#pragma once

template<class LAYER1_TYPE>
class NeuralNetOneLayer
{
	LAYER1_TYPE m_layer1;
	double m_lfLearningRate;
public:
	NeuralNetOneLayer(void);
	~NeuralNetOneLayer(void);

	void SetLearnRate(double lfLearnRate) { m_lfLearningRate = lfLearnRate; }

	bool Train(const double * const arrLfInputs, const double * const arrLfIntendedOutputs, double * arrLfScratch)
	{
		m_layer1.Eval(arrLfInputs);
		const double * arrLfActualOutputs = m_layer1.GetOutputVec();
		for(int i = 0; i < m_layer1.GetNumOutputs(); ++i)
		{
			arrLfScratch[i] = arrLfActualOutputs[i] - arrLfIntendedOutputs[i];
		}
		m_layer1.CalcErrorPartials(arrLfScratch);
		m_layer1.DoBackpropStep(m_lfLearningRate, arrLfInputs);
		return true;
	}

	const double * const Eval(const double * const arrLfInputs)
	{
		m_layer1.Eval(arrLfInputs);
		return m_layer1.GetOutputVec();
	}

	//bool Eval(const double * const arrLfInputs);

	//bool CalcErrorPartials(const double * const arrLfDErrDInputPrev);	// gets dErr/dAct and dErr/dInput

	//const double * const GetOutputVec() const { return m_arrLfOutputs; }

	//const double * const GetDErrDAct() const { return m_arrLfDerrorDactivation; } // gets sigmas 
};


template<class LAYER1_TYPE>
NeuralNetOneLayer<LAYER1_TYPE>::NeuralNetOneLayer(void):m_lfLearningRate(0.1)
{
}

template<class LAYER1_TYPE>
NeuralNetOneLayer<LAYER1_TYPE>::~NeuralNetOneLayer(void)
{
}