time seriesfamily
TCN (Temporal Convolutional Network)
Generic convolutional architecture for sequence modelling, shown to match or beat recurrent networks on many sequence tasks. Paper by Bai et al. (2018).
Levelfamily
Classtime series
Parametersnot in the notes
Contextnot in the notes
Released4 Mar 2018
Opennessopen source
Runs onnot in the notes
Statusactive
Identity
- Developer
- Carnegie Mellon University, Intel
- Family
- not in the notes
- Released
- 4 Mar 2018 sourcesannouncement page
- Weights published
- –
- Record checked
- 12 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.
Architecture and Size
- Architecture
- CNN Causal dilated convolutions with residual blocks
- Total parameters
- – sources
- Active parameters
- –
- Checkpoint parameters
- –
- Context length
- not in the notes
- Input
- time series
- Output
- time series
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).
Openness and Access
- Openness
- open source
- Licence
- MIT License sources
- Access routes
- not in the notes
Where this comes from
The licence file governs over registry tags and aggregator labels.
Deployment
- Runs on
- not in the notes
- Footprint
- Licence is that of the authors' locuslab/TCN repository (MIT).
- Runtimes
- not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.
Indonesia
- Indonesian support
- not stated
- Regional languages
- not in the notes
- Jakarta hosting
- unknown
- Languages
- not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.
Benchmark Results
The notes record no benchmark result for this model.
Lineage
The notes record no lineage for this model.
Industry Use Cases
No industry use case links this model.
Links
ModelTCN (Temporal Convolutional Network)Carnegie Mellon University, time series
TCN (Temporal Convolutional Network)Carnegie Mellon University, time seriesUse CasesIndustrial Forecasting (Load, Throughput, Demand)IndustrialDemand ForecastingRetail and LogisticsUse cases of models in the same R&D topic; none is recorded for this model itself.
Who Runs Itnone recordedDeployments of these use cases; none names this model.
Sources
- arxiv.org/abs/1803.01271 https://arxiv.org/abs/1803.01271
- github.com/locuslab/TCN https://github.com/locuslab/TCN
- nixtlaverse.nixtla.io/neuralforecast/docs/capabilities/overview.html https://nixtlaverse.nixtla.io/neuralforecast/docs/capabilities/overview.html
- modelzoo.co/model/tcn-pytorch https://modelzoo.co/model/tcn-pytorch
- huggingface.co/datasets/pwc-archive/methods https://huggingface.co/datasets/pwc-archive/methods
- arxiv.org/html/1803.01271 https://arxiv.org/html/1803.01271
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "TCN (Temporal Convolutional Network)", https://aurion.semai.id/models/tcn/, records of October 2026.