In this paper, we present a simple, yet effective, attention and memory mechanism that is reminiscent of Memory Networks and we demonstrate it in question-answering scenarios. Our mechanism is based on four simple premises: a) memories can be formed from word sequences by using convolutional networks; b) distance measurements can be taken at a neuronal level; c) a recursive softmax function can...

The problem of the efficient design material microstructures exhibiting desired properties spans a variety engineering and science applications. ability to rapidly generate that exhibit user-specified property distributions can transform iterative process traditional microstructure-sensitive design. We reformulate microstructure using constrained generative adversarial network (GAN) model. This...

Abstract Representation learning for video is increasingly gaining attention in the field of computer vision. For instance, prediction models enable activity and scene forecasting or vision-based planning control. In this article, we investigate combination differentiable physics spatial transformers a deep action conditional representation network. By our model learns physically interpretable ...

One of the most important fields in robotics is the optimization of controllers. Currently, robots are often treated as a black box in this optimization process, which is the reason why derivative-free optimization methods such as evolutionary algorithms or reinforcement learning are omnipresent. When gradient-based methods are used, models are kept small or rely on finite difference approximat...

1. We consider differential topology to be the study of differentiable manifolds and differentiable maps. Then, naturally, manifolds are considered equivalent if they are diffeomorphic, i.e., there exists a differentiable map from one to the other with a differentiable inverse. For convenience, differentiable means C; in the problems we consider, C' would serve as well. The notions of different...

The theory of derivative of noninteger order goes back to Leibniz, Liouville, Riemann, Grunwald and Letnikov. Derivatives of fractional order have found many applications in recent studies in mechanics, physics, economics, medicine.Classes of fractional differentiable systems have studied in [10], [4]. In the first section the fractional tangent bundle to a differentiable manifold is defined, u...

‎In this paper‎, ‎we shall establish some extended Simpson-type inequalities‎ ‎for differentiable convex functions and differentiable concave functions‎ ‎which are connected with Hermite-Hadamard inequality‎. ‎Some error estimates‎ ‎for the midpoint‎, ‎trapezoidal and Simpson formula are also given‎.

We review recent developments in differential topology with special concern for their possible significance to physical theories, especially general relativity. In particular we are concerned here with the discovery of the existence of non-standard (“fake” or “exotic”) differentiable structures on topologically simple manifolds such as S, Rand S ×R. Because of the technical difficulties involve...

We introduce a paradigm for understanding physical scenes without human annotations. At the core of our system is a physical world representation that is first recovered by a perception module and then utilized by physics and graphics engines. During training, the perception module and the generative models learn by visual de-animation — interpreting and reconstructing the visual information st...

In this paper, we train turbulence models based on convolutional neural networks. These learned improve under-resolved low resolution solutions to the incompressible Navier-Stokes equations at simulation time. Our study involves development of a differentiable numerical solver that supports propagation optimisation gradients through multiple steps. The significance property is demonstrated by s...