1. Introduction

In this tutorial, we'll be diving into the world of artificial intelligence (AI) by building a basic artificial neural network. The goal of this tutorial is to give you an understanding of how neural networks function and how to implement them in your AI applications.

By the end of this tutorial, you'll have learned:
- What exactly a neural network is
- How to design the architecture of a neural network
- How to feed data into your network
- How to interpret the output of your network

As for prerequisites, having a basic understanding of Python programming and some familiarity with machine learning concepts will be helpful.

2. Step-by-Step Guide

Neural networks are inspired by the human brain and consist of interconnected layers of nodes or "neurons". These networks take in input data, process it through multiple layers of neurons, and provide an output.

The process of building a neural network typically involves the following steps:
- Designing the Network Architecture: This involves deciding the number of layers and the number of nodes in each layer.
- Initializing Parameters: This involves assigning initial weights and biases to your network.
- Loop:
- Forward Propagation: In this step, you calculate the output for given input.
- Cost Computation: Here, you measure how well your network is performing.
- Backward Propagation: In this step, you update your weights and biases to improve your network.
- Prediction: Finally, you use your trained network to make predictions on unseen data.

3. Code Examples

We'll use the Python library Keras to build a simple neural network. Keras is a high-level neural networks API, built on top of TensorFlow.

Example 1: Designing the Network Architecture

from keras.models import Sequential
from keras.layers import Dense

# create a sequential model
model = Sequential()

# add the first hidden layer with 10 nodes, input_dim specifies the number of input variables
model.add(Dense(10, input_dim=8, activation='relu'))

# add the second hidden layer with 10 nodes
model.add(Dense(10, activation='relu'))

# add an output layer with 1 node (since we're dealing with a binary classification problem)
model.add(Dense(1, activation='sigmoid'))

Example 2: Compiling and Training the Model

# compile the model
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])

# train the model
model.fit(X, Y, epochs=150, batch_size=10)

Example 3: Making Predictions

# make class predictions with the model
predictions = model.predict_classes(X)

# summarize the first 5 cases
for i in range(5):
    print('%s => %d (expected %d)' % (X[i].tolist(), predictions[i], Y[i]))

4. Summary

In this tutorial, we have learned the basics of building a neural network for AI applications. We've seen how to design the architecture of the network, feed data into the network, and interpret the output. The next steps would be to explore different types of neural networks and understand when to use which type.

Here are some additional resources:
- Deep Learning Book by Ian Goodfellow, Yoshua Bengio, and Aaron Courville
- Keras Documentation

5. Practice Exercises

Exercise 1: Try modifying the architecture of the network. How does adding more layers or nodes affect the performance?

Exercise 2: Experiment with different types of activation functions (like 'tanh', 'softmax'). How does the choice of activation function impact the results?

Exercise 3: Try implementing a neural network for a multiclass classification problem.

Remember, the key to mastering neural networks is practice and experimentation. Don't be afraid to tweak parameters and try different architectures!