Stochastic Modeling
Artificial Intelligence
A variation of gradient descent that updates parameters using a single randomly chosen training example at each iteration.
Detailed Explanation
Stochastic Gradient Descent (SGD) is an optimization algorithm used in machine learning to minimize a loss function. Unlike traditional gradient descent, which computes gradients using the entire dataset, SGD updates model parameters using only one randomly selected training example per iteration. This approach reduces computation time and helps the model escape local minima, making it suitable for large-scale data.
Use Cases
- •Optimize neural networks efficiently by updating weights with individual data points, accelerating training on large datasets.
Related Terms
Other terms in the Artificial Intelligence category