Artificial neurons

Artificial neurons are based on the structure of the biological neuron and use mathematical functions with real values to simulate their behavior. Such artificial neurons are called perceptrons, a concept that was developed in the 50s and 60s by the scientist Frank Rosenblatt. Taking this mathematical analogy into account, we can talk about the biological neurons as follows:

  • Dendrites: The number of inputs the neuron accepts. It can also be seen as the number of dimensions, D, of the input data.
  • Synapses: weights associated with the dendrites. These are the values that change during the training phase. At the end of the ...

Get Hands-On Neural Networks with TensorFlow 2.0 now with the O’Reilly learning platform.

O’Reilly members experience live online training, plus books, videos, and digital content from nearly 200 publishers.