Backpropagation is a fundamental algorithm used to train artificial neural networks. It is used to minimize the error between the predicted output and the actual output by adjusting the network's weights.
In a neural network, weights are the adjustable parameters that control the strength of the connections between neurons in the layers.
The derivative of activation functions is crucial in the training of neural networks, especially during the backpropagation process.
The exponential function is unique in calculus because it is the only function that is its own derivative. This property makes it extremely important in various fields like physics, economics, and engineering.
Cross-entropy is a loss function commonly used in machine learning, particularly in classification tasks. It measures the difference between two probability distributions: the true labels and the predicted probabilities.
Neural Network is a machine learning model inspired by the human brain, designed to recognize patterns and solve complex tasks. It consists of interconnected units called neurons organized into layers
Activation functions in machine learning define how a neuron in a neural network processes input data and decides whether to pass it to the next layer.
Probability Distribution describes how the probabilities are distributed over the possible outcomes of a random variable. It can be discrete, where outcomes are countable (e.g., rolling a die), or continuous, where outcomes can take any value within a range (e.g., heights of people).
Probability is a measure of the likelihood that a particular event will occur, quantified as a number between 0 and 1, where 0 indicates impossibility and 1 indicates certainty. It is used to model uncertainty and make predictions about random events in various fields, including machine learning.
The chain rule is a fundamental theorem in calculus that provides a method for computing the derivative of a composite function. It allows us to understand how a change in one variable propagates through a series of dependent variables
The Gradient Descent algorithm has numerous variants, each developed to address specific issues or improve performance under certain conditions
