Abstract: Approaches in accordance with various embodiments provide for fluid simulation with substantially reduced time and memory requirements with respect to conventional approaches. In particular, various embodiments can perform time and energy efficient, large scale fluid simulation on processing hardware using a method that does not solve for the Navier-Stokes equations to enforce incompressibility. Instead, various embodiments generate a density tensor and rigid body map tensor for a large number of particles contained in a sub-domain. Collectively, the density tensor and rigid body map may represent input channels of a network with three spatial-dimensions. The network may apply a series of operations to the input channels to predict an updated position and updated velocity for each particle at the end of a frame. Such approaches can handle tens of millions of particles within a virtually unbounded simulation domain, as compared to classical approaches that solve for the Navier-Stokes equations.

Abstract: Approaches in accordance with various embodiments provide for fluid simulation with substantially reduced time and memory requirements with respect to conventional approaches. In particular, various embodiments can perform time and energy efficient, large scale fluid simulation on processing hardware using a method that does not solve for the Navier-Stokes equations to enforce incompressibility. Instead, various embodiments generate a density tensor and rigid body map tensor for a large number of particles contained in a sub-domain. Collectively, the density tensor and rigid body map may represent input channels of a network with three spatial-dimensions. The network may apply a series of operations to the input channels to predict an updated position and updated velocity for each particle at the end of a frame. Such approaches can handle tens of millions of particles within a virtually unbounded simulation domain, as compared to classical approaches that solve for the Navier-Stokes equations.

Abstract: Personalized coaching is provided to users of an application, such as players of an electronic gaming application. Data can be obtained that demonstrates how skilled users utilize an application, such as how professional players play a game. This data can be used to train a machine learning model for the game. Gameplay data for an identified player can be obtained, and related information provided as input to the trained model. The model can infer one or more actions or strategies to be taken by the player in order to achieve a determined goal. The information can be conveyed to the player using visual, audio, or haptic guidance during gameplay, or can be provided offline, such as with video or rendered replay of the game session. The types of advice or coaching given can vary depending upon factors such as the goals, skill level, and preferences of the player, and can update over time.

Abstract: Personalized coaching is provided to users of an application, such as players of an electronic gaming application. Data can be obtained that demonstrates how skilled users utilize an application, such as how professional players play a game. This data can be used to train a machine learning model for the game. Gameplay data for an identified player can be obtained, and related information provided as input to the trained model. The model can infer one or more actions or strategies to be taken by the player in order to achieve a determined goal. The information can be conveyed to the player using visual, audio, or haptic guidance during gameplay, or can be provided offline, such as with video or rendered replay of the game session. The types of advice or coaching given can vary depending upon factors such as the goals, skill level, and preferences of the player, and can update over time.

Abstract: Approaches in accordance with various embodiments provide for fluid simulation with substantially reduced time and memory requirements with respect to conventional approaches. In particular, various embodiments can perform time and energy efficient, large scale fluid simulation on processing hardware using a method that does not solve for the Navier-Stokes equations to enforce incompressibility. Instead, various embodiments generate a density tensor and rigid body map tensor for a large number of particles contained in a sub-domain. Collectively, the density tensor and rigid body map may represent input channels of a network with three spatial-dimensions. The network may apply a series of operations to the input channels to predict an updated position and updated velocity for each particle at the end of a frame. Such approaches can handle tens of millions of particles within a virtually unbounded simulation domain, as compared to classical approaches that solve for the Navier-Stokes equations.

Abstract: Approaches in accordance with various embodiments provide for fluid simulation with substantially reduced time and memory requirements with respect to conventional approaches. In particular, various embodiments can perform time and energy efficient, large scale fluid simulation on processing hardware using a method that does not solve for the Navier-Stokes equations to enforce incompressibility. Instead, various embodiments generate a density tensor and rigid body map tensor for a large number of particles contained in a sub-domain. Collectively, the density tensor and rigid body map may represent input channels of a network with three spatial-dimensions. The network may apply a series of operations to the input channels to predict an updated position and updated velocity for each particle at the end of a frame. Such approaches can handle tens of millions of particles within a virtually unbounded simulation domain, as compared to classical approaches that solve for the Navier-Stokes equations.

Abstract: Personalized coaching is provided to users of an application, such as players of an electronic gaming application. Data can be obtained that demonstrates how skilled users utilize an application, such as how professional players play a game. This data can be used to train a machine learning model for the game. Gameplay data for an identified player can be obtained, and related information provided as input to the trained model. The model can infer one or more actions or strategies to be taken by the player in order to achieve a determined goal. The information can be conveyed to the player using visual, audio, or haptic guidance during gameplay, or can be provided offline, such as with video or rendered replay of the game session. The types of advice or coaching given can vary depending upon factors such as the goals, skill level, and preferences of the player, and can update over time.