JNTU B.Tech IV NEURAL NETWORKS AND DEEP LEARNING Previous Question Paper (July - 2023 - R16)

Supervised learning involves training a model on a labeled dataset where the input data is paired with the correct output, allowing the algorithm to learn a mapping function to predict labels for new, unseen data. In contrast, unsupervised learning utilizes unlabeled data, where the algorithm must identify hidden patterns, structures, or groupings within the input data without explicit guidance or target outputs.

The sigmoid function, which maps input values to a range between 0 and 1, is primarily categorized into two types based on its mathematical formulation:

1. Logistic Sigmoid Function: This is the standard sigmoid function defined as
   f(x) = 1 / (1 + e⁻ˣ)
   . It is widely used in binary classification tasks and in the output layer of neural networks to represent probabilities.
2. Hyperbolic Tangent (tanh) Function: This is a scaled and shifted version of the logistic sigmoid, defined as
   f(x) = (eˣ - e⁻ˣ) / (eˣ + e⁻ˣ)
   . It maps inputs to a range between -1 and 1, making it zero-centered, which often leads to faster convergence during training compared to the logistic sigmoid.