____________is the number of times the algorithm runs on the whole training dataset.BatchEpochLearning rateCost function

____________denotes the number of samples to be taken to for updating the model parameters.BatchEpochLearning rateCost function

What is the purpose of the learning rate in neural network optimization?Review LaterTo control the number of epochsTo determine the batch sizeTo adjust the step size during weight updatesTo set the initial weights

The ______________ optimization algorithm updates weights more frequently than batch gradient descent by using one training example at a time.

The algorithm is known for its efficient computational performance for large datasets by approximating the gradient of the cost function on smaller batches. On the other hand, the algorithm adapts the learning rate for each parameter by considering the recent magnitude of the gradients, helping in faster convergence, especially when dealing with data.

Suppose we trained an MLP for 100 epochs with PyTorch. When creating the Dataloader, we set the batch size to be 40 and other parameters have been set to default. We know that it has generated 30 batches in total. After training completed, how many samples has the model been trained with in total? (Consider the same samples fed during different epochs as different samples. i.e., if we only have 1 sample and the model has been trained for 10 epochs, the answer will be 10.) Choose the most accurate range.