Главная
Study mode:
on
1
Intro
2
Deep Learning in NLP and Beyond: Overview
3
Neural networks: motivation
4
Neuron (perceptron)
5
Activation function
6
Non-linearity: example
7
Hidden layer
8
Deep Learning in NLP: RNN language model
9
RNN Extensions: Longer Short Term Memory
10
Comparison on Penn Treebank
11
Future of Deep Learning Research for NLP
12
Conclusion
Description:
Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only! Grab it Explore the frontiers of deep learning in natural language processing and beyond in this 57-minute lecture by Tomas Mikolov, a research scientist at Facebook AI Research. Gain insights into the success stories of advanced machine learning techniques in NLP, focusing on recurrent neural networks. Discover the motivations driving researchers towards deep learning approaches and learn about novel ideas for future research aimed at developing machines capable of understanding natural language and communicating with humans. Delve into topics such as neural network fundamentals, including neurons, activation functions, and hidden layers. Examine the applications of recurrent neural networks in language modeling and their extensions like Long Short-Term Memory networks. Compare performance on the Penn Treebank dataset and contemplate the future directions of deep learning research in NLP. This talk, presented at the Center for Language & Speech Processing (CLSP) at Johns Hopkins University in 2015, offers valuable perspectives on the evolving landscape of artificial intelligence and language understanding. Read more

Deep Learning in NLP and Beyond - 2015

Center for Language & Speech Processing(CLSP), JHU
Add to list