Explain: Artificial Neural Networks.

·         Artificial neural networks (ANNs) are statistical models capable of modeling and processing nonlinear relationships between inputs and outputs in parallel.

·   They are characterized by containing adaptive weights along paths between neurons that can be tuned by a learning algorithm.

·   In addition to the learning algorithm itself, one must choose an appropriate cost function.

    ·   The cost function is used to learn the optimal solution to the problem being solved.

    ·   This involves determining the best values for all parameters, with neuron path adaptive weights being the primary target.

·   It’s  usually  done   through   optimization techniques   such   as   gradient   descent or stochastic gradient descent.

·  These optimization techniques basically try to make the ANN solution be as close as possible to the optimal solution, which when successful means that the ANN is able to solve the intended problem with high performance.

·  Architecturally, an artificial neural network is modeled using layers of artificial neurons, or computational units able to receive input and apply an activation function along with a threshold to determine if messages are passed along.

·   In a simple model, the first layer is the input layer, followed by one hidden layer, and lastly by an output layer. Each layer can contain one or more neurons.

·  Models can become increasingly complex, and with increased abstraction and problem solving capabilities by increasing the number of hidden layers, the number of neurons in any given layer, and/or the number of paths between neurons.

  

  ·  An increased chance of overfitting can also occur with increased model complexity.

   ·  Model architecture and tuning are therefore major components of ANN techniques, in addition to the actual learning algorithms themselves.

  

  ·  All of these characteristics of an ANN can have significant impact on the performance of the model.

  ·  While ANNs are extremely powerful, they can also be very complex and are considered black box algorithms, which means that their inner-workings are very difficult to understand and explain.