A review of unsupervised feature learning and deep learning for time-series modeling

By Martin Längkvist, Lars Karlsson, Amy Loutfi. 2014

1,187 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Representation & Self-Supervised Learning, Signal Processing, Time-Series & Forecasting

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Omer Berat Sezer
2. A. Ozbayoglu
3. Jan Gasthaus
4. Tim Januschowski
5. Bernie Wang
6. Chenyou Fan
7. K. Khorasani
8. Mehrsan Javan Roshtkhari

In Representation & Self-Supervised Learning

1. A. Ozbayoglu
2. Omer Berat Sezer
3. K. Khorasani
4. Mehrsan Javan Roshtkhari
5. Bahareh Pourbabaee
6. Zhiqiang Shang
7. Sutanu Bhowmick
8. Limin Sun

In Signal Processing

1. Bernie Wang
2. Tim Januschowski
3. Jan Gasthaus
4. Syama Sundar Rangapuram
5. A. Ozbayoglu
6. Omer Berat Sezer
7. Yinhai Wang
8. Danielle C. Maddix

In Time-Series & Forecasting

1. Bernie Wang
2. Omer Berat Sezer
3. Tim Januschowski
4. A. Ozbayoglu
5. Jan Gasthaus
6. Danielle C. Maddix
7. Syama Sundar Rangapuram
8. Christoph Bergmeir

Citations in the corpus

• Forecasting Across Time Series Databases using Long Short-Term Memory Networks on Groups of Similar Series (2017, background): “In fact, LSTMs possess the ability of remembering over 100 steps of a sequence (Längkvist et al., 2014).”
• Financial Trading Model with Stock Bar Chart Image Time Series with Deep Convolutional Neural Networks (2019, methodology): “Langkvist et al. [20] reviewed the deep learning models (Boltzmann machine, autoencoder, recurrent neural network, convolution and pooling, and hidden Markov model) which are used for the analysis of time-series data, especially stock market indexes and stock prices.”
• Knowledge Capture and Replay for Continual Learning (2020, neutral): “, 2019], time-series modeling [Längkvist et al., 2014], etc.”
• Scene classification based on single-layer SAE and SVM (2015, methodology): “Recently, representation learning has been a hot research topic in the field of machine leaning (Hinton et al., 2006; Bengio et al., 2013; Langkvist et al., 2014).”
• Deep Learning for Time Series Forecasting: Tutorial and Literature Survey (2020, background): “Accordingly, deep learning has had a sizable impact on forecasting [110] and NNs have long entered the canon of standard techniques for forecasting [84].”
• Unsupervised Representation Learning for Time Series with Temporal Neighborhood Coding (2021, background): “While integral for many applications, unsupervised representation learning has been far less studied for time series (Längkvist et al., 2014), compared to other domains such as vision or natural language processing (Denton et al., 2017; Radford et al., 2015; Gutmann & Hyvärinen, 2012; Wang & Gupta,…”
• Financial Time Series Prediction Based on Deep Learning (2017, background): “In a multi-level superimposed deep neural network, the non-linear activation function enables a more expressive model to learn more abstract feature representation [15].”
• Deep learning approach for active classification of electrocardiogram signals (2016, background): “, handcrafted features fed as input to a kernel classifier), deep learning has shown outstanding results in many applications such as image classification [23], object recognition [6], face recognition [29], medical image analysis [10], and time series data [16, 24, 36].”