paper-with-me

홈 › Papers

Optimizing and Contrasting Recurrent Neural Network Architectures

2015-10-16 · Ben Krause

Recurrent Neural Networks (RNNs) have long been recognized for their potential to model complex time series. However, it remains to be determined what optimization techniques and recurrent architectures can be used to best realize this potential. The experiments presented take a deep look into Hessian free optimization, a powerful second order optimization method that has shown promising results, but still does not enjoy widespread use. This algorithm was used to train to a number of RNN architectures including standard RNNs, long short-term memory, multiplicative RNNs, and stacked RNNs on the task of character prediction. The insights from these experiments led to the creation of a new multiplicative LSTM hybrid architecture that outperformed both LSTM and multiplicative RNNs. When tested on a larger scale, multiplicative LSTM achieved character level modelling results competitive with the state of the art for RNNs using very different methodology.

📄 PDF Abstract BibTeX arXiv:1510.04953

Code (0)

등록된 구현이 없습니다.

Tasks

Time SeriesTime Series Analysis

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 Statistical Recurrent Unit

2017-03-01 · ICML 2017 8 · Junier B. Oliva, Barnabas Poczos, Jeff Schneider

Sophisticated gated recurrent neural network architectures like LSTMs and GRUs have been shown to be highly effective in a myriad of applications. We develop an un-gated unit, the statistical recurrent unit (SRU), that i…

Bayesian Optimization

Classify or Select: Neural Architectures for Extractive Document Summarization

2016-11-14 · Ramesh Nallapati, Bo-Wen Zhou, Mingbo Ma

We present two novel and contrasting Recurrent Neural Network (RNN) based architectures for extractive summarization of documents. The Classifier based architecture sequentially accepts or rejects each sentence in the or…

Document SummarizationExtractive Document SummarizationExtractive SummarizationExtractive Text Summarization+1

Optimizing Performance of Recurrent Neural Networks on GPUs

2016-04-07 · Jeremy Appleyard, Tomas Kocisky, Phil Blunsom

As recurrent neural networks become larger and deeper, training times for single networks are rising into weeks or even months. As such there is a significant incentive to improve the performance and scalability of these…

Autoregressive + Chain of Thought = Recurrent: Recurrence's Role in Language Models' Computability and a Revisit of Recurrent Transformer

2024-09-14 · Xiang Zhang, Muhammad Abdul-Mageed, Laks V. S. Lakshmanan

The Transformer architecture excels in a variety of language modeling tasks, outperforming traditional neural architectures such as RNN and LSTM. This is partially due to its elimination of recurrent connections, which a…

Language ModelingLanguage Modelling

Neuroevolution of Recurrent Architectures on Control Tasks

2023-04-03 · Maximilien Le Clei, Pierre Bellec

Modern artificial intelligence works typically train the parameters of fixed-sized deep neural networks using gradient-based optimization techniques. Simple evolutionary algorithms have recently been shown to also be cap…

Evolutionary AlgorithmsOpenAI Gymreinforcement-learningReinforcement Learning