CLEVR, on which we achieve state-of-the-art, super-human performance; text-based question answering using the bAbI suite of tasks; and complex reasoning about dynamic physical systems.

Neural Information Processing Systems http://nips.cc/

We study fairness in collaborative-filtering recommender systems, which are sensitive to discrimination that exists in historical data.

Neural Information Processing Systems http://nips.cc/

The predictive learning of spatiotemporal sequences aims to generate future images by learning from the historical frames, where spatial appearances and temporal variations are two crucial structures.

The FS-RNN incorporates the strengths of both multiscale RNNs and deep transition RNNs as it processes sequential data on different timescales and learns complex transition functions from one time step to the next.

Calcium imaging has become an indispensable tool in systems neuroscience research.

Our key idea is to introduce a novel self-expressive layer between the encoder and the decoder to mimic the "self-expressiveness" property that has proven effective in traditional subspace clustering.

Linear Dynamical Systems (LDSs) are fundamental tools for modeling spatiotemporal data in various disciplines.

This problem, chordal Markov network structure learning (CMSL), is computationally notoriously challenging; e.g., finding a maximum likelihood chordal Markov network