Split a Tensor for Shuffling in Outsourcing Computation Tasks: abstract simplified (17715863)

• This abstract for appeared for patent application number 17715863 Titled 'Split a Tensor for Shuffling in Outsourcing Computation Tasks'

Simplified Explanation

The abstract describes a method for protecting the access to a tensor used in deep learning computations when outsourcing the computations to external entities. The tensor is a data structure with elements arranged in rows and columns. The method involves dividing the tensor into smaller parts and shuffling them, along with other tasks, before outsourcing them to external entities. The results returned by these entities are then used to compute the final result of the tensor in the neural network. This partitioning and shuffling technique helps prevent the external entities from accessing or reconstructing the original tensor.

Original Abstract Submitted

Protection of access to a tensor in outsourcing deep learning computations via shuffling. For example, the tensor in the computation of an artificial neural network can have elements arranged in a first dimension of rows and a second dimension of columns. The tensor can be partitioned along the first dimension and the second dimension to generate computing tasks that are shuffled and/or mixed with other tasks for outsourcing to external entities. Computing results returned from the external entities can be used to generate a computing result of the tensor in the computation of the artificial neural network. The partitioning and shuffling can prevent the external entities from accessing and/or reconstructing the tensor.