Machines that Learn: The Neural Model

Author(s): Armin Jazi | Scientist Engineer Artist

Originally published on Towards AI.

This member-only story is on us. Upgrade to access all of Medium.

The Neural Model closely mirrors the structure of biological neural systems. Just as biological neurons connect through axons and synapses to form complex networks, neurons in machine learning models connect through weighted paths to process information. This parallel extends beyond structural similarity to functional resemblance in information processing and decision-making.

Having discussed a position on the definition of machines that learn, what follows is a comparative study of biological neurons and how they are modeled in machines that learn.

Before addressing the neural model, we need a basic understanding of biological neurons. The generic neuron has, on one end, the input end, several fine processes called Dendrites (because they resemble a tree, dendro- is a Greek root meaning “tree,” hence dendrite, dendrochronology, etc.). On the other end, axons. The cell body is often called soma (as in somatic, related to the body).

Fig.1: Biological neuron. John D. Enderle PhD, in Introduction to Biomedical Engineering (Third Edition), 2012

The axon is a long, thin process that leaves the cell body and may run for meters. The axon is the transmission line of the neuron. Axons can give rise to collateral branches, along with the… Read the full blog for free on Medium.

Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.

Published via Towards AI