Towards Nonlinear Disentanglement in Natural Data with Temporal Sparse Coding

Understand

We construct an unsupervised learning model that achieves nonlinear disentanglement of underlying factors of variation in naturalistic videos.

• Previous work suggests that representations can be disentangled if all but a few factors in the environment stay constant at any point in time.
• As a result, algorithms proposed for this problem have only been tested on carefully constructed datasets with this exact property, leaving it unclear whether they will transfer to natural scenes.
• Here we provide evidence that objects in segmented natural movies undergo transitions that are typically small in magnitude with occasional large jumps, which is characteristic of a temporally sparse distribution.