Neural Networks

Neural networks are an algorithm used to solve problems of a complex nature that are not easily coded, and they are a mainstay of machine learning as it is understood today.

They are called “neural networks” because the behavior of their component nodes vaguely resembles that of biological neurons. A neuron receives incoming signals from several other neurons via synaptic connections and integrates them. If the resulting activation exceeds a certain threshold it generates an Action Potential that propagates through its axon to one or more neurons.

We can consider a neural network as a black box, with inputs, intermediate layers where “things happen,” and outputs that constitute the final result.

The neural network is composed of “units” called neurons, arranged in successive layers. each neuron is typically connected to all the neurons in the next layer by weighted connections. a connection is nothing more than a numerical value (the “weight” precisely), which is multiplied by the value of the connected neuron.

Each neuron sums the weighted values of all the neurons connected to it and adds a bias value. an “activation function” is applied to this result, which does nothing more than mathematically transform the value before passing it to the next layer.

In this way, the input values are propagated through the network to the output neurons.

In conclusion, the ultimate goal is to adjust weights and biases so as to arrive at the desired result. Several techniques can be used to achieve this goal, one of which is machine learning.

Are you interested in our services? Request information!