Time Series Compression using Quaternion Valued Neural Networks and Quaternion Backpropagation

• URL: http://arxiv.org/abs/2403.11722v2
• Date: Mon, 25 Mar 2024 13:34:40 GMT
• Title: Time Series Compression using Quaternion Valued Neural Networks and Quaternion Backpropagation
• Authors: Johannes Pöppelbaum, Andreas Schwung,
• Abstract summary: We propose a novel quaternionic time-series compression methodology where we divide a long time-series into segments of data. We extract the min, max, mean and standard deviation of these chunks as representative features and encapsulate them in a quaternion. This time-series is processed using quaternion valued neural network layers.
• Score: 3.8750364147156247
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: We propose a novel quaternionic time-series compression methodology where we divide a long time-series into segments of data, extract the min, max, mean and standard deviation of these chunks as representative features and encapsulate them in a quaternion, yielding a quaternion valued time-series. This time-series is processed using quaternion valued neural network layers, where we aim to preserve the relation between these features through the usage of the Hamilton product. To train this quaternion neural network, we derive quaternion backpropagation employing the GHR calculus, which is required for a valid product and chain rule in quaternion space. Furthermore, we investigate the connection between the derived update rules and automatic differentiation. We apply our proposed compression method on the Tennessee Eastman Dataset, where we perform fault classification using the compressed data in two settings: a fully supervised one and in a semi supervised, contrastive learning setting. Both times, we were able to outperform real valued counterparts as well as two baseline models: one with the uncompressed time-series as the input and the other with a regular downsampling using the mean. Further, we could improve the classification benchmark set by SimCLR-TS from 81.43% to 83.90%.

Related papers

• Thresholds for the distributed surface code in the presence of memory decoherence [0.0]
  We present a framework for numerical simulations of a memory channel using the distributed toric surface code. We quantitatively investigate the effect of memory decoherence and evaluate the advantage of GHZ creation protocols tailored to the level of decoherence.
  arXiv  Detail & Related papers  (2024-01-19T15:41:00Z)
• Spatio-temporal DeepKriging for Interpolation and Probabilistic Forecasting [2.494500339152185]
  We propose a deep neural network (DNN) based two-stage model fortemporal-temporal and forecasting. We adopt the quant-based loss function in the processes to provide probabilistic forecasting. It is suitable for large-scale prediction of complex-temporal processes.
  arXiv  Detail & Related papers  (2023-06-20T11:51:44Z)
• Robust Detection of Lead-Lag Relationships in Lagged Multi-Factor Models [61.10851158749843]
  Key insights can be obtained by discovering lead-lag relationships inherent in the data. We develop a clustering-driven methodology for robust detection of lead-lag relationships in lagged multi-factor models.
  arXiv  Detail & Related papers  (2023-05-11T10:30:35Z)
• Irregularly-Sampled Time Series Modeling with Spline Networks [0.0]
  We propose using the splines as an input to a neural network, in particular, applying the transformations on the interpolating function directly. This allows us to represent the irregular sequence compactly and use this representation in the downstream tasks such as classification and forecasting.
  arXiv  Detail & Related papers  (2022-10-19T15:05:41Z)
• HyperTime: Implicit Neural Representation for Time Series [131.57172578210256]
  Implicit neural representations (INRs) have recently emerged as a powerful tool that provides an accurate and resolution-independent encoding of data. In this paper, we analyze the representation of time series using INRs, comparing different activation functions in terms of reconstruction accuracy and training convergence speed. We propose a hypernetwork architecture that leverages INRs to learn a compressed latent representation of an entire time series dataset.
  arXiv  Detail & Related papers  (2022-08-11T14:05:51Z)
• EXIT: Extrapolation and Interpolation-based Neural Controlled Differential Equations for Time-series Classification and Forecasting [19.37382379378985]
  neural controlled differential equations (NCDEs) are considered as a breakthrough in deep learning. In this work, we enhance NCDEs by redesigning their core part, i.e., generating a continuous path from a discrete time-series input. Our NCDE design can use both the extrapolation and the extrapolated information for downstream machine learning tasks.
  arXiv  Detail & Related papers  (2022-04-19T09:37:36Z)
• Imputing Missing Observations with Time Sliced Synthetic Minority Oversampling Technique [0.3973560285628012]
  We present a simple yet novel time series imputation technique with the goal of constructing an irregular time series that is uniform across every sample in a data set. We fix a grid defined by the midpoints of non-overlapping bins (dubbed "slices") of observation times and ensure that each sample has values for all of the features at that given time. This allows one to both impute fully missing observations to allow uniform time series classification across the entire data and, in special cases, to impute individually missing features.
  arXiv  Detail & Related papers  (2022-01-14T19:23:24Z)
• Cluster-and-Conquer: A Framework For Time-Series Forecasting [94.63501563413725]
  We propose a three-stage framework for forecasting high-dimensional time-series data. Our framework is highly general, allowing for any time-series forecasting and clustering method to be used in each step. When instantiated with simple linear autoregressive models, we are able to achieve state-of-the-art results on several benchmark datasets.
  arXiv  Detail & Related papers  (2021-10-26T20:41:19Z)
• Compact representations of convolutional neural networks via weight pruning and quantization [63.417651529192014]
  We propose a novel storage format for convolutional neural networks (CNNs) based on source coding and leveraging both weight pruning and quantization. We achieve a reduction of space occupancy up to 0.6% on fully connected layers and 5.44% on the whole network, while performing at least as competitive as the baseline.
  arXiv  Detail & Related papers  (2021-08-28T20:39:54Z)
• Deep Cellular Recurrent Network for Efficient Analysis of Time-Series Data with Spatial Information [52.635997570873194]
  This work proposes a novel deep cellular recurrent neural network (DCRNN) architecture to process complex multi-dimensional time series data with spatial information. The proposed architecture achieves state-of-the-art performance while utilizing substantially less trainable parameters when compared to comparable methods in the literature.
  arXiv  Detail & Related papers  (2021-01-12T20:08:18Z)
• Convolutional Tensor-Train LSTM for Spatio-temporal Learning [116.24172387469994]
  We propose a higher-order LSTM model that can efficiently learn long-term correlations in the video sequence. This is accomplished through a novel tensor train module that performs prediction by combining convolutional features across time. Our results achieve state-of-the-art performance-art in a wide range of applications and datasets.
  arXiv  Detail & Related papers  (2020-02-21T05:00:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.