Neural Networks Flashcards
6 cards from real Artificial Intelligence practice questions. Tap to flip, then mark Knew It or Still Learning — missed cards come back until you master them.
Read the first 6 Neural Networks flashcards as text
What distinguishes a convolutional neural network (CNN) from a standard feedforward network?
Answer: CNNs apply learnable filters that share weights spatially
CNNs use convolutional filters with shared weights to detect local patterns efficiently, especially in image data.
What is the purpose of a pooling layer in a CNN?
Answer: Reduce spatial dimensions and provide translational invariance
Pooling (e.g., max pooling) downsamples feature maps, reducing computation and making features more invariant to small shifts.
What is batch normalization designed to do?
Answer: Normalize layer inputs to speed up and stabilize training
Batch normalization normalizes activations within a mini-batch, reducing internal covariate shift and allowing higher learning rates.
In a recurrent neural network (RNN), what makes it suitable for sequential data?
Answer: It maintains a hidden state that captures information from previous time steps
RNNs pass a hidden state from one time step to the next, allowing the network to remember previous inputs.
What problem do LSTMs (Long Short-Term Memory networks) solve compared to standard RNNs?
Answer: Vanishing gradients over long sequences
LSTMs use gating mechanisms (forget, input, output gates) to maintain gradients over long sequences, addressing the vanishing gradient problem.
What is the softmax function used for in the output layer of a multi-class classifier?
Answer: Convert raw scores (logits) into a probability distribution over classes
Softmax exponentiates and normalizes logits so they sum to 1, providing class probabilities for multi-class classification.