paper-with-me

홈 › Papers

State-Frequency Memory Recurrent Neural Networks

2017-08-01 · ICML 2017 8 · Hao Hu, Guo-Jun Qi

Modeling temporal sequences plays a fundamental role in various modern applications and has drawn more and more attentions in the machine learning community. Among those efforts on improving the capability to represent temporal data, the Long Short-Term Memory (LSTM) has achieved great success in many areas. Although the LSTM can capture long-range dependency in the time domain, it does not explicitly model the pattern occurrences in the frequency domain that plays an important role in tracking and predicting data points over various time cycles. We propose the State-Frequency Memory (SFM), a novel recurrent architecture that allows to separate dynamic patterns across different frequency components and their impacts on modeling the temporal contexts of input sequences. By jointly decomposing memorized dynamics into state-frequency components, the SFM is able to offer a fine-grained analysis of temporal sequences by capturing the dependency of uncovered patterns in both time and frequency domains. Evaluations on several temporal modeling tasks demonstrate the SFM can yield competitive performances, in particular as compared with the state-of-the-art LSTM models.

📄 PDF Abstract BibTeX

Code (2)

dlarsen5/AdaptiveSFM tf
hhkunming/State-Frequency-Memory-Recurrent-Neural-Networks

Tasks

Temporal Sequences

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

Optimum Output Long Short-Term Memory Cell for High-Frequency Trading Forecasting

2023-04-17 · Adamantios Ntakaris, Moncef Gabbouj, Juho Kanniainen

High-frequency trading requires fast data processing without information lags for precise stock price forecasting. This high-paced stock price forecasting is usually based on vectors that need to be treated as sequential…

Frequency Domain Reservoir Computing

2026-06-23 · Klaus Schertler, Xiomara Runge, Andrea Ceni, David Kappel 외 arxiv

While the quadratic sequence-length bottleneck of transformers has fueled a resurgence in recurrent models, effectively capturing complex dynamics requires architectures that balance efficient training with highly expres…

Memory-Gated Recurrent Networks

2020-12-24 · Yaquan Zhang, Qi Wu, Nanbo Peng, Min Dai 외

The essence of multivariate sequential learning is all about how to extract dependencies in data. These data sets, such as hourly medical records in intensive care units and multi-frequency phonetic time series, often ti…

Time SeriesTime Series Analysis

Learning Quantum Processes with Memory -- Quantum Recurrent Neural Networks

2023-01-19 · Dmytro Bondarenko, Robert Salzmann, Viktoria-S. Schmiesing

Recurrent neural networks play an important role in both research and industry. With the advent of quantum machine learning, the quantisation of recurrent neural networks has become recently relevant. We propose fully qu…

Quantum Machine Learning

Incremental Training of a Recurrent Neural Network Exploiting a Multi-Scale Dynamic Memory

2020-06-29 · Antonio Carta, Alessandro Sperduti, Davide Bacciu

The effectiveness of recurrent neural networks can be largely influenced by their ability to store into their dynamical memory information extracted from input sequences at different frequencies and timescales. Such a fe…

speech-recognitionSpeech Recognition