An Artificial Neural Network (ANN) is a type of computer system designed to work similarly to how our brains process information. Just like our brains have neurons (nerve cells) that are connected and help us think and learn, ANNs use artificial neurons to process data and solve problems.

Here’s a simple breakdown:

1. Neurons: In an ANN, the basic units are called neurons (also known as nodes). Each neuron receives input, processes it, and passes it along to other neurons.

2. Layers: Neurons are organized into layers. The first layer takes in the raw data, like numbers or images, and the final layer produces the result. In between, there can be several “hidden layers” that help in understanding the data better.

3. Connections: The neurons are connected to each other, and each connection has a weight. The weight determines how much influence one neuron has on another. The ANN adjusts these weights during learning to get better at solving tasks.

4. Learning: ANNs learn by being shown examples. For example, if you want an ANN to recognize pictures of cats, you show it lots of pictures labeled as “cat” or “not cat.” Over time, it learns to identify patterns that help it recognize cats on its own.

5. Training: The network adjusts itself by comparing its output to the correct answer and making small changes (called training) to improve over time.

Simple Example:¶

Imagine you’re teaching a child to recognize fruits. You show them apples and bananas and tell them the names. Over time, the child learns to tell the difference between an apple and a banana by recognizing certain patterns like shape and color. ANNs do something similar but with numbers and data, instead of fruits.

Key Points:¶

• ANNs are good at recognizing patterns, like identifying objects in pictures or translating languages.
• They are “trained” by giving them lots of examples so they can improve.
• They can handle complex tasks by learning from data without needing to be programmed for every specific task.

In summary, an ANN is like a simplified digital brain that learns from examples and helps computers perform tasks that usually require human intelligence, such as recognizing images, speech, or patterns in data.

Let’s Review with Diagrams¶

Artificial Neural Network Structure¶

An Artificial Neural Network (ANN) is modeled on the brain where neurons are connected in complex patterns to process data from the senses, establish memories and control the body. An Artificial Neural Network (ANN) is a system based on the operation of biological neural networks or it is also defined as an emulation of biological neural system.

What we will learn in this session ?¶

• The Neuron
• The Activation Function
• How do Neural Network works ?
• How do Neural Networks Learn ?
• Gradient Descent
• Stochastic Gradient Descent
• Backpropagation

1 : THE NEURON¶

A neuron (also called neurone or nerve cell) is a cell that carries electrical impulses. Neurons are the basic units of the nervous system. Every neuron is made of a cell body (also called a soma), dendrites and an axon. Dendrites and axons are nerve fibres.

• Dendrites : are the receivers of the signal to the neuron
• Axon : is the transmitter of the signal to the neuron

How it works in Machine Learning¶

In this image you can see Green Neuron receive signal from the Yellow Neuron through synapse

2. Activation Function