Question 2What is NOT TRUE about RNNs?1 pointRNNs are VERY suitable for sequential data.RNNs need to keep track of states, which is computationally expensive. RNNs are very robust against vanishing gradient problem.

Why are RNNs susceptible to issues with their gradients?1 pointGradients can grow exponentiallyGradients can quickly drop and stabilize at near zeroPropagation of errors due to the recurrent characteristicNumerical computation of gradients can drive into instabilitiesAll of the above

Which problem arises when training RNNs on long sequences?All of the given optionsUnderfittingVanishing or exploding gradientsOverfittingHigh bias

What is the advantage of using recurrent layers in an RNN?Question 21Answera. They can handle variable-length inputsb.   They can generate synthetic datac.They can handle non-linear transformationsd.    They can capture temporal dependencies in the input data

What is a significant benefit of using the Transformer model over RNNs for sequence-to-sequence tasks?*1 pointTransformers are easier to train due to parallel processing.Transformers are better at handling long sequences without loss of information.Transformers require less data to train.Transformers do not require attention mechanisms.

Recurrent Artificial Neural NetworksRecurrent Artificial Neural Networks (RNNs) are a type of neural network architecture that is designed to handle sequential data by introducing connections between units in the network that form directed cycles. This cyclic structure allows information to persist over time and enables the network to exhibit dynamic temporal behavior.In contrast to feedforward neural networks, where information flows in one direction from input to output, RNNs have connections that loop back on themselves, allowing them to maintain an internal state or memory of previous inputs. This makes them well-suited for tasks that involve sequential data or time series, such as natural language processing, speech recognition, and time series prediction. The basic unit of an RNN is called a recurrent neuron or a recurrent unit.