Continuous Timescale Long-Short Term Memory Neural Network for Human Intent Understanding
Understanding of human intention by observing a series of human actions has been a challenging task. In order to do so, we need to analyze longer sequences of human actions related with intentions and extract the context from the dynamic features. The multiple timescales recurrent neural network (MT...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2017-08-01
|
| Series: | Frontiers in Neurorobotics |
| Subjects: | |
| Online Access: | http://journal.frontiersin.org/article/10.3389/fnbot.2017.00042/full |
| _version_ | 1819120970715103232 |
|---|---|
| author | Zhibin Yu Dennis S. Moirangthem Minho Lee |
| author_facet | Zhibin Yu Dennis S. Moirangthem Minho Lee |
| author_sort | Zhibin Yu |
| collection | DOAJ |
| description | Understanding of human intention by observing a series of human actions has been a challenging task. In order to do so, we need to analyze longer sequences of human actions related with intentions and extract the context from the dynamic features. The multiple timescales recurrent neural network (MTRNN) model, which is believed to be a kind of solution, is a useful tool for recording and regenerating a continuous signal for dynamic tasks. However, the conventional MTRNN suffers from the vanishing gradient problem which renders it impossible to be used for longer sequence understanding. To address this problem, we propose a new model named Continuous Timescale Long-Short Term Memory (CTLSTM) in which we inherit the multiple timescales concept into the Long-Short Term Memory (LSTM) recurrent neural network (RNN) that addresses the vanishing gradient problem. We design an additional recurrent connection in the LSTM cell outputs to produce a time-delay in order to capture the slow context. Our experiments show that the proposed model exhibits better context modeling ability and captures the dynamic features on multiple large dataset classification tasks. The results illustrate that the multiple timescales concept enhances the ability of our model to handle longer sequences related with human intentions and hence proving to be more suitable for complex tasks, such as intention recognition. |
| first_indexed | 2024-12-22T06:29:08Z |
| format | Article |
| id | doaj.art-11f0e79b851044eeb2907a2a0b277a47 |
| institution | Directory Open Access Journal |
| issn | 1662-5218 |
| language | English |
| last_indexed | 2024-12-22T06:29:08Z |
| publishDate | 2017-08-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neurorobotics |
| spelling | doaj.art-11f0e79b851044eeb2907a2a0b277a472022-12-21T18:35:45ZengFrontiers Media S.A.Frontiers in Neurorobotics1662-52182017-08-011110.3389/fnbot.2017.00042280009Continuous Timescale Long-Short Term Memory Neural Network for Human Intent UnderstandingZhibin Yu0Dennis S. Moirangthem1Minho Lee2Department of Electrical Engineering, College of Information Science and Engineering, Ocean University of ChinaQingdao, ChinaSchool of Electronics Engineering, Kyungpook National UniversityDaegu, South KoreaSchool of Electronics Engineering, Kyungpook National UniversityDaegu, South KoreaUnderstanding of human intention by observing a series of human actions has been a challenging task. In order to do so, we need to analyze longer sequences of human actions related with intentions and extract the context from the dynamic features. The multiple timescales recurrent neural network (MTRNN) model, which is believed to be a kind of solution, is a useful tool for recording and regenerating a continuous signal for dynamic tasks. However, the conventional MTRNN suffers from the vanishing gradient problem which renders it impossible to be used for longer sequence understanding. To address this problem, we propose a new model named Continuous Timescale Long-Short Term Memory (CTLSTM) in which we inherit the multiple timescales concept into the Long-Short Term Memory (LSTM) recurrent neural network (RNN) that addresses the vanishing gradient problem. We design an additional recurrent connection in the LSTM cell outputs to produce a time-delay in order to capture the slow context. Our experiments show that the proposed model exhibits better context modeling ability and captures the dynamic features on multiple large dataset classification tasks. The results illustrate that the multiple timescales concept enhances the ability of our model to handle longer sequences related with human intentions and hence proving to be more suitable for complex tasks, such as intention recognition.http://journal.frontiersin.org/article/10.3389/fnbot.2017.00042/fullcontinuous timescalerecurrent neural networkLSTMclassificationdynamic sequence |
| spellingShingle | Zhibin Yu Dennis S. Moirangthem Minho Lee Continuous Timescale Long-Short Term Memory Neural Network for Human Intent Understanding Frontiers in Neurorobotics continuous timescale recurrent neural network LSTM classification dynamic sequence |
| title | Continuous Timescale Long-Short Term Memory Neural Network for Human Intent Understanding |
| title_full | Continuous Timescale Long-Short Term Memory Neural Network for Human Intent Understanding |
| title_fullStr | Continuous Timescale Long-Short Term Memory Neural Network for Human Intent Understanding |
| title_full_unstemmed | Continuous Timescale Long-Short Term Memory Neural Network for Human Intent Understanding |
| title_short | Continuous Timescale Long-Short Term Memory Neural Network for Human Intent Understanding |
| title_sort | continuous timescale long short term memory neural network for human intent understanding |
| topic | continuous timescale recurrent neural network LSTM classification dynamic sequence |
| url | http://journal.frontiersin.org/article/10.3389/fnbot.2017.00042/full |
| work_keys_str_mv | AT zhibinyu continuoustimescalelongshorttermmemoryneuralnetworkforhumanintentunderstanding AT dennissmoirangthem continuoustimescalelongshorttermmemoryneuralnetworkforhumanintentunderstanding AT minholee continuoustimescalelongshorttermmemoryneuralnetworkforhumanintentunderstanding |