Neuralmagic Inc.

Microsoft Technology Licensing, LLC

Dan Alistarh

Nir N Shavit

Alexander Matveev

Justin Kopinsky

Mark Kurtz

Rati Gelashvili

Bozidar Radunovic

Thomas Karagiannis

Ghufran Baig

A system and method of accelerating execution of a NN model, by at least one processor may include: receiving a first matrix A, representing elements of a kernel K of the NN model and a second matrix B, representing elements of an input I to kernel K; producing from matrix A, a group-sparse matrix A', comprising G tensors of elements. The number of elements in each tensor is defined by, or equal to a number of entries in each index of an input tensor register used for a specific Single Instruction Multiple Data (SIMD) tensor operation, and all elements of A&#x2032; outside said G tensors are null. The system and method may further include executing kernel K on input I, by performing at least one computation of the SIMD tensor operation, having as operands elements of a tensor of the G tensors and corresponding elements of the B matrix.

System and method of accelerating execution of a neural network

Training a neural network (NN) may include training a NN N, and for S, a version of N to be sparsified (e.g. a copy of N), removing NN elements from S to create a sparsified version of S, and training S using outputs from N (e.g. 'distillation'). A boosting or reintroduction phase may follow sparsification: training a NN may include for a trained NN N and S, a sparsified version of N, re-introducing NN elements previously removed from S, and training S using outputs from N. The boosting phase need not use a NN sparsified by 'distillation.' Training and sparsification, or training and reintroduction, may be performed iteratively or over repetitions.

Systems and methods for neural network pruning with accuracy preservation

Techniques for distributed selection of white space channels are described. According to one or more embodiments, techniques described herein enable fair allocation of available white spaces among entities seeking access to the white spaces, such as base stations and client devices in a particular geographical region. According to one or more embodiments, techniques for distributed selection of white space channels enable individual network components to detect white space network attributes and distribute white space channels based on the detected attributes. Alternatively or additionally, multiple base stations can collaborate to share information about white spaces in a particular region.

Distributed selection of white space channels

Growing community of inventors

Meyrin, Switzerland

Dan Alistarh