SITHCon: A neural network robust to variations in input scaling on the time dimension

• URL: http://arxiv.org/abs/2107.04616v1
• Date: Fri, 9 Jul 2021 18:11:50 GMT
• Title: SITHCon: A neural network robust to variations in input scaling on the time dimension
• Authors: Brandon G. Jacques, Zoran Tiganj, Aakash Sarkar, Marc W. Howard, Per B. Sederberg
• Abstract summary: In machine learning, convolutional neural networks (CNNs) have been extremely influential in both computer vision and in recognizing patterns extended over time. This paper introduces a Scale-Invariant Temporal History Convolution network (SITHCon) that uses a logarithmically-distributed temporal memory.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In machine learning, convolutional neural networks (CNNs) have been extremely influential in both computer vision and in recognizing patterns extended over time. In computer vision, part of the flexibility arises from the use of max-pooling operations over the convolutions to attain translation invariance. In the mammalian brain, neural representations of time use a set of temporal basis functions. Critically, these basis functions appear to be arranged in a geometric series such that the basis set is evenly distributed over logarithmic time. This paper introduces a Scale-Invariant Temporal History Convolution network (SITHCon) that uses a logarithmically-distributed temporal memory. A max-pool over a logarithmically-distributed temporal memory results in scale-invariance in time. We compare performance of SITHCon to a Temporal Convolution Network (TCN) and demonstrate that, although both networks can learn classification and regression problems on both univariate and multivariate time series $f(t)$, only SITHCon has the property that it generalizes without retraining to rescaled versions of the input $f(at)$. This property, inspired by findings from neuroscience and psychology, could lead to large-scale networks with dramatically different capabilities, including faster training and greater generalizability, even with significantly fewer free parameters.

Related papers

• A Dynamical Model of Neural Scaling Laws [79.59705237659547]
  We analyze a random feature model trained with gradient descent as a solvable model of network training and generalization. Our theory shows how the gap between training and test loss can gradually build up over time due to repeated reuse of data.
  arXiv  Detail & Related papers  (2024-02-02T01:41:38Z)
• Time-Parameterized Convolutional Neural Networks for Irregularly Sampled Time Series [26.77596449192451]
  Irregularly sampled time series are ubiquitous in several application domains, leading to sparse, not fully-observed and non-aligned observations. Standard sequential neural networks (RNNs) and convolutional neural networks (CNNs) consider regular spacing between observation times, posing significant challenges to irregular time series modeling. We parameterize convolutional layers by employing time-explicitly irregular kernels.
  arXiv  Detail & Related papers  (2023-08-06T21:10:30Z)
• Recurrent Neural Networks with more flexible memory: better predictions than rough volatility [0.0]
  We compare the ability of vanilla and extended long short term memory networks to predict asset price volatility. We show that the model with the smallest validation loss systemically outperforms rough volatility predictions by about 20% when trained and tested on a dataset with multiple time series.
  arXiv  Detail & Related papers  (2023-08-04T14:24:57Z)
• MTS2Graph: Interpretable Multivariate Time Series Classification with Temporal Evolving Graphs [1.1756822700775666]
  We introduce a new framework for interpreting time series data by extracting and clustering the input representative patterns. We run experiments on eight datasets of the UCR/UEA archive, along with HAR and PAM datasets.
  arXiv  Detail & Related papers  (2023-06-06T16:24:27Z)
• 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)
• The Separation Capacity of Random Neural Networks [78.25060223808936]
  We show that a sufficiently large two-layer ReLU-network with standard Gaussian weights and uniformly distributed biases can solve this problem with high probability. We quantify the relevant structure of the data in terms of a novel notion of mutual complexity.
  arXiv  Detail & Related papers  (2021-07-31T10:25:26Z)
• Reservoir Memory Machines as Neural Computers [70.5993855765376]
  Differentiable neural computers extend artificial neural networks with an explicit memory without interference. We achieve some of the computational capabilities of differentiable neural computers with a model that can be trained very efficiently.
  arXiv  Detail & Related papers  (2020-09-14T12:01:30Z)
• Incremental Training of a Recurrent Neural Network Exploiting a Multi-Scale Dynamic Memory [79.42778415729475]
  We propose a novel incrementally trained recurrent architecture targeting explicitly multi-scale learning. We show how to extend the architecture of a simple RNN by separating its hidden state into different modules. We discuss a training algorithm where new modules are iteratively added to the model to learn progressively longer dependencies.
  arXiv  Detail & Related papers  (2020-06-29T08:35:49Z)
• Liquid Time-constant Networks [117.57116214802504]
  We introduce a new class of time-continuous recurrent neural network models. Instead of declaring a learning system's dynamics by implicit nonlinearities, we construct networks of linear first-order dynamical systems. These neural networks exhibit stable and bounded behavior, yield superior expressivity within the family of neural ordinary differential equations.
  arXiv  Detail & Related papers  (2020-06-08T09:53:35Z)
• Temporal Interlacing Network [8.876132549551738]
  temporal interlacing network (TIN) is a simple yet powerful operator for learning temporal features. TIN fuses the two kinds of information by interlacing spatial representations from the past to the future. TIN wins the $1st$ in the ICCV19 - Multi Moments in Time challenge.
  arXiv  Detail & Related papers  (2020-01-17T19:06:05Z)
• A Deep Structural Model for Analyzing Correlated Multivariate Time Series [11.009809732645888]
  We present a deep learning structural time series model which can handle correlated multivariate time series input. The model explicitly learns/extracts the trend, seasonality, and event components. We compare our model with several state-of-the-art methods through a comprehensive set of experiments on a variety of time series data sets.
  arXiv  Detail & Related papers  (2020-01-02T18:48:29Z)

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.