ForecastNet: A Time-Variant Deep Feed-Forward Neural Network Architecture for Multi-Step-Ahead Time-Series Forecasting

• URL: http://arxiv.org/abs/2002.04155v2
• Date: Sat, 27 Jun 2020 23:24:54 GMT
• Title: ForecastNet: A Time-Variant Deep Feed-Forward Neural Network Architecture for Multi-Step-Ahead Time-Series Forecasting
• Authors: Joel Janek Dabrowski, YiFan Zhang, Ashfaqur Rahman
• Abstract summary: We propose ForecastNet, which uses a deep feed-forward architecture to provide a time-variant model. ForecastNet is demonstrated to outperform statistical and deep learning benchmark models on several datasets.
• Score: 6.043572971237165
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recurrent and convolutional neural networks are the most common architectures used for time series forecasting in deep learning literature. These networks use parameter sharing by repeating a set of fixed architectures with fixed parameters over time or space. The result is that the overall architecture is time-invariant (shift-invariant in the spatial domain) or stationary. We argue that time-invariance can reduce the capacity to perform multi-step-ahead forecasting, where modelling the dynamics at a range of scales and resolutions is required. We propose ForecastNet which uses a deep feed-forward architecture to provide a time-variant model. An additional novelty of ForecastNet is interleaved outputs, which we show assist in mitigating vanishing gradients. ForecastNet is demonstrated to outperform statistical and deep learning benchmark models on several datasets.

Related papers

• TCCT-Net: Two-Stream Network Architecture for Fast and Efficient Engagement Estimation via Behavioral Feature Signals [58.865901821451295]
  We present a novel two-stream feature fusion "Tensor-Convolution and Convolution-Transformer Network" (TCCT-Net) architecture. To better learn the meaningful patterns in the temporal-spatial domain, we design a "CT" stream that integrates a hybrid convolutional-transformer. In parallel, to efficiently extract rich patterns from the temporal-frequency domain, we introduce a "TC" stream that uses Continuous Wavelet Transform (CWT) to represent information in a 2D tensor form.
  arXiv  Detail & Related papers  (2024-04-15T06:01:48Z)
• Unified Training of Universal Time Series Forecasting Transformers [104.56318980466742]
  We present a Masked-based Universal Time Series Forecasting Transformer (Moirai) Moirai is trained on our newly introduced Large-scale Open Time Series Archive (LOTSA) featuring over 27B observations across nine domains. Moirai achieves competitive or superior performance as a zero-shot forecaster when compared to full-shot models.
  arXiv  Detail & Related papers  (2024-02-04T20:00:45Z)
• Gated Recurrent Neural Networks with Weighted Time-Delay Feedback [59.125047512495456]
  We introduce a novel gated recurrent unit (GRU) with a weighted time-delay feedback mechanism. We show that $tau$-GRU can converge faster and generalize better than state-of-the-art recurrent units and gated recurrent architectures.
  arXiv  Detail & Related papers  (2022-12-01T02:26:34Z)
• Stochastic Recurrent Neural Network for Multistep Time Series Forecasting [0.0]
  We leverage advances in deep generative models and the concept of state space models to propose an adaptation of the recurrent neural network for time series forecasting. Our model preserves the architectural workings of a recurrent neural network for which all relevant information is encapsulated in its hidden states, and this flexibility allows our model to be easily integrated into any deep architecture for sequential modelling.
  arXiv  Detail & Related papers  (2021-04-26T01:43:43Z)
• Radflow: A Recurrent, Aggregated, and Decomposable Model for Networks of Time Series [77.47313102926017]
  Radflow is a novel model for networks of time series that influence each other. It embodies three key ideas: a recurrent neural network to obtain node embeddings that depend on time, the aggregation of the flow of influence from neighboring nodes with multi-head attention, and the multi-layer decomposition of time series. We show that Radflow can learn different trends and seasonal patterns, that it is robust to missing nodes and edges, and that correlated temporal patterns among network neighbors reflect influence strength.
  arXiv  Detail & Related papers  (2021-02-15T00:57:28Z)
• 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)
• LAVARNET: Neural Network Modeling of Causal Variable Relationships for Multivariate Time Series Forecasting [18.89688469820947]
  A novel neural network-based architecture is proposed, termed LAgged VAriable NETwork. It intrinsically estimates the importance of latent lagged variables and combines high dimensional representations of them to predict future values time series. Our model is compared with other baseline and state of the art neural network architectures on one simulated data set and four real data sets from meteorology, music, solar activity, finance areas.
  arXiv  Detail & Related papers  (2020-09-02T10:57:28Z)
• Orthogonalized SGD and Nested Architectures for Anytime Neural Networks [30.598394152055338]
  Orthogonalized SGD dynamically re-balances task-specific gradients when training a multitask network. Experiments demonstrate that training with Orthogonalized SGD significantly improves accuracy of anytime networks.
  arXiv  Detail & Related papers  (2020-08-15T03:06:34Z)
• Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks [91.65637773358347]
  We propose a general graph neural network framework designed specifically for multivariate time series data. Our approach automatically extracts the uni-directed relations among variables through a graph learning module. Our proposed model outperforms the state-of-the-art baseline methods on 3 of 4 benchmark datasets.
  arXiv  Detail & Related papers  (2020-05-24T04:02:18Z)
• On the performance of deep learning models for time series classification in streaming [0.0]
  This work is to assess the performance of different types of deep architectures for data streaming classification. We evaluate models such as multi-layer perceptrons, recurrent, convolutional and temporal convolutional neural networks over several time-series datasets.
  arXiv  Detail & Related papers  (2020-03-05T11:41:29Z)
• Stacked Boosters Network Architecture for Short Term Load Forecasting in Buildings [0.0]
  This paper presents a novel deep learning architecture for short term load forecasting of building energy loads. The architecture is based on a simple base learner and multiple boosting systems that are modelled as a single deep neural network. The architecture is evaluated in several short-term load forecasting tasks with energy data from an office building in Finland.
  arXiv  Detail & Related papers  (2020-01-23T08:35:36Z)

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.