ConvolutionalNN {Microsoft.VisualBasic.MachineLearning.CNN}

.NET clr documentation

ConvolutionalNN

Description

A network class holding the layers and some helper functions for training and validation. Convolutional neural network (CNN) is a regularized type of feed-forward neural network that learns feature engineering by itself via filters (or kernel) optimization. Vanishing gradients and exploding gradients, seen during backpropagation in earlier neural networks, are prevented by using regularized weights over fewer connections. @author Daniel Persson (mailto.woden@gmail.com) and s.chekanov

+https://github.com/kalaspuffar/JavaCNN +https://github.com/karpathy/convnetjs

Declare

            
# namespace Microsoft.VisualBasic.MachineLearning.CNN
export class ConvolutionalNN {
   # Accumulate parameters and gradients for the entire network
   BackPropagationResult: BackPropResult[];
   input: InputLayer;
   LayerNum: integer;
   output: LossLayer;
   # This is a convenience function for returning the argmax
   #  prediction, assuming the last layer of the net is a softmax
   Prediction: integer;
}

        

.NET clr type reference tree

1. use by property member BackPropagationResult: BackPropResult
2. use by property member input: InputLayer
3. use by property member output: LossLayer

---