We borrow inspirations from the structure of a human brain and designed the neural networks we know today. The idea of neurons in neural networks has similar characteristics to our biological neurons in our brain.
A human brain contains about 86 billion neurons, each individually linked to other neurons. Biological neurons are cells, when it gets activated, it generates a spike and sends information to other neurons.
Like our brain, a neural network consists of many interconnected neurons. When a neuron receives inputs from other neurons, it gets activated, and it sends information to other neurons.
An artificial neuron is a mathematical function conceived as a model of biological neurons [wikipedia]
The brain’s plasticity allows us to learn and improve our skills. Every time we learn new things, we are creating and strengthening the connections between neurons. That’s why when we practise a task, we become better at it.
Neural networks learn when we feed it with lots of data. Each connection of our neural network is associated with a weight that dictates the importance between neurons. During the training process, the weights are tuned accordingly to strengthen or weaken the connection.
Because we have seen enough cats, we can be confident that this is a cat. Likewise, if we provide our neural networks with enough cats images, it will start to recognise cats.