|
|
Inside EasyNN-plusA Neural Network produced by EasyNN-plus has two components. The components are the Node and the Connection. These components are replicated to make the neural network. A Node consists of a Neuron with positioning and connecting information. A Connection consists of a Weight with node addressing information.   The Grid used by EasyNN-plus also has two components. These are the Example row and the Input/Output column. These are replicated to make the grid.     All the component parts of EasyNN-plus are implemented as reusable classes to simplify future development. The following information is a very basic description of the classes. The true names of the variables and functions are not used.     The Neural Network   Node   Positioning and connection
Type: Input, Output or Hidden.   Number: Node reference number.   Layer Type: Input, Output or Hidden.   First In: Number of the first connection into this node.   Last In: Number of the last connection into this node.   Neuron   Net Input: Sum of all activation * weight inputs to the node + Bias.   Activation: 1.0 / (1.0 + e (-Net Input))   Output Node Error: Target - Activation   Hidden Node Error: Error + Delta * Weight   Delta: Error * Activation * (1.0 - Activation)   Bias: Bias + Delta Bias   Bias Derivative: Bias derivative + Delta   Delta Bias: Learning Rate * Bias Derivative + Momentum * Delta Bias   Connection   Node addressing   To: The Node that the connection is going to.   From: Node that the connection is coming from.   Number: Connection reference number.   Weight   Type: Variable or Fixed.   Weight: Weight + Delta Weight.   Weight Derivative: Weight Derivative + To: Delta * From: Activation.   Delta Weight: Learning Rate * Weight Derivative + Momentum * Delta Weight.   The Grid
Example row
Name: Optional Example name.   Type: Training, Validating, Querying or Exclude.   Values: Array of values in example row.   Scaled Values: Array of scaled values in example row.   Forecasted Values: Array of forecasted values in example row.   Input/Output column
Name: Optional Input/Output name.   Type: Input, Output, Serial or Exclude.   Mode: Real, Integer, Bool, Text or Image.   Lock: True or False.   Lowest: Lowest value in column.   Highest: Highest value in column.         | ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
|