Transfers ToCSUDescriptionThis course focuses on in-depth understanding of Deep learning concepts, architectures and applications. Training Deep learning networks can be a challenging task and requires a good understanding of the nature of gradient descent and its variants. Students will learn about different forms of loss functions and hyper parameters and regularization in convolutional neural networks, RNNs and generative adversarial networks. The focus then turns into reinforcement learning as an alternative to supervised learning. Keras/TensorFlow will be used as a key framework to model different neural network architectures. 