Supervised Learning

Unsupervised Learning

1. Supervised Learning is also known as associative learning, in which the network is trained by providing it with input and matching output patterns. Unsupervised Learning is also known as self-organization, in which an output unit is trained to respond to clusters of patterns within the input.
2. Supervised training requires the pairing of each input vector with a target vector representing the desired output. Unsupervised training is employed in self-organizing neural networks.
3. During the training session, an input vector is applied to the network, and it results in an output vector. This response is then compared with the target response. During training, the neural network receives input patterns and organizes these patterns into categories. When a new input pattern is applied, the neural network provides an output response indicating the class to which the input patterns belong.
4. If the actual response differs from the target response, the network will generate an error signal. If a class cannot be found for the input pattern, a new class is generated.
5. The error minimization in this kind of training requires a supervisor or teacher. These input-output pairs can be provided by an external teacher, or by the system which contains a neural network. Unsupervised training does not require a teacher, it requires certain guidelines to form groups. Grouping can be done based on color, shape, and any other property of the object.
6. Supervised training methods are used to perform non-linear mapping in pattern classification networks, pattern association networks, and multi-layer neural networks.  Unsupervised learning is useful for data compression and clustering.
7. Supervised learning generates a global model and a local model. In this, a system is supposed to discover statistically silent features of the input population.