Member-only story
The application of an Artificial Neuron on the Iris Dataset in Python
Predicting flowers’ variety with a single layer neural network without a deep learning library
Introduction
Artificial Neural Networks (ANNs) are extremely powerful. Recent developments brought scientists to create NNs with more connections than a human brain. To give you an idea, it is estimated that an average brain has 86 billion neurons and 100 billion synapses. On the other hand, the largest NN in 2022, “Megatron-Turing NGL 530B (MT-NGL)”, a monolithic transformer language model, has 530 billion parameters. Still, the human brain is proficient in more than one field, MT-NGL is only specialized in language processing.
How did we come this far?
Artificial Neurons
“An artificial neuron is a mathematical function conceived as a model of biological neurons, a neural network. Artificial neurons are elementary units in an artificial neural network[1].”
It was 1943 and the publishing of McCullock and Pitts of the first concept of a simplified brain cell called the McCulloch-Pitts (MCP) neuron, represented a milestone towards the development of ANNs. The two neuroscientists were trying to understand how…
