All MCQs

The correct answer is gpus accelerate deep learning by performing many parallel numerical operations. This matches the Deep Learning course topic: GPU programming.

The correct answer is lstm networks use gates to manage long-term dependencies and reduce vanishing-gradient effects. This matches the Deep Learning course topic: LSTM.

The correct answer is backpropagation through time unfolds an rnn across time steps to compute gradients. This matches the Deep Learning course topic: BPTT.

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 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 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 sparse coding encourages representations where only a small number of units are active. This matches the Deep Learning course topic: Sparse coding.

The correct answer is an autoencoder learns to encode input into a latent representation and reconstruct it. This matches the Deep Learning course topic: Autoencoders.

The correct answer is cnn computational cost depends on filter size, input size, channels, and number of filters. This matches the Deep Learning course topic: CNN complexity.

The correct answer is a feature map represents filter responses across spatial locations. This matches the Deep Learning course topic: CNN feature maps.

The correct answer is pooling reduces spatial dimensions while keeping important features. This matches the Deep Learning course topic: CNN pooling.

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