Autoregressive Convolutional Neural Networks for Asynchronous Time Series
arXiv:1703.04122
Abstract
We propose Significance-Offset Convolutional Neural Network, a deep convolutional network architecture for regression of multivariate asynchronous time series. The model is inspired by standard autoregressive (AR) models and gating mechanisms used in recurrent neural networks. It involves an AR-like weighting system, where the final predictor is obtained as a weighted sum of adjusted regressors, while the weights are datadependent functions learnt through a convolutional network. The architecture was designed for applications on asynchronous time series and is evaluated on such datasets: a hedge fund proprietary dataset of over 2 million quotes for a credit derivative index, an artificially generated noisy autoregressive series and UCI household electricity consumption dataset. The proposed architecture achieves promising results as compared to convolutional and recurrent neural networks.
Proceedings of The 35th International Conference on Machine Learning (ICML), Stockholm, Sweden, 2018, to appear
References in corpus (7)
- Deep Learning in Neural Networks: An Overview
- Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
- Language Modeling with Gated Convolutional Networks
- Conditional Time Series Forecasting with Convolutional Neural Networks
- Phased LSTM: Accelerating Recurrent Network Training for Long or Event-based Sequences
- Deep Learning for Time-Series Analysis
- eCommerceGAN : A Generative Adversarial Network for E-commerce
Cited by in corpus (7)
- Time Series Forecasting With Deep Learning: A Survey
- Conditional Time Series Forecasting with Convolutional Neural Networks
- Ensemble Kalman Inversion: A Derivative-Free Technique For Machine Learning Tasks
- Data-Driven Vehicle Trajectory Forecasting
- Black-Box Inference for Non-Linear Latent Force Models
- Volatility Forecasting with 1-dimensional CNNs via transfer learning
- Synergetic Learning of Heterogeneous Temporal Sequences for Multi-Horizon Probabilistic Forecasting