/**++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
 *
 *                                              PANIC
 *                              Portable Algorithms and Numerics In C++
 *
 *                       Scientific computing from scratch, with feeling.
 *
 * Copyright (c) 2026 Michelle Bausager
 *
 * This file is part of PANIC.
 *
 * PANIC is free software licensed under the GNU General Public License v3.0 or later.
 * You may redistribute and/or modify it under the terms of the GPL.
 *
 * PANIC is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY;
 * without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
 * See the LICENSE file for the full license text.
 *
 * SPDX-License-Identifier: GPL-3.0-or-later
 *
 *++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
 *
 * Project Name:      PANIC
 * Module Name:       neural_network
 * File Name:         layer_dense.hpp
 * Revision:          0.1.0
 * Date:              23-06-2026
 * Author:            Michelle Bausager
 *
 * Description:
 * Defines the dense layers used in neural network
 *
 *++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++*/
#pragma once

//---------------------------------------------------------------------------------------------------------------------------
// INCLUDE DESCRIPTION
//---------------------------------------------------------------------------------------------------------------------------
#include <config/types.hpp> // panic::uint_t, panic::int_t, and panic::real_t
#include <neural_network/layer/layer.hpp> // for base layer struct
#include <tensor/vector.hpp>
#include <tensor/matrix.hpp>

//---------------------------------------------------------------------------------------------------------------------------
// DEFINE DESCRIPTION
//---------------------------------------------------------------------------------------------------------------------------

//---------------------------------------------------------------------------------------------------------------------------
// TYPE DESCRIPTION
//---------------------------------------------------------------------------------------------------------------------------

//--------------------------------------------------------------------------------------------------------------------------
// Function Name : panic::neural_network::layer_dense
//
// Description:
//   Dense/fully-connected neural network layer.
//
// Inputs:
//   Samples x input size 				const panic::tensor::real_matrix&
//
//   Weight shape:
//     input_size x neuron_count
//
//   Bias shape:
//     1 x neuron_count
//
//   Output shape:
//     samples x neuron_count			panic::tensor::real_matrix
//
// Notes:
//   forward(input) calculates:
//
//     outputs = inputs * weights + biases
//--------------------------------------------------------------------------------------------------------------------------
namespace panic{
	namespace neural_network{

struct layer_dense : public layer{

	panic::tensor::real_matrix weights;
	panic::tensor::real_vector biases;
	panic::tensor::real_matrix outputs;

	// Empthy contructor
	layer_dense();

	// Contructor with layer size
	layer_dense(panic::types::uint_t input_size, panic::types::uint_t neurons);

	// Decontructor  (All internal variables has decontructors, so we can just use default)
	~layer_dense() = default;

	// Forward function for forward pass
	bool forward(const panic::tensor::real_matrix& inputs);

	// Backward pass
	bool backward(const panic::tensor::real_matrix& dinpus);
};

	} // namespace tensor
} // namespace panic

//---------------------------------------------------------------------------------------------------------------------------
// VARIABLE DESCRIPTION
//---------------------------------------------------------------------------------------------------------------------------

//---------------------------------------------------------------------------------------------------------------------------
// FUNCTION PROTOTYPE
//---------------------------------------------------------------------------------------------------------------------------