Summary of Quaternion Recurrent Neural Network with Real-time Recurrent Learning and Maximum Correntropy Criterion, by Pauline Bourigault et al.
Quaternion recurrent neural network with real-time recurrent learning and maximum correntropy criterion
by Pauline Bourigault, Dongpo Xu, Danilo P. Mandic
First submitted to arxiv on: 22 Feb 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary Medium Difficulty summary: The paper presents a novel quaternion recurrent neural network (QRNN) model that can process 3D and 4D data with outliers in real-time. To achieve this, the authors combine the real-time recurrent learning (RTRL) algorithm with the maximum correntropy criterion (MCC) as the loss function. This approach is shown to be less sensitive to outliers compared to traditional mean square error methods, making it suitable for applications involving noisy or uncertain data. The QRNN model is derived using the generalized HR (GHR) calculus, which enables compact and elegant derivations of real functions of quaternion variables. Simulation results in motion prediction for lung cancer radiotherapy demonstrate the effectiveness of this approach. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Low Difficulty summary: This paper creates a new way to process 3D and 4D data quickly and accurately, even when there are mistakes or outliers. They use a special type of neural network called a quaternion recurrent neural network (QRNN) and combine it with two algorithms: real-time recurrent learning (RTRL) and the maximum correntropy criterion (MCC). This helps remove errors and makes the model better at handling noisy data. The authors tested this approach in a specific application, motion prediction for lung cancer radiotherapy, and found that it works well. |
Keywords
* Artificial intelligence * Loss function * Neural network
