Neural networks are a foundational technology in Machine Learning (ML) and Artificial Intelligence (AI). Deep Learning (DL) is a subset of ML that is based on neural networks. Needless to say, the inspiration of using this framework in ML is the brain. A neuron is the most fundamental unit of a neural network. A neuron contains four parts:
- Dendrite: receives signals from other neurons.
- Synapse: point of connection to other neurons.
- Soma: processes the information.
- Axon: transmits the output of the neuron.
This is a very simplified account of how neurons work. In reality, there’s a massive network of interconnected neurons in our brains, which perform different functions from each other and get activated to different stimuli. Further, these neurons are also arranged in a hierarchy of layers. Information passes through each layer, which performs some function, and generates some output at the end. While this hardly explains how the brain works, it works as the basis for how neural networks work in DL.