In artificial neural networks, the hidden layer is a series of

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. The artificial neuron receives one or more inputs (representing ...

that processes the inputs received from the input layers before passing them to the output layer. An example of a neural network utilizing a hidden layer is the

feedforward neural network A feedforward neural network (FNN) is an artificial neural network wherein connections between the nodes do ''not'' form a cycle. As such, it is different from its descendant: recurrent neural networks. The feedforward neural network was the ...

. The hidden layers transform inputs from the input layer to the output layer. This is accomplished by applying what are called weights to the inputs and passing them through what is called an activation function, which calculate input based on input and weight. This allows the artificial neural network to learn

non-linear In mathematics and science, a nonlinear system is a system in which the change of the output is not proportional to the change of the input. Nonlinear problems are of interest to engineers, biologists, physicists, mathematicians, and many other ...

relationships between the input and output data. The weighted inputs can be randomly assigned. They can also be fine-tuned and calibrated through what is called

backpropagation In machine learning, backpropagation (backprop, BP) is a widely used algorithm for training feedforward artificial neural networks. Generalizations of backpropagation exist for other artificial neural networks (ANNs), and for functions gener ...

Limitations

A large number of hidden layers in terms of the

complexity Complexity characterises the behaviour of a system or model whose components interact in multiple ways and follow local rules, leading to nonlinearity, randomness, collective dynamics, hierarchy, and emergence. The term is generally used to c ...

at hand can cause what is called

overfitting mathematical modeling, overfitting is "the production of an analysis that corresponds too closely or exactly to a particular set of data, and may therefore fail to fit to additional data or predict future observations reliably". An overfitt ...

, where the network matches the data to the level where

generalization A generalization is a form of abstraction whereby common properties of specific instances are formulated as general concepts or claims. Generalizations posit the existence of a domain or set of elements, as well as one or more common character ...

is limited. With the opposite situation of the number of hidden layers being less than the complexity at hand can cause underfitting, and the system may struggle to take on the problem given to it.Effects of Hidden Layers on the Efficiency of Neural Networks Muhammad Uzair, Noreen Jamil

IEEE The Institute of Electrical and Electronics Engineers (IEEE) is a 501(c)(3) professional association for electronic engineering and electrical engineering (and associated disciplines) with its corporate office in New York City and its operati ...

23rd Multitopic Conference

References

Deep learning Machine learning