Uses Temporal Convolutional Networks with dilated causal convolutions for sequence-to-sequence changepoint prediction.
tcn_detect(
data,
true_changepoints = NULL,
window_size = 64,
n_filters = 64,
kernel_size = 3,
dilations = c(1, 2, 4, 8, 16),
dropout = 0.2,
epochs = 50,
threshold = 0.5,
verbose = FALSE
)List with changepoints, probabilities, and model
Numeric vector of time series data
Optional vector of known changepoints for supervised training. If NULL, uses unsupervised approach.
Size of input window (default: 64)
Number of convolutional filters (default: 64)
Kernel size for convolutions (default: 3)
Dilation rates (default: c(1, 2, 4, 8, 16))
Dropout rate (default: 0.2)
Training epochs (default: 50)
Detection threshold (default: 0.5)
Show training progress (default: FALSE)
Bai, S., Kolter, J. Z., and Koltun, V. (2018). An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling