Mechanism diagram · CNN / TCN
How it works
TCN stacks 1-D causal convolutions with increasing dilation factors.
Receptive field grows exponentially with depth: a TCN with N layers and base kernel size k has receptive field roughly k × 2^N.
Residual connections stabilise deep stacks.
Pros and cons on this universe
Pros
- Parallelisable across time — much faster than RNN at training.
- Standard baseline in the time-series literature.
- Receptive field is interpretable and easy to tune.
Cons / failure modes
- Rank #22 IC — weak on this universe.
- Beaten by BITCN (bidirectional variant) and ModernTCN on the literature benchmark.
- No dossier in the research base.