公开(公告)号：US11640295B2

公开(公告)日：2023-05-02

申请号：US16913756

申请日：2020-06-26

Applicant: Intel Corporation

Inventor： Mariano Tepper ,  Bryn Keller ,  Mihai Capota ,  Vy Vo ,  Nesreen Ahmed ,  Theodore Willke

IPC: G06F8/75 ,  G06N3/08 ,  G06N3/04

Abstract: Systems, apparatuses and methods may provide for technology that generates a dependence graph based on a plurality of intermediate representation (IR) code instructions associated with a compiled program code, generates a set of graph embedding vectors based on the plurality of IR code instructions, and determines, via a neural network, one of an analysis of the compiled program code or an enhancement of the program code based on the dependence graph and the set of graph embedding vectors. The technology may provide a graph attention neural network that includes a recurrent block and at least one task-specific neural network layer, the recurrent block including a graph attention layer and a transition function. The technology may also apply dynamic per-position recurrence-halting to determine a number of recurring steps for each position in the recurrent block based on adaptive computation time.

公开(公告)号：US20200326934A1

公开(公告)日：2020-10-15

申请号：US16913756

申请日：2020-06-26

Applicant: Intel Corporation

Inventor： Mariano Tepper ,  Bryn Keller ,  Mihai Capota ,  Vy Vo ,  Nesreen Ahmed ,  Theodore Willke

IPC: G06F8/75 ,  G06N3/04 ,  G06N3/08

Abstract: Systems, apparatuses and methods may provide for technology that generates a dependence graph based on a plurality of intermediate representation (IR) code instructions associated with a compiled program code, generates a set of graph embedding vectors based on the plurality of IR code instructions, and determines, via a neural network, one of an analysis of the compiled program code or an enhancement of the program code based on the dependence graph and the set of graph embedding vectors. The technology may provide a graph attention neural network that includes a recurrent block and at least one task-specific neural network layer, the recurrent block including a graph attention layer and a transition function. The technology may also apply dynamic per-position recurrence-halting to determine a number of recurring steps for each position in the recurrent block based on adaptive computation time.

公开(公告)号：US20200324794A1

公开(公告)日：2020-10-15

申请号：US16912241

申请日：2020-06-25

Applicant: Intel Corporation

Inventor： Guixiang Ma ,  Nicole Beckage ,  Nesreen Ahmed ,  Ignacio Alvarez

IPC: B60W60/00 ,  G06N3/04 ,  G06N3/08 ,  G06F16/28 ,  G06F16/29

Abstract: Systems, apparatuses and methods may provide for technology that generates a series of time-stamped object graphs based on object trajectory histories derived from external object data for a plurality of external objects, such as vehicles. The technology may also generate, via a first neural network such as a graph attention network, a series of relational object representations based on the series of time-stamped object graphs, and determine, via a second neural network such as a long short-term memory network, predicted object trajectories for the plurality of external objects based on the series of relational object representations. The technology may also modify behavior of an autonomous vehicle based on the predicted object trajectories and real-time perceptual error information.