公开(公告)号：US20250104329A1

公开(公告)日：2025-03-27

申请号：US18653088

申请日：2024-05-02

Applicant: NVIDIA Corporation

Inventor： Jakob Richard Hoydis ,  Faycal Ait Aoudia ,  Sebastian Cammerer ,  Alexander Georg Keller ,  Merlin Nimier-David ,  Nikolaus Binder ,  Guillermo Anibal Marcus Martinez

IPC: G06T15/06

Abstract: Embodiments of the present disclosure relate to neural components for differentiable ray tracing of radio propagation. Differentiable ray tracing may be used to refine the scene geometry of the physical environment, to learn or optimize the scene properties of objects in the scene, to learn or optimize the scene properties of antennas, and to learn or optimize antenna patterns, array geometries, and orientations and positions of transmitters and receivers. Once scene properties have been learned or optimized, the differentiable ray tracer may further be used to simulate the performance of different configurations of the transmitters, receivers, and scene geometry. In an embodiment, one or more of the scene geometry, scene properties, and antenna characteristics are computed by a differentiable parametric function, such as a neural network, etc. and parameters of the differentiable parametric function are learned using the differentiable ray tracing.

公开(公告)号：US11968040B2

公开(公告)日：2024-04-23

申请号：US18118637

申请日：2023-03-07

Applicant: NVIDIA Corporation

Inventor： Jakob Hoydis ,  Sebastian Cammerer ,  Faycal Ait Aoudia ,  Alexander Keller

IPC: H04L1/00 ,  G06N3/04 ,  G06N3/042

CPC classification number: H04L1/0054 ,  G06N3/04 ,  G06N3/042 ,  H04L1/0057

Abstract: Various embodiments and implementations of graph-neural-network (GNN)-based decoding applications are disclosed. The GNN-based decoding schemes are broadly applicable to different coding schemes, and capable of operating on both binary and non-binary codewords, in different implementations. Advantageously, the inventive GNN-based decoding is scalable, even with arbitrary block lengths, and not subject to typical limits with respect to dimensionality. Decoding performance of the inventive GNN-based techniques demonstrably matches or outpaces BCH and LDPC (both regular and 5G NR) decoding algorithms, while exhibiting improvements with respect to number of iterations required and scalability of the GNN-based approach. These inventive concepts are implemented, according to various embodiments, as methods, systems, and computer program products.

公开(公告)号：US20230082536A1

公开(公告)日：2023-03-16

申请号：US17821956

申请日：2022-08-24

Applicant: NVIDIA Corporation

Inventor： Jakob Richard Hoydis ,  Sebastian Cammerer ,  Alexander Georg Keller

IPC: G06N3/08 ,  H04L1/00 ,  H04L25/02

Abstract: A system, apparatus, and method are provided for performing fast re-training of fully fused neural networks configured to implement at least a portion of a transceiver. At least one of a demapping module, an equalization module, or a channel estimation module can be implemented, at least in part, using a fully fused neural network. The neural network can be trained online during operation by acquiring training data sets using a number of received frames of data. Re-training of the neural network is performed periodically to adapt the neural network to changing channel characteristics. In various embodiments, a neural demapper, a neural channel estimator, and a neural receiver are disclosed to replace or augment one or more components of the transceiver. In another embodiment, an auto-encoder can be implemented across a transmitter and receiver to replace most of the components of the transceiver, the auto-encoder being trained via an end-to-end learning algorithm.

公开(公告)号：US20240265619A1

公开(公告)日：2024-08-08

申请号：US18509428

申请日：2023-11-15

Applicant: NVIDIA Corporation

Inventor： Faycal Ait Aoudia ,  Jakob Richard Hoydis ,  Nikolaus Binder ,  Merlin Nimier-David ,  Sebastian Cammerer ,  Alexander Georg Keller ,  Guillermo Anibal Marcus Martinez

IPC: G06T15/06 ,  G06F30/27 ,  G06N3/04

CPC classification number: G06T15/06 ,  G06F30/27 ,  G06N3/04

Abstract: Embodiments of the present disclosure relate to learning digital twins of radio environments. Differentiable ray tracing may be used to refine the scene geometry of the physical environment, to learn or optimize the scene properties of objects in the scene, to learn or optimize the scene properties of antennas, and to learn or optimize antenna patterns, array geometries, and orientations and positions of transmitters and receivers. Once scene properties have been learned or optimized, the differentiable ray tracer may further be used to simulate radio wave propagation to simulate the performance of different configurations of the scene geometry and radio devices, such as antennas. In an embodiment, one or more of the scene geometry, scene properties, and antenna characteristics are computed by a differentiable parametric function, such as a neural network, etc. and parameters of the differentiable parametric function are learned using the differentiable ray tracing.

公开(公告)号：US20230403100A1

公开(公告)日：2023-12-14

申请号：US18118637

申请日：2023-03-07

Applicant: NVIDIA Corporation

Inventor： Jakob Hoydis ,  Sebastian Cammerer ,  Faycal Ait Aoudia ,  Alexander Keller

IPC: H04L1/00 ,  G06N3/04

CPC classification number: H04L1/0054 ,  H04L1/0057 ,  G06N3/04

Abstract: Various embodiments and implementations of graph-neural-network (GNN)-based decoding applications are disclosed. The GNN-based decoding schemes are broadly applicable to different coding schemes, and capable of operating on both binary and non-binary codewords, in different implementations. Advantageously, the inventive GNN-based decoding is scalable, even with arbitrary block lengths, and not subject to typical limits with respect to dimensionality. Decoding performance of the inventive GNN-based techniques demonstrably matches or outpaces BCH and LDPC (both regular and 5G NR) decoding algorithms, while exhibiting improvements with respect to number of iterations required and scalability of the GNN-based approach. These inventive concepts are implemented, according to various embodiments, as methods, systems, and computer program products.

公开(公告)号：US20230052645A1

公开(公告)日：2023-02-16

申请号：US17672566

申请日：2022-02-15

Applicant: NVIDIA Corporation

Inventor： Alexander Georg Keller ,  Alex John Bauld Evans ,  Thomas Müller-Höhne ,  Faycal Ait Aoudia ,  Nikolaus Binder ,  Jakob Hoydis ,  Christoph Hermann Schied ,  Sebastian Cammerer ,  Matthijs van Keirsbilck ,  Guillermo Anibal Marcus Martinez

IPC: G06N3/08 ,  G06N3/02

Abstract: Neural network performance is improved in terms of training speed and/or accuracy by encoding (mapping) inputs to the neural network into a higher dimensional space via a hash function. The input comprises coordinates used to identify a point within a d-dimensional space (e.g., 3D space). The point is quantized and a set of vertex coordinates corresponding to the point are input to a hash function. For example, for d=3, space may be partitioned into axis-aligned voxels of identical size and vertex coordinates of a voxel containing the point are input to the hash function to produce a set of encoded coordinates. The set of encoded coordinates is used to lookup D-dimensional feature vectors in a table of size T that have been learned. The learned feature vectors are filtered (e.g., linearly interpolated, etc.) based on the coordinates of the point to compute a feature vector corresponding to the point.