20 — Deep Learning

N-BEATS & N-HiTS#

Deep Learning✓ Mathematical
◆ The PatternPure MLP architectures for forecasting

N-BEATS uses stacks of fully-connected blocks that produce both a backward forecast (reconstructing the input) and a forward forecast. Residual connections between blocks let each stack focus on what previous stacks missed. The interpretable variant decomposes into trend and seasonal basis functions. N-HiTS adds hierarchical interpolation for efficiency.

// Interactive — N-BEATS block architecture
# Python — N-BEATS with Darts
from darts.models import NBEATSModel

model = NBEATSModel(
    input_chunk_length=96,
    output_chunk_length=24,
    generic_architecture=True,
    num_stacks=30,
    num_layers=4
)
model.fit(train_series)
pred = model.predict(n=24)
Pattern bridge: N-BEATS’ residual stacking works like boosting — each block fits the residual from the previous one. The backward/forward forecast split mirrors the train/validation concept built into the architecture itself.
← Previous
Transformers for Time Series
Open in the full reader, with the topic sidebar →