Method and circuits for associating a norm to each component of an input pattern presented to a neural network
AssigneeIBM Corporation
InventorsGhislain Imbert de Tremiolles, Pascal Tannhof
Life of this patent
Estimating the term…
Loading patent…
AssigneeIBM Corporation
InventorsGhislain Imbert de Tremiolles, Pascal Tannhof
Estimating the term…
The method and circuits of the present invention aim to associate a norm to each component of an input pattern presented to an input space mapping algorithm based artificial neural network (ANN) during the distance evaluation process. The set of norms, referred to as the “component” norms is memorized in specific memorization means in the ANN. In a first embodiment, the ANN is provided with a global memory, common for all the neurons of the ANN, that memorizes all the component norms. For each component of the input pattern, all the neurons perform the elementary (or partial) distance calculation with the corresponding prototype components stored therein during the distance evaluation process using the associated component norm. The distance elementary calculations are then combined using a “distance” norm to determine the final distance between the input pattern and the prototypes stored in the neurons. In another embodiment, the set of component norms is memorized in the neurons themselves in the prototype memorization means, so that the global memory is no longer physically necessary. This implementation allows to significantly optimize the consumed silicon area when the ANN is integrated in a silicon chip.
An improved Artificial Neural Network (ANN) adapted to associate a component norm (C_norm) to each component of an input pattern having p components in the process of evaluating the final distance between the input pattern and the prototypes stored in the neurons of the ANN comprising:
An improved Artificial Neural Network (ANN) adapted to associate a component norm (C_norm) to each component of an input pattern having p components in the process of evaluating the final distance between the input pattern and the prototypes stored in the neurons of the ANN that is adapted to be partitioned in m groups of neurons corresponding to m different global contexts comprising:
An improved Artificial Neural Network (ANN) adapted to associate a component norm (C_norm) to each component of an input pattern having p components in the process of evaluating the final distance between the input pattern and the prototypes stored in the neurons of the ANN comprising:
An improved Artificial Neural Network (ANN) adapted to associate a component norm (C_norm) to each component of an input pattern having p components in the process of evaluating the final distance between the input pattern and the prototypes stored in the neurons of the ANN that is adapted to be partitioned in m groups of neurons corresponding to m different global contexts comprising:
A method for associating a component norm to each component of an input pattern (having p components) stored in an external memory (host) and to the corresponding component of all prototypes stored in the n neurons of an artificial neural network (ANN) in the process of evaluating the final distance between said input pattern and the prototypes for each neuron using a distance norm comprising the steps of:
A method for associating a component norm to each component of an input pattern (having p components) stored in an external memory (host) and to the corresponding component of at least one group of prototypes stored in the n neurons of an artificial neural network (ANN) partitioned in a an plurality of m groups having each a determined context in the process of evaluating the final distance between said input pattern and the prototypes for each neuron of said at least one group using a distance norm comprising the steps of:
Dependencies are inferred from the claim text.