Releases: SeldonIO/alibi-detect
Releases · SeldonIO/alibi-detect
v0.4.0
v0.3.1
v0.3.1 (2020-02-26)
Added
- Adversarial autoencoder detection method (offline method,
alibi_detect.ad.adversarialae.AdversarialAE
) - Add pretrained adversarial and outlier detectors to Google Cloud Bucket and include fetch functionality
- Add data/concept drift dataset (CIFAR-10-C) to Google Cloud Bucket and include fetch functionality
- Update VAE loss function and log var layer
- Fix tests for Prophet outlier detector on Python 3.6
- Add batch sizes for all detectors
v0.3.0
v0.3.0 (2020-01-17)
Added
- Multivariate time series outlier detection method OutlierSeq2Seq (offline method,
alibi_detect.od.seq2seq.OutlierSeq2Seq
) - ECG and synthetic data examples for OutlierSeq2Seq detector
- Auto-Encoder outlier detector (offline method,
alibi_detect.od.ae.OutlierAE
) - Including tabular and categorical perturbation functions (
alibi_detect.utils.perturbation
)
v0.2.0
v0.2.0 (2019-12-06)
Added
- Univariate time series outlier detection methods: Prophet (offline method,
alibi_detect.od.prophet.OutlierProphet
)
and Spectral Residual (online method,alibi_detect.od.sr.SpectralResidual
) - Function for fetching Numenta Anomaly Benchmark time series data (
alibi_detect.datasets.fetch_nab
) - Perturbation function for time series data (
alibi_detect.utils.perturbation.inject_outlier_ts
) - Roadmap
v0.1.0
Change Log
v0.1.0 (2019-11-19)
Added
- Isolation Forest (Outlier Detection)
- Mahalanobis Distance (Outlier Detection)
- Variational Auto-Encoder (VAE, Outlier Detection)
- Auto-Encoding Gaussian Mixture Model (AEGMM, Outlier Detection)
- Variational Auto-Encoding Gaussian Mixture Model (VAEGMM, Outlier Detection)
- Adversarial Variational Auto-Encoder (Adversarial Detection)