Building of Custom Convolution Filter for a Neural Network Using an Automated Evolutionary Process
AssigneeInternational Business Machines Corporation
InventorsMihir Choudhury, Atin Sood, Ruchir Puri
Life of this patent
Estimating the term…
Loading patent…
AssigneeInternational Business Machines Corporation
InventorsMihir Choudhury, Atin Sood, Ruchir Puri
Estimating the term…
Mechanisms are provided for synthesizing a computer implemented neural network. An initially trained neural network is received and modified by introducing a new hidden layer of neurons and new connections that connect the new hidden layer of neurons to an output layer and a previous layer of neurons previously directly connected to the output layer of neurons to generate a modified neural network. The modified neural network is trained through one or more epochs of machine learning to generate modified weight values for the new connections and the new connections are pruned based on the modified weight values to remove a subset of the new connections and leaving remaining connections in the modified neural network. A merge operation is performed on the remaining connections in the modified neural network to generate a custom convolution filter and modified neural network. The modified neural network is then retrained for deployment.
A method, in a data processing system, for synthesizing a computer implemented neural network with a custom convolution filter, the method comprising:
A computer program product comprising a computer readable storage medium having a computer readable program stored therein, wherein the computer readable program, when executed on a computing device, causes the computing device to synthesize a computer implemented neural network with a custom convolution filter, at least by:
An apparatus comprising:
Dependencies are inferred from the claim text.