Corpus ID: 229152569

Learning Representations from Temporally Smooth Data

@article{Moghaddam2020LearningRF,
  title={Learning Representations from Temporally Smooth Data},
  author={Shima Rahimi Moghaddam and Fanjun Bu and C. Honey},
  journal={ArXiv},
  year={2020},
  volume={abs/2012.06694}
}
Events in the real world are correlated across nearby points in time, and we must learn from this temporally smooth data. However, when neural networks are trained to categorize or reconstruct single items, the common practice is to randomize the order of training items. What are the effects of temporally smooth training data on the efficiency of learning? We first tested the effects of smoothness in training data on incremental learning in feedforward nets and found that smoother data slowed… Expand

References

SHOWING 1-10 OF 41 REFERENCES
Biologically plausible deep learning - but how far can we go with shallow networks?
Understanding the difficulty of training deep feedforward neural networks
Constructing and Forgetting Temporal Context in the Human Cerebral Cortex
Switching between internal and external modes: A multiscale learning principle
A reservoir of time constants for memory traces in cortical neurons
Perceptual straightening of natural videos
Induction of Multiscale Temporal Structure
Curriculum learning
...
1
2
3
4
5
...