Artificial neural network with trainable activation functions and fractional derivative values
AssigneeIntel Corporation
InventorsJulio Zamora Esquivel, Jose Camacho Perez, Paulo Lopez Meyer, Hector Cordourier Maruri, Jesus Cruz Vargas
Life of this patent
Estimating the term…
Abstract
Systems, apparatuses and methods may provide for technology that adjusts a plurality of weights in a neural network model and adjusts a plurality of activation functions in the neural network model. The technology may also output the neural network model in response to one or more conditions being satisfied by the plurality of weights and the plurality of activation functions. In one example, two or more of the activation functions are different from one another and the activation functions are adjusted on a per neuron basis.
Claims24
A computing system comprising:
- a network controller;
- a processor coupled to the network controller;
- and
- a memory coupled to the processor, the memory including a set of instructions, which when executed by the processor, cause the computing system to:
- adjust a plurality of weights in a neural network model,
- adjust, via a plurality of difference values on a per neuron basis, a plurality of activation functions in the neural network model, and
- output the neural network model in response to one or more conditions being satisfied by the plurality of weights and the plurality of activation functions.
A semiconductor apparatus comprising:
- one or more substrates;
- and
- logic coupled to the one or more substrates, wherein the logic is implemented at least partly in one or more of configurable logic or fixed-functionality hardware logic, the logic coupled to the one or more substrates to:
- adjust a plurality of weights in a neural network model,
- adjust, via a plurality of difference values on a per neuron basis, a plurality of activation functions in the neural network model, and
- output the neural network model in response to one or more conditions being satisfied by the plurality of weights and the plurality of activation functions.
At least one computer readable storage medium comprising a set of instructions, which when executed by a computing system, cause the computing system to:
- adjust a plurality of weights in a neural network model;
- adjust, via a plurality of difference values on a per neuron basis, a plurality of activation functions in the neural network model;
- and
- output the neural network model in response to one or more conditions being satisfied by the plurality of weights and the plurality of activation functions.
A method comprising:
- adjusting a plurality of weights in a neural network model;
- adjusting, via a plurality of difference values on a per neuron basis, a plurality of activation functions in the neural network model;
- and
- outputting the neural network model in response one or more conditions being satisfied by the plurality of weights and the plurality of activation functions.
Dependencies are inferred from the claim text.