paramGradientCheck
====================================

.. js:function:: NeuralNetwork.paramGradientCheck(name, params, delta_params, batch_Y, exp_work, cost, batch_idx, layer_idx, last_delta_y_dt)

    パラメータごとの勾配の計算のチェック

    :param string  name: パラメータ名
    :param float[] params: パラメータの配列
    :param float[] delta_params: パラメータのδの配列 
    :param float[] batch_Y: 正解の出力
    :param float[] exp_work: 作業用データ
    :param double  cost: コスト
    :param int     batch_idx: ミニバッチ内のインデックス
    :param int     layer_idx: レイヤーのインデックス
    :param float[] last_delta_y_dt: 最後のレイヤーのδy

ソース
^^^^^^

.. code-block:: js

            paramGradientCheck(name, params, delta_params, batch_Y, exp_work, cost, batch_idx, layer_idx, last_delta_y_dt){
                Assert(params.length == delta_params.length);
                // delta bias
                var idx_list = random.RandomSampling(params.length, 3);
    
                for(let i of idx_list){
                    var b = params[i];
                    var db = delta_params[i];
                    var eps = b * 0.01;
    
                    params[i] = b - eps;
                    var cost1 = this.forwardCost(batch_Y, exp_work, batch_idx, layer_idx, last_delta_y_dt);
    
                    params[i] = b + eps;
                    var cost2 = this.forwardCost(batch_Y, exp_work, batch_idx, layer_idx, last_delta_y_dt);
    
                    var diff = db * 2 * eps - (cost2 - cost1);
                    console.log("delta-%s : %f dC:%f eps:%f cost:%f,%f,%f", name, diff, db, eps, cost1, cost - cost1, cost2 - cost);
    
                    params[i] = b;
                }
            }