- TensorFlow with Keras
- Training and testing based on simulation for: CERN 18
Dense layer:
![](/~rdzhigad/data/ml/layers/dense.png)
Dense neuron math:
![](/~rdzhigad/data/ml/layers/dense_neuron.png)
"Gauss neuron":
![](/~rdzhigad/data/ml/layers/gauss_neuron.png)
Sum of "Gauss neurons" to represent data (time specter of typical channel @ CERN18):
![](/~rdzhigad/data/ml/layers/gauss_3.png)
Use sum of gaussian and dense neurons:
![](/~rdzhigad/data/ml/layers/sum.png)