C++ Feed-Forward Neural Network

After a few days of reading articles, watching videos and bugging my head around neural networks, I have finally managed to understand it just so I could write my own feed-forward implementation in C++.

It does have some scratch back-propagation functionality, but it needs further work (not done yet).

Here's my code, I would like you to point out any bad practices, tips, you know :)

main.cpp

#include "neural-net.hpp"

int main(int argc, char **argv)
{
    srand(time(NULL));

    /* Topology: x-y-z-...-n where a is the input layer and n is the output layer */
    /* In this case: 1 input layer with 2 neurons, 1 hidden layer with 3 neurons and an output layer with 1 neuron */
    std::vector vecTopology = { 2, 3, 1 };
    NeuralNet net(vecTopology, false);

    /* Set the input values and expected results for back-propagation (not finished!) */
    std::vector vecInputs(vecTopology[0], 1);
    std::vector vecExpected(3, 0);

    std::cout << "Inputs: ";
    for (int i = 0; i < vecInputs.size(); i++) {
        std::cout << vecInputs[i] << " ";
    }
    std::cout << "\n\n";

    net.feedForward(vecInputs);
    net.backPropagate(vecExpected);

    net.status();
}

neural-net.hpp

#ifndef NEURALNET_HPP
#define NEURALNET_HPP

#include "Neuron.hpp"

class NeuralNet
{
public:
    NeuralNet(const std::vector &, bool = false);
    void status();
    void setWeight(unsigned, unsigned, unsigned, double);
    void feedForward(const std::vector &);
    void backPropagate(const std::vector &);
    std::vector getOutput();

private:
    std::vector vecLayers;
    bool useBias;
};

#endif

neural-net.cpp

```
#include "neural-net.hpp"

NeuralNet::NeuralNet(const std::vector &vecTopology, bool useBias)
{
this->useBias = useBias;

/ 'Build' the network based on the topology /
for (unsigned l = 0; l vecLayers.push_back(Layer());

unsigned nAxons = (l == vecTopology.size() - 1) ? 0 : vecTopology[l + 1];
for (unsigned n = 0; n useBias) ?

So here my 2 cents.

-
I think all the this-> makes it hard to read. Also this is only necessary when there might be name conflicts, which are not there.

-
The randomWeight function should be a member of the Axon. Therefore you can initialize the axon vector simply by

vecAxons = std::vector(nAxon);

-
Even if you do not go for that, you should alwas reserve memory if you know the size of an array beforehand. Therewith you avoid reallocations.

vecAxons.reserve(nAxons);

-
As you use C++ you should utilize the random library rather than rand. When you want to develop serious models rand is not your friend.

-
You should try to use range based loops, which improve readability. For example

/* Calculate the sum of inputs * weights going to the neuron and pass it through the transfer function... */
for (unsigned n = 0; n outputSum += vecPreviousLayer[n].output * vecPreviousLayer[n].vecAxons[this->index].weight;
}

can be written as

/* Calculate the sum of inputs * weights going to the neuron and pass it through the transfer function... */
for (const Neuron& sourceNeuron : vecPreviousLayer) {
    outputSum += sourceNeuron.output * sourceNeuron.vecAxons[index].weight;
}

-
Whenever possible avoid pow() of natural numbers. I know it is tedious, but pow is just incredibly slow, especially stuff like pow(x,2) vs x*x

StackExchange Code Review Q#158670, answer score: 4