All MCQs

The correct answer is a deep belief network is built using stacked probabilistic latent-variable layers. This matches the Deep Learning course topic: Deep belief networks.

The correct answer is deep learning can map acoustic or sequential features to speech units or text. This matches the Deep Learning course topic: Speech recognition applications.

The correct answer is gradient descent updates parameters in the direction that reduces loss. This matches the Deep Learning course topic: Gradient descent.

The correct answer is data augmentation creates modified training examples to improve robustness. This matches the Deep Learning course topic: Data augmentation.

The correct answer is a restricted boltzmann machine has visible and hidden units with no connections within the same layer. This matches the Deep Learning course topic: RBM.

The correct answer is deep learning is used for language modeling, translation, and text classification. This matches the Deep Learning course topic: NLP applications.

The correct answer is the learning rate controls the step size of parameter updates. This matches the Deep Learning course topic: Learning rate.

The correct answer is data normalization scales or centers data to support stable training. This matches the Deep Learning course topic: Data normalization.

The correct answer is a recurrent neural network processes sequential data using connections across time steps. This matches the Deep Learning course topic: RNN.

The correct answer is evaluation metrics such as accuracy, precision, recall, and loss help compare models. This matches the Deep Learning course topic: Evaluation metrics.

The correct answer is convolution applies learnable filters to local regions of input data. This matches the Deep Learning course topic: CNN convolution.

The correct answer is dropout randomly disables units during training to reduce co-adaptation. This matches the Deep Learning course topic: Dropout.