Core Deep Learning Models - MLPs, CNNs, and RNNs August 01, 2020 MLPs (Multilayer perceptrons) common in simple logistic and linear regression problems. CNNs (Convolutional neural networks) are for multi-dimensional data like images and videos. A CNN excels in extracting feature maps for classification, segmentation, generation, and other purposes. RNNs (Recurrent neural networks) are for sequential data input (like text in Natural Language Processing (NLP) or stream of sensor data in instrumentation) because the internal design allows the network to discover dependency in the history of data that is useful for prediction. LSTMs (Long Short-Term Memory) members of the RNN family have been used in both machine translation and question answering problems.