diff --git a/README.md b/README.md
index 5eb62aa..1cf69ac 100644
--- a/README.md
+++ b/README.md
@@ -55,13 +55,10 @@ PINN is a novel approach that involves neural networks to solve supervised learn
#### Problem definition
First step is formalization of the problem in the PINA framework. We take as example here a simple Poisson problem, but PINA is already able to deal with **multi-dimensional**, **parametric**, **time-dependent** problems.
Consider:
-$$
-\begin{cases}
-\nabla u = \sin(\pi x) \sin(\pi y) & \quad\text{in}\, D,\\
-u = 0 &\quad\text{on}\, \Gamma_1 \cup\Gamma_2 \cup\Gamma_3 \cup\Gamma_4, \\
-\end{cases}
-$$
-where $D= [0, 1]^2$ is a square domain, $\Gamma_1 \cup\Gamma_2 \cup\Gamma_3 \cup\Gamma_4$ are the boundaries and $u$ the unknown field. The translation in PINA code becomes a new class containing all the information about the domain, about the `conditions` and nothing more:
+
+ 
+
+where *D* is a square domain, *Gamma*s are the boundaries and *u* the unknown field. The translation in PINA code becomes a new class containing all the information about the domain, about the `conditions` and nothing more:
```python
class Poisson(SpatialProblem):
spatial_variables = ['x', 'y']
@@ -104,6 +101,9 @@ plotter = Plotter()
plotter.plot(pinn)
```
After the training we can infer our model, save it or just plot the PINN approximation.
+
+ 
+
## Dependencies and installation
diff --git a/readme/poisson_plot.png b/readme/poisson_plot.png
new file mode 100644
index 0000000..cb3d6d8
Binary files /dev/null and b/readme/poisson_plot.png differ
diff --git a/readme/poisson_problem.png b/readme/poisson_problem.png
new file mode 100644
index 0000000..5931275
Binary files /dev/null and b/readme/poisson_problem.png differ