Important Deep learning Concept Explained Part – 2
Algorithm that converges will eventually reach an optimal answer, even if very slowly. An algorithm that doesn’t converge may never reach an optimal answer.
Rate at which optimizers change weights and biases. High learning rate generally trains faster but risks not converging whereas a lower rate trains slower.
Issues with very large/small values due to limits of floating-point numbers in computers.
Mapping from discrete objects. Such as words, to vectors of real numbers. Useful because classifier/neural networks work well on vectors of real numbers.
Series of convolutional operations, each acting a different slice of the input matrix.
Method for regularization that involves ending training early.
Technique to minimize loss by computing the gradients of loss with respect to the model’s parameters, conditioned on training data.