Exploring Neural Networks in C# .NET
- Logistic Sigmoid
- Hyperbolic Tangent
- Heaviside Step
- Softmax
- Back-propagation
- Genetic Algorithm
- Particle Swarm Optimization
- Number of Hidden Neurons
- Momentum
- Learning Rate
- Weight Decay
- Feed-forward
- Activation Functions
- Data Encoding
- Error
- Training
- Free Parameters
- Over-fitting
- Input Neurons (Determined by the amount of inputs)
- Hidden Neurons (The unsolved mystery of neural networks, try different amounts until wanted result)
- Output Neurons (How many choices could the final answer be? Yes or No [2 Output Neurons] Yes, No, Maybe? [3 Output Neurons])
- Bias (Normally is a dummy input usually set at '1.0')
It is easy to "over-fit" a neural network. You do not wan't 100& during training. However you do wan't 100% Accuracy on the Test Set.