Placeholder chapter page. Sections are produced by the book-skills pipeline.
Sections
- 13.1 Sensor windows as tensors; channel and axis structure
- 13.2 1D convolutions and temporal pooling
- 13.3 Multiresolution and dilated features
- 13.4 Learned vs fixed filterbanks
- 13.5 Normalization and augmentation for sensors
- 13.6 Inductive biases for time series
- 13.7 Debugging and inspecting learned filters
Lab 13
train a 1D CNN for human activity recognition; visualize learned filters.