This 11-video course explores the concept of deep learning and implementation of deep learning-based frameworks for natural language processing (NLP) and audio data analysis. Discover the architectures of recurrent neural network (RNN) that can be used in modeling NLP, and the challenges of unsupervised learning and the approach of using deep learning from the perspective of common unsupervised feature machine learning. First, examine the prominent statistical classification models and compare generative classifiers with discriminative classifiers; then recall different types of generative models, with focus on generative adversarial network, variational autoencoders, and flow-based generative model. Learn about setting up and working with PixelCNN; explore differences between multilayer perception (MLP), convolutional neural network (CNN), and RNN. Explore the essential capabilities and variants of ResNet that can be used for computer vision and deep learning. Finally, take a look at encoders in neural networks and compare the capabilities of standard autoencoders and variational autoencoders. The concluding exercise involves recalling RNN architecture that can be used in modeling NLP, variants of ResNet, and setting up PixelCNN.
recall the concept of deep learning and the approach of using deep learning-based frameworks to model NLP tasks and audio data analysis
describe the role of recurrent neural network and the various architectures of recurrent neural network that can be used in modeling natural language processing
recognize the challenges associated with unsupervised learning and the approach of using deep learning from the perspective of common unsupervised feature learning
describe the prominent statistical classification models and compare generative classifiers with discriminative classifiers
recall the different types of generative models, with focus on generative adversarial network, variational autoencoders, and flow-based generative model
demonstrate the steps involved in setting up and working with PixelCNN
describe the characteristics of the different classes of artificial neural networks and the difference between MLP, CNN, and RNN
recognize the essential capabilities and variants of ResNet that can be used for computer vision and deep learning
describe encoders in neural networks and compare the capabilities of standard autoencoders and variational autoencoders
recall the prominent architectures of recurrent neural network that can be used in modeling natural language processing, list the variants of ResNet that can be used for computer vision and deep learning, and set up PixelCNN