Add multilayer perceptron.

README.md

@@ -76,8 +76,8 @@ _Usage examples: as a substitute of all other algorithms in general, image recog
 
 #### 🤖 Multilayer Perceptron (MLP)
 
-- 📗 [Math | Multilayer Perceptron](homemade/neural_network)
-- ⚙️ [Code | Multilayer Perceptron](https://github.com/trekhleb/homemade-machine-learning/blob/master/homemade/neural_network/multilayer_perceptron.py)
+- 📗 [Math | Multilayer Perceptron](homemade/neural_network) - theory and links for further readings
+- ⚙️ [Code | Multilayer Perceptron](https://github.com/trekhleb/homemade-machine-learning/blob/master/homemade/neural_network/multilayer_perceptron.py) - implementation example
 - ▶️ [Demo | Multilayer Perceptron](https://nbviewer.jupyter.org/github/trekhleb/homemade-machine-learning/blob/master/notebooks/neural_network/multilayer_perceptron_demo.ipynb) - recognize handwritten digits from `28x28` pixel images.
 
 ## Machine Learning Map

homemade/neural_network/README.md

@@ -1,5 +1,11 @@
 # Neural Network
 
+## Jupyter Demos
+
+▶️ [Demo | Multilayer Perceptron](https://nbviewer.jupyter.org/github/trekhleb/homemade-machine-learning/blob/master/notebooks/neural_network/multilayer_perceptron_demo.ipynb) - recognize handwritten digits from `28x28` pixel images.
+
+## Definition
+
 **Artificial neural networks** (ANN) or connectionist systems are computing systems vaguely inspired by the biological neural networks that constitute animal brains. The neural network itself isn't an algorithm, but rather a framework for many different machine learning algorithms to work together and process complex data inputs. Such systems "learn" to perform tasks by considering examples, generally without being programmed with any task-specific rules.
 
 ![Neuron](https://upload.wikimedia.org/wikipedia/commons/1/10/Blausen_0657_MultipolarNeuron.png)