日撸代码300行：第73天（固定激活函数的BP神经网络，训练与测试过程理解）

       进一步梳理理解了一下正向和反向传播。Forward 是利用当前网络对一条数据进行预测的过程，BackPropagation 是根据误差进行网络权重调节的过程。

       完整的代码在72天，这里只粘贴Forward和BackPropagation两个方法。

	/**
	 * ***********************************************************
	 * Forward prediction.
	 * 
	 * @param paraInput   The input data of one instance.
	 * @return   The data at the output end.
	 * ***********************************************************
	 */
	public double[] forward(double[] paraInput) {
		// Initialize the input layer.
		for (int i = 0; i < layerNodeValues[0].length; i++) {
			layerNodeValues[0][i] = paraInput[i];
		}//of for i
		
		// Calculate the node values of each layer.
		double z;
		for (int l = 1; l < numLayers; l++) {
			for (int j = 0; j < layerNodeValues[l].length; j++) {
				// Initialize according to the offset, which is always +1
				//(l-1)层的第（该层节点个数）个节点（偏置）指向下一层[j]节点的值；z等于该边的权值。
				z = edgeWeights[l - 1][layerNodeValues[l - 1].length][j];//数组edgeWeights的第三维表示下一层节点的索引
				
				// Weighted sum on all edges for this node.
				for (int i = 0; i < layerNodeValues[l - 1].length; i++) {
					z += edgeWeights[l - 1][i][j] * layerNodeValues[l - 1][i];
				}//of for i (循环上一层的节点)
				
				// Sigmoid activation.
				// This line should be changed for other activation functions.
				layerNodeValues[l][j] = 1 / (1 + Math.exp(-z));
			}//of for j（循环要计算的节点的当前层节点）
		}//of for l（循环神经网络的层）
		return layerNodeValues[numLayers - 1];
	}//of forward

	/**
	 * ******************************************************
	 * Back propagation and change the edge weights.
	 * 
	 * @param paraTarget  For 3-class data, it is [0, 0, 1], [0, 1, 0] or [1, 0, 0].
	 * ******************************************************
	 */
	public void backPropagation(double[] paraTarget) {
		// Step 1. Initialize the output layer error.
		int l = numLayers - 1;   //第l层，即输出层
		for (int j = 0; j < layerNodeErrors[l].length; j++) {
			layerNodeErrors[l][j] = layerNodeValues[l][j] * (1 - layerNodeValues[l][j]) 
					* (paraTarget[j] - layerNodeValues[l][j]); 
			//套用输出层误差公式。上游传过来的值（即误差）乘以激活函数的倒数，这里sigmod的倒数为y(1-y)。）
		}//of for j
		
		// Step 2. Back-propagation even for l == 0
		while (l > 0) {
			l--;
			// Layer l, for each node.
			for (int j = 0; j < layerNumNodes[l]; j++) {
				double z = 0.0;
				// For each node of the next layer.
				for (int i = 0; i < layerNumNodes[l + 1]; i++) {
					if (l > 0) {
						z += layerNodeErrors[l + 1][i] * edgeWeights[l][j][i];
						//(l+1)层的第i个节点，乘以l层第j个节点指向下一层第i个节点的边的权重。
					}//of if
					
					// Weight adjusting.
					edgeWeightsDelta[l][j][i] = mobp * edgeWeightsDelta[l][j][i] + 
							learningRate * layerNodeErrors[l + 1][i] * layerNodeValues[l][j];
					edgeWeights[l][j][i] += edgeWeightsDelta[l][j][i];
					if (j == layerNumNodes[l] - 1) {
						// Weight adjusting for the offset part.
                        //偏置节点没包含在每层节点个数里，所以要加1.
						edgeWeightsDelta[l][j + 1][i] = mobp * edgeWeightsDelta[l][j + 1][i]
								+ learningRate * layerNodeErrors[l + 1][i];
						edgeWeights[l][j + 1][i] += edgeWeightsDelta[l][j + 1][i];
					}//of if
				}//of for i
				
				// Record the error according to the differential of Sigmoid.
				// This line should be changed for other activation functions.
				layerNodeErrors[l][j] = layerNodeValues[l][j] * (1 - layerNodeValues[l][j]) * z;
			}//of for j
		}//of while
	}//of backPropagation

edgeWeights与edgeWeightsDelta两个三维数组，再声明的时候第二维大小就是“layerNumNodes[l] + 1”。所以，偏置节点没包含在layerNumNodes[l] 里。因此在偏置调整时第二维的下标是j+1。