Uses self-supervised contrastive learning to detect changepoints by identifying where the learned representations change significantly.
cpc_detect(
data,
window_size = 64,
encoding_dim = 32,
n_negative = 10,
prediction_steps = 5,
epochs = 100,
threshold = NULL,
verbose = FALSE
)List with changepoints and learned encodings
Numeric vector
Window size (default: 64)
Encoding dimension (default: 32)
Number of negative samples (default: 10)
Future steps to predict (default: 5)
Training epochs (default: 100)
Detection threshold for representation distance
Show progress
Oord, A. v. d., Li, Y., and Vinyals, O. (2018). Representation Learning with Contrastive Predictive Coding