Corpus ID: 220768838

Evaluation metrics for behaviour modeling

@article{Im2020EvaluationMF,
  title={Evaluation metrics for behaviour modeling},
  author={D. Im and Iljung S. Kwak and K. Branson},
  journal={ArXiv},
  year={2020},
  volume={abs/2007.12298}
}
A primary difficulty with unsupervised discovery of structure in large data sets is a lack of quantitative evaluation criteria. In this work, we propose and investigate several metrics for evaluating and comparing generative models of behavior learned using imitation learning. Compared to the commonly-used model log-likelihood, these criteria look at longer temporal relationships in behavior, are relevant if behavior has some properties that are inherently unpredictable, and highlight biases in… Expand

References

SHOWING 1-10 OF 34 REFERENCES
Point process latent variable models of larval zebrafish behavior
Deep attention networks reveal the rules of collective motion in zebrafish
Probabilistic Models of Larval Zebrafish Behavior Reveal Structure on Many Scales
Learning recurrent representations for hierarchical behavior modeling
An Evaluation of Trajectory Prediction Approaches and Notes on the TrajNet Benchmark
Mapping Sub-Second Structure in Mouse Behavior
Detecting Social Actions of Fruit Flies
Activity Forecasting
A stochastic neuronal model predicts random search behaviors at multiple spatial scales in C. elegans
...
1
2
3
4
...