A single neuron. More...
Public Attributes | |
| long | count |
| How often the value of this neuron has been evaluated. | |
| double | x |
| Neuron value before application of activation function. | |
| double | value |
| Neuron value. | |
| double | dfdx |
| Derivative of activation function with respect to its argument \( \frac{\partial f_a}{\partial x} \). | |
| double | d2fdx2 |
| Second derivative of activation function with respect to its argument \( \frac{\partial^2 f_a}{\partial x^2} \). | |
| double | bias |
| Bias value assigned to this neuron (if this is neuron \( y_i^n \) this bias value is \( b_{i}^{n} \)). | |
| double | dxdG |
| Derivative of neuron value before application of activation function with respect to input layer neurons \( \frac{\partial x}{\partial G} \). | |
| double | min |
| Minimum neuron value over data set (neuron statistics). | |
| double | max |
| Maximum neuron value over data set (neuron statistics). | |
| double | sum |
| Sum of neuron values over data set (neuron statistics). | |
| double | sum2 |
| Sum of squared neuron values over data set (neuron statistics). | |
| double * | weights |
| NN weights assigned to neuron. | |
Detailed Description
A single neuron.
Definition at line 357 of file NeuralNetwork.h.
Member Data Documentation
◆ count
| long nnp::NeuralNetwork::Neuron::count |
How often the value of this neuron has been evaluated.
Definition at line 360 of file NeuralNetwork.h.
Referenced by nnp::NeuralNetwork::allocateLayer(), nnp::NeuralNetwork::propagateLayer(), and nnp::NeuralNetwork::setInput().
◆ x
| double nnp::NeuralNetwork::Neuron::x |
Neuron value before application of activation function.
Definition at line 362 of file NeuralNetwork.h.
Referenced by nnp::NeuralNetwork::allocateLayer(), and nnp::NeuralNetwork::propagateLayer().
◆ value
| double nnp::NeuralNetwork::Neuron::value |
Neuron value.
Definition at line 364 of file NeuralNetwork.h.
Referenced by nnp::NeuralNetwork::allocateLayer(), nnp::NeuralNetwork::propagateLayer(), and nnp::NeuralNetwork::setInput().
◆ dfdx
| double nnp::NeuralNetwork::Neuron::dfdx |
Derivative of activation function with respect to its argument \( \frac{\partial f_a}{\partial x} \).
Definition at line 367 of file NeuralNetwork.h.
Referenced by nnp::NeuralNetwork::allocateLayer(), and nnp::NeuralNetwork::propagateLayer().
◆ d2fdx2
| double nnp::NeuralNetwork::Neuron::d2fdx2 |
Second derivative of activation function with respect to its argument \( \frac{\partial^2 f_a}{\partial x^2} \).
Definition at line 370 of file NeuralNetwork.h.
Referenced by nnp::NeuralNetwork::allocateLayer(), and nnp::NeuralNetwork::propagateLayer().
◆ bias
| double nnp::NeuralNetwork::Neuron::bias |
Bias value assigned to this neuron (if this is neuron \( y_i^n \) this bias value is \( b_{i}^{n} \)).
Definition at line 373 of file NeuralNetwork.h.
Referenced by nnp::NeuralNetwork::allocateLayer(), and nnp::NeuralNetwork::propagateLayer().
◆ dxdG
| double nnp::NeuralNetwork::Neuron::dxdG |
Derivative of neuron value before application of activation function with respect to input layer neurons \( \frac{\partial x}{\partial G} \).
Definition at line 377 of file NeuralNetwork.h.
Referenced by nnp::NeuralNetwork::allocateLayer().
◆ min
| double nnp::NeuralNetwork::Neuron::min |
Minimum neuron value over data set (neuron statistics).
Definition at line 379 of file NeuralNetwork.h.
Referenced by nnp::NeuralNetwork::allocateLayer(), nnp::NeuralNetwork::propagateLayer(), and nnp::NeuralNetwork::setInput().
◆ max
| double nnp::NeuralNetwork::Neuron::max |
Maximum neuron value over data set (neuron statistics).
Definition at line 381 of file NeuralNetwork.h.
Referenced by nnp::NeuralNetwork::allocateLayer(), nnp::NeuralNetwork::propagateLayer(), and nnp::NeuralNetwork::setInput().
◆ sum
| double nnp::NeuralNetwork::Neuron::sum |
Sum of neuron values over data set (neuron statistics).
Definition at line 383 of file NeuralNetwork.h.
Referenced by nnp::NeuralNetwork::allocateLayer(), nnp::NeuralNetwork::propagateLayer(), and nnp::NeuralNetwork::setInput().
◆ sum2
| double nnp::NeuralNetwork::Neuron::sum2 |
Sum of squared neuron values over data set (neuron statistics).
Definition at line 385 of file NeuralNetwork.h.
Referenced by nnp::NeuralNetwork::allocateLayer(), nnp::NeuralNetwork::propagateLayer(), and nnp::NeuralNetwork::setInput().
◆ weights
| double* nnp::NeuralNetwork::Neuron::weights |
NN weights assigned to neuron.
If this is neuron \(i\) in layer \(n\), \( y_i^n \), these weights are \( \left\{ a_{ji}^{n-1, n} \right\}_{j=1,\ldots,N_n} \).
Definition at line 390 of file NeuralNetwork.h.
Referenced by nnp::NeuralNetwork::allocateLayer(), and nnp::NeuralNetwork::propagateLayer().
The documentation for this struct was generated from the following file:
- /home/runner/work/n2p2/n2p2/src/libnnp/NeuralNetwork.h
