Udemy – NLP Deep Learning – Part 1, 2021–7 – Download

Descriptions

Deep learning for NLP. I will introduce core deep learning concepts such as multilayer perceptrons, word embeddings, and recurrent neural networks. These concepts form the basis for a good understanding of advanced deep learning models for natural language processing. In this course, I will introduce core deep learning concepts such as multilayer perceptrons, word embeddings, and recurrent neural networks. I will introduce concepts such as encoder-decoder attention models, ELMo, GLUE, Transformers, GPT and BERT. I will introduce concepts such as sentence embeddings and generative transformer models. These concepts form the basis for a good understanding of advanced deep learning models for today’s natural language generation. I will talk O Encoder,Decoder models in the context of machine translation and beam search decoder operation. Next, I’ll talk about the concept of encoder-decoder attention. Next, I will elaborate on the different types of attention such as global attention, local attention, hierarchical attention, and attention to sentence pairs using CNN as well as LSTM. We will also talk about visualization of attention. Finally, we discuss ELMo, which is a way of using recurrent models to compute context-sensitive word embeddings.