2Introduction Associating SOLAR (SOLAR_A) SOLAR_A structures are hierarchically organized and have ability to classify patterns in a network of sparsely connected neurons.
3AssociationTrainingNeurons learn associations between pattern and its code. Once the training is completed, a network is capable to make necessary associations.TestingWhen the network is presented with the pattern only, it drives the associated input signals to these code values that represent the observed pattern.
4Signal definitionThe inner signals in the network range from 0 to 1. A signal is a determinate low or determinate high if its value is 0 or 1.weak lowweak high0.5 “inactive”, or “high impedance”
5Neurons’ definitionsIf a neuron is able to observe any type of statistical correlations of its input connections, it will function as an associative neuron.Otherwise it will be a transmitting neuron.
6Associative neuronA neuron is called an associative neuron when its inputs I1 and I2 are associatedInputs I1 and I2 are associated if and only if I2 can be implied from I1 and I1 can be implied from I2 simultaneously.
7associative neuronLow I1 is associated with low I2, and high I1 is associated with high I2.I1 and I2 are inputs an associative neuron has received in training.It is quite clear that I1 and I2 are most likely to be simultaneously low or high although there is some noise.This can be verified using P(I2 | I1) and P(I1 | I2), and implying values I2 from I1 and I1 from I2.
8Network Structure Hierarchical structure In horizontal direction, the neurons on one layer can only connect to the neurons on the previous layer.
9Network Structure The connection in vertical direction obeys 80% Gaussian distribution with standard deviation 2+ 20% uniform distribution
10Network StructureThe network uses feedback signals to pass information backwards to the associated inputs.
11TestingDuring testing, the missing parts of the data need to be recovered from the existing data through association.For example, in a pattern recognition problem, the associated code inputs are unknown and therefore set to 0.5.
13Iris Plants Database The Iris database has: 3 classes (Iris Setosa, Iris Versicolour and Iris Virginica)4 numeric attributes (petal length, petal width , sepal length , sepal width )150 instances of 50 instances for each class, where each class refers to a type of iris plant.The classification objectiveIdentify the class ID based on the input feature (attribute) values
14Coding of the databaseThe 4 features were scaled linearly and coded using a sliding bar code .Input bits from (V-Min)+1 to (V-Min)+L will be set high and remaining bits will be lowN-L=Max-Min
15Coding of the databaseWe scaled the 4 features of Iris database between 0-30, andSet the length of L equal to 12The total length of each feature is 42The feature input requires 168 bits
16Coding of the databaseIn order to increase the probability that each feature is associated with sample class code, we merged the 4 features.
18Coding of the database There are 3 classes total We use 3M bits to code the class ID maximizing their code Hamming distanceThe white part is filled by 2M-bit 0 string, while the grey part is filled by M-bit 1 string.
19Iris database simulation Rows class IDRows Features