paper-with-me

Papers

Path-Normalized Optimization of Recurrent Neural Networks with ReLU Activations

2016-05-23 · NeurIPS 2016 12 · Behnam Neyshabur, Yuhuai Wu, Ruslan Salakhutdinov, Nathan Srebro

We investigate the parameter-space geometry of recurrent neural networks (RNNs), and develop an adaptation of path-SGD optimization method, attuned to this geometry, that can learn plain RNNs with ReLU activations. On several datasets that require capturing long-term dependency structure, we show that path-SGD can significantly improve trainability of ReLU RNNs compared to RNNs trained with SGD, even with various recently suggested initialization schemes.

📄 PDF Abstract BibTeX arXiv:1605.07154

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

SGD Stochastic Gradient Descent is an iterative optimization technique that uses minibatches of data to form an expectation of the gradient, rather than the full gradient using…
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…

Similar Papers 제목 키워드 기반

Path Space for Recurrent Neural Networks with ReLU Activations

2019-09-25 · Yue Wang, Qi Meng, Wei Chen, YuTing Liu 외

It is well known that neural networks with rectified linear units (ReLU) activation functions are positively scale-invariant (i.e., the neural network is invariant to positive rescaling of weights). Optimization algorith…

Optimization Theory for ReLU Neural Networks Trained with Normalization Layers

2020-06-11 · ICML 2020 1 · Yonatan Dukler, Quanquan Gu, Guido Montúfar

The success of deep neural networks is in part due to the use of normalization layers. Normalization layers like Batch Normalization, Layer Normalization and Weight Normalization are ubiquitous in practice, as they impro…

Learning Theory

Dual Rectified Linear Units (DReLUs): A Replacement for Tanh Activation Functions in Quasi-Recurrent Neural Networks

2017-07-25 · Fréderic Godin, Jonas Degrave, Joni Dambre, Wesley De Neve

In this paper, we introduce a novel type of Rectified Linear Unit (ReLU), called a Dual Rectified Linear Unit (DReLU). A DReLU, which comes with an unbounded positive and negative image, can be used as a drop-in replacem…

Language ModelingLanguage ModellingSentiment AnalysisSentiment Classification

Gradient Descent Maximizes the Margin of Homogeneous Neural Networks

2019-06-13 · ICLR 2020 1 · Kaifeng Lyu, Jian Li

In this paper, we study the implicit regularization of the gradient descent algorithm in homogeneous neural networks, including fully-connected and convolutional neural networks with ReLU or LeakyReLU activations. In par…

Input-Output Equivalence of Unitary and Contractive RNNs

2019-10-30 · M. Emami, M. Sahraee-Ardakan, S. Rangan, A. K. Fletcher

Unitary recurrent neural networks (URNNs) have been proposed as a method to overcome the vanishing and exploding gradient problem in modeling data with long-term dependencies. A basic question is how restrictive is the u…