关于此课程： This course will teach you how to build models for natural language, audio, and other sequence data. Thanks to deep learning, sequence algorithms are working far better than just two years ago, and this is enabling numerous exciting applications in speech recognition, music synthesis, chatbots, machine translation, natural language understanding, and many others. You will: - Understand how to build and train Recurrent Neural Networks (RNNs), and commonly-used variants such as GRUs and LSTMs. - Be able to apply sequence models to natural language problems, including text synthesis. - Be able to apply sequence models to audio applications, including speech recognition and music synthesis. This is the fifth and final course of the Deep Learning Specialization. deeplearning.ai is also partnering with the NVIDIA Deep Learning Institute (DLI) in Course 5, Sequence Models, to provide a programming assignment on Machine Translation with deep learning. You will have the opportunity to build a deep learning project with cutting-edge, industry-relevant content.
此课程适用人群： - Learners that took course one, two, and four of the specialization. Course three is also recommended. - Anyone that already has a solid understanding of learning with neural networks, including convolutional networks, and wants to learn how to develop recurrent neural networks.
教学方： Andrew Ng, Co-founder, Coursera; Adjunct Professor, Stanford University; formerly head of Baidu AI Group/Google Brain
教学方： Head Teaching Assistant - Kian Katanforoosh, Lecturer of Computer Science at Stanford University, deeplearning.ai, Ecole CentraleSupelec
教学方： Teaching Assistant - Younes Bensouda Mourri, Mathematical & Computational Sciences, Stanford University, deeplearning.ai
| 基本信息 | 课程 5（共 5 门，Deep Learning Specialization ） |
| 级别 | 中级 |
| 语言 | English, 字幕： Chinese (Simplified) |
| 硬件要求 | There is no hardware requirement |
| 如何通过 | 通过所有计分作业以完成课程。 |
| 用户评分 |
- 视频: Notation
- 视频: Recurrent Neural Network Model
- 视频: Backpropagation through time
- 视频: Different types of RNNs
- 视频: Language model and sequence generation
- 视频: Sampling novel sequences
- 视频: Vanishing gradients with RNNs
- 视频: Gated Recurrent Unit (GRU)
- 视频: Long Short Term Memory (LSTM)
- 视频: Bidirectional RNN
- 视频: Deep RNNs
- Notebook: Building a recurrent neural network - step by step
- Notebook: Dinosaur Island - Character-Level Language Modeling
- Notebook: Jazz improvisation with LSTM
- 视频: Using word embeddings
- 视频: Properties of word embeddings
- 视频: Embedding matrix
- 视频: Learning word embeddings
- 视频: Word2Vec
- 视频: Negative Sampling
- 视频: GloVe word vectors
- 视频: Sentiment Classification
- 视频: Debiasing word embeddings
- Notebook: Operations on word vectors - Debiasing
- Notebook: Emojify
- 视频: Picking the most likely sentence
- 视频: Beam Search
- 视频: Refinements to Beam Search
- 视频: Error analysis in beam search
- 视频: Bleu Score (optional)
- 视频: Attention Model Intuition
- 视频: Attention Model
- 视频: Speech recognition
- 视频: Trigger Word Detection
- 视频: Conclusion and thank you
- Notebook: Neural Machine Translation with Attention
- Notebook: Trigger word detection
Each course is like an interactive textbook, featuring pre-recorded videos, quizzes and projects.
Connect with thousands of other learners and debate ideas, discuss course material, and get help mastering concepts.
Earn official recognition for your work, and share your success with friends, colleagues, and employers.
| 购买课程 | |
|---|---|
| 访问课程材料 | 可用 |
| 访问评分的材料 | 可用 |
| 收到最终成绩 | 可用 |
| 获得可共享的课程证书 | 可用 |
Challenging and interesting last episode of the series!
Great content, and leaves me set to build systems making predictions for or conversions between sequences- particularly including text posts, which are an interest of mine.
Deducted a star because a couple of ungraded exercises contained errors which had been left uncorrected; they were still valuable, especially the manual implementation of backprop one, but there's some missing attention to detail there. But the level and effectiveness and practical applicability of the course remains excellent and I'd still heavily recommend it.
This last course of the series while still being excellent, it had a few minor issues in the assignments and was quite hard compared to the previous four. Nevertheless, I still learned a lot from it and I am really grateful for it being available.
KC
Very comprehensive. Learned a lot. Especially helpful when Prof Ng recommends the relevant papers to read. Thank you.