Feature acquisition in predictive modeling is an important task many practical applications. For example, patient health prediction, we do not fully observe their personal features and need to dynamically select acquire. Our goal acquire a small subset of that maximize prediction performance. Recently, some works reformulated feature as Markov decision process applied reinforcement learning (RL...

Procedural modeling allows for an automatic generation of large amounts similar assets, but there is limited control over the generated output. We address this problem by introducing Automatic Differentiable Modeling (ADPM). The forward procedural model generates a final editable model. user modifies output interactively, and modifications are transferred back to as its parameters solving inver...

We introduce a novel differentiable hybrid traffic simulator , which simulates using model of both macroscopic and microscopic models can be directly integrated into neural network for control flow optimization. This is the first that compute gradients states across time steps inhomogeneous lanes. To gradient between two types in framework, we present intermediate conversion component bridges l...

We present a novel, fast differentiable simulator for soft-body learning and control applications. Existing simulators can be classified into two categories based on their time integration methods: Simulators using explicit timestepping schemes require tiny timesteps to avoid numerical instabilities in gradient computation, implicit typically compute gradients by employing the adjoint method so...

We introduce a new model, the Recurrent Entity Network (EntNet). It is equipped with a dynamic long-term memory which allows it to maintain and update a representation of the state of the world as it receives new data. For language understanding tasks, it can reason on-the-fly as it reads text, not just when it is required to answer a question or respond as is the case for a Memory Network (Suk...

In the recent paper Communications in Nonlinear Science and Numerical Simulation. Vol.18. No.11. (2013) 2945-2948, it was demonstrated that a violation of the Leibniz rule is a characteristic property of derivatives of non-integer orders. It was proved that all fractional derivatives Dα, which satisfy the Leibniz rule Dα(fg) = (Dαf) g+ f (Dαg), should have the integer order α = 1, i.e. fraction...

Cost functions formulated in four-dimensional variational data assimilation (4DVAR) are nonsmooth in the presence of discontinuous physical processes (i.e., the presence of ‘‘on–off’’ switches in NWP models). The adjoint model integration produces values of subgradients, instead of gradients, of these cost functions with respect to the model’s control variables at discontinuous points. Minimiza...