Sequence to sequence learning with encoder-decoder neural network models
In recent years, there has been a lot of research in the area of sequence to sequence learning with neural network models. These models are widely used for applications such as language modeling, translation, part of speech tagging, and automatic speech recognition. In this talk, we will give an overview of sequence to sequence learning, starting with a description of recurrent neural networks (RNNs) for language modeling. We will then explain some of the drawbacks of RNNs, such as their inability to handle input and output sequences of different lengths, and describe how encoder-decoder networks, and attention mechanisms solve these problems. We will close with some real-world examples, including how encoder-decoder networks are used at LinkedIn.
Outline/Structure of the Talk
- An overview of sequence to sequence learning
- Introduction to RNNs for language modeling, translation, speech tagging, and automatic speech recognition
- Drawbacks of RNNs (such as their inability to handle input and output sequences of different lengths)
- Describe how encoder-decoder networks and attention mechanisms solve these problems.
- We will close with some real-world examples, including how encoder-decoder networks are used at LinkedIn.
Learning Outcome
- Understanding of RNNs for Language Modeling
- Draws of RNNs and how to overcome them
- How LinkedIn is using encoder-decoder networks
Target Audience
Data Scientists, Data Engineers, Data Specialists, Machine Learning Engineers, Data Science Enthusiasts
Video
schedule Submitted 3 years ago
Recent Activities
- description Naresh Jain updated proposal Sequence to sequence lear...schedule 3 years ago
- description Deepti Tomar updated proposal Sequence to sequence lear...schedule 3 years ago
- description Naresh Jain updated proposal Sequence to sequence lear...schedule 3 years ago
Call for Proposals CLOSED
Ended on Apr 15 '19 11:30 PM IST
We are looking for deep technical topics related to Data Science. We are committed to diversity and believe in transparency. Hence, all proposals will be public.
Registered user will be able to comment on your proposal. You are required to reply to those comments to provide clarifications, explain revisions and respond to questions. The program team will look at how well you've responded to comments and updated your proposal to incorporate public suggestions. Ultimately the decision to accept a session resides with the program team.
Your proposal stands the best chance to be selected, if it's unique, fully flushed, ready-to-go. Please ensure you've read:
To encourage early submissions and iterative improvement of proposals, we start accepting proposals as soon as we find them a good fit. Since competition gets tougher with progressing time, it is advisable to avoid waiting until the last minute for proposal submission.
Dr. Vikas Agrawal
Anoop Kulkarni
Naresh Jain
Usha Rengaraju
Dipanjan Sarkar
