Step 1: Getting To Know AI

What is AI?
Artificial Intelligence (AI) means teaching computers to think and learn like humans. Instead of just following exact instructions, AI can make decisions, recognize patterns, and improve over time. It powers things like voice assistants, recommendation systems, and self-driving cars.

What will this tutorial cover?
In this tutorial, you'll learn how to build a basic AI from scratch. We'll start simple and build up step-by-step:

• Step 1: Understand what AI really is and how it works.
• Step 2: Create a basic neuron, which is the building block of AI, that can convert inputs to outputs.
• Step 3: Connect multiple neurons to make your AI smarter and able to solve more complex problems.

By the end, you'll have a clear understanding of how AI works at its core and how to create your own simple AI models!

AI Assistant - Step 2: Basic Nueron

A simple nueron works by taking in a string of numbers such as ASCII or other variables, then applying a weight and balance to the numbers to get an output. Tuning these weights and balances allows for the AI to develop the idea of what you want the input to mean. For this tutorial we will be using Numpy with Python to make the basic neuron. Lets get started!

1. First we will import Numpy.

                    import numpy as np
                

2. Next we will define our neuron class. We will add our init function which will define our weights, biases, and input values.

                    import numpy as np
                    class Neuron:
                        def __init__(self, bias, weights):
                            self.bias = bias
                            self.weight = weights
                            self.inputs = None
                

3. Next we will add our activation function. This is the function that will take in our inputs and apply the weights and biases to get an output.

                    import numpy as np
                    class Neuron:
                        def __init__(self, bias, weights):
                            self.bias = bias
                            self.weight = weights
                            self.inputs = None

                    def activation_function(self, inputs):
                        self.inputs = inputs
                        output = np.dot(self.inputs, self.weight) + self.bias
                        return output
                

4. Now we will implement a ReLu function which will allow us to get a positive output from our neuron.

                  import numpy as np
                  class Neuron:
                      def __init__(self, bias, weights):
                          self.bias = bias
                          self.weight = weights
                          self.inputs = None
                      def activation_function(self, inputs):
                          self.inputs = inputs
                          output = np.dot(self.inputs, self.weight) + self.bias
                          return self.relu(output)
                      def relu(self, x):
                          return 1 / (1 + np.exp(-x))
                

5. Finally we will create an instance of our neuron and test it with some inputs.

                  import numpy as np
                  class Neuron:
                      def __init__(self, bias, weights):
                          self.bias = bias
                          self.weight = weights
                          self.inputs = None
                      def activation_function(self, inputs):
                          self.inputs = inputs
                          output = np.dot(self.inputs, self.weight) + self.bias
                          return self.relu(output)
                      def relu(self, x):
                          return 1 / (1 + np.exp(-x))
                      
                  if __name__ == "__main__":
                      bias = 0.5
                      weights = np.array([0.2, 0.8, -0.5])
                      neuron = Neuron(bias, weights)
                      
                      inputs = np.array([1.0, 0.5, -1.0])
                      output = neuron.activation_function(inputs)
                      
                      print("Neuron output:", output)
                

And that's it! You have created a basic neuron that can take in inputs, apply weights and biases, and return an output. You can now use this neuron to build more complex neural networks.

AI Assistant - Step 3: Multiple Neurons

Template stuff to be implemented later