-02-24 · ICLR 2019 5 · Ivan Chelombiev, Conor Houghton, Cian O'Donnell

To improve how neural networks function it is crucial to understand their learning process. The information bottleneck theory of deep learning proposes that neural networks achieve good generalization by compressing thei…

L2 RegularizationMutual Information Estimation