Supervised Learning - Classification Week 9 Challenge

1.

A neural network is a system composed of many simple processing elements operating in parallel which can acquire, store and utilise experiential knowledge.

The processing ability of the network is stored in the inter unit connection strengths ,or weights and function of processing element.

2.

A sub-field of machine learning that is based on learning several levels of representations, corresponding to a hierarchy of features or factors or concepts, where higher-level concepts are defined from lower-level ones, and the same lower-level concepts can help to drive many higher-level concepts.

3.

An activation function is a function that is added into an artificial neural network in order to help the network learn complex matters in data. When comparing with a neuron based model that is in our brains, the activation function is at the end deciding what is to be fired to the next neuron.

4.

The different type of activation functions are:-

- identity function

- linear function

- Tanh function

- ReLU function

- Softmax function

- Binary step function

5.

Back error is short for back error propagation. The word propagation is synonymous to broadcast, dissemination promulgation, circulation; and if we take the whole name it means disseminate the error of a result back to the input in order to rectify the result. Back propagation (BP) method is the Generalized Delta Rule and it belongs to the supervised learning family.