À propos de ce cours : 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.
Les destinataires de ce cours : - 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.
Enseigné par : Andrew Ng, CEO/Founder Landing AI; Co-founder, Coursera; Adjunct Professor, Stanford University; formerly Chief Scientist,Baidu and founding lead of Google Brain
Enseigné par : Head Teaching Assistant - Kian Katanforoosh, Lecturer of Computer Science at Stanford University, deeplearning.ai, Ecole CentraleSupelec
Enseigné par : Teaching Assistant - Younes Bensouda Mourri, Mathematical & Computational Sciences, Stanford University, deeplearning.ai
| Informations de base | Cours 5 de 5 dans Deep Learning Specialization |
| Niveau | Intermédiaire |
| Langue | Anglais, Sous-titres : Chinois (simplifié) |
| Matériel requis | There is no hardware requirement |
| Comment réussir | Réussissez tous les devoirs notés pour terminer le cours. |
| Notes des utilisateurs |
- Vidéo: Notation
- Vidéo: Recurrent Neural Network Model
- Vidéo: Backpropagation through time
- Vidéo: Different types of RNNs
- Vidéo: Language model and sequence generation
- Vidéo: Sampling novel sequences
- Vidéo: Vanishing gradients with RNNs
- Vidéo: Gated Recurrent Unit (GRU)
- Vidéo: Long Short Term Memory (LSTM)
- Vidéo: Bidirectional RNN
- Vidéo: Deep RNNs
- Notebook: Building a recurrent neural network - step by step
- Notebook: Dinosaur Island - Character-Level Language Modeling
- Notebook: Jazz improvisation with LSTM
- Vidéo: Using word embeddings
- Vidéo: Properties of word embeddings
- Vidéo: Embedding matrix
- Vidéo: Learning word embeddings
- Vidéo: Word2Vec
- Vidéo: Negative Sampling
- Vidéo: GloVe word vectors
- Vidéo: Sentiment Classification
- Vidéo: Debiasing word embeddings
- Notebook: Operations on word vectors - Debiasing
- Notebook: Emojify
- Vidéo: Picking the most likely sentence
- Vidéo: Beam Search
- Vidéo: Refinements to Beam Search
- Vidéo: Error analysis in beam search
- Vidéo: Bleu Score (optional)
- Vidéo: Attention Model Intuition
- Vidéo: Attention Model
- Vidéo: Speech recognition
- Vidéo: Trigger Word Detection
- Vidéo: Conclusion and thank you
- Notebook: Neural Machine Translation with Attention
- Notebook: Trigger word detection
每門課程都像是一本互動的教科書，具有預先錄製的視頻、測驗和項目。
與其他成千上萬的學生相聯繫，對想法進行辯論，討論課程材料，並尋求幫助來掌握概念。
獲得正式認證的作業，並與朋友、同事和雇主分享您的成功。
| Acheter le cours | |
|---|---|
| Accéder au contenu du cours | Disponible |
| Accéder au contenu noté | Disponible |
| Recevoir une Note Finale | Disponible |
| Obtenir un Certificat de Cours partageable | Disponible |
The sequence model course is good , but compared to the convolutional neural net course it somewhat lacking in the content. But overall the concepts and assignments are good and challenging.
Doesn't hide the math behind concepts. Provides a very detailed explanation of topics covered. Assignments are fun to do.
A wonderful, intellectual experience!
Don't fret if you are having to look up a few documentations, the comprehensive documentations of the built-in functions/layers needed are accessible on the official websites of the libraries(Keras, NumPy).
LX
Wonderful course! WONDERFUL Specialization!