https://github.com/enet4/dspt-representation-learning
"Pulling out the big GANs: from representation learning to faking things" - a talk for Data Science Portugal
https://github.com/enet4/dspt-representation-learning
deep-learning presentation-slides
Last synced: 7 months ago
JSON representation
"Pulling out the big GANs: from representation learning to faking things" - a talk for Data Science Portugal
- Host: GitHub
- URL: https://github.com/enet4/dspt-representation-learning
- Owner: Enet4
- Created: 2019-05-25T13:29:09.000Z (over 6 years ago)
- Default Branch: master
- Last Pushed: 2019-06-04T18:21:44.000Z (over 6 years ago)
- Last Synced: 2024-12-30T01:49:53.527Z (about 1 year ago)
- Topics: deep-learning, presentation-slides
- Language: JavaScript
- Homepage: https://enet4.github.io/dspt-representation-learning
- Size: 60.1 MB
- Stars: 3
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
## Pulling out the big GANs: from representation learning to faking things
A talk about representation learning and generative adversarial networks, presented for the [56th Meetup](https://www.meetup.com/datascienceportugal/events/261030588) of [Data Science Portugal](www.datascienceportugal.com). The estimated duration is 30 minutes.
[See the slides here.](https://enet4.github.io/dspt-representation-learning)
**Abstract:**
The modern practice of deep learning has enabled automatic solutions to problems once thought very hard to achieve. Its emergence in multiple computer science fields (computer vision, natural language processing, and more) is influencing a wide spectrum of projects and applications. In a recent breakthrough, generative adversarial networks (GANs) made way for use cases beyond surprisingly appealing generative models, and they could become the culprit for many of the upcoming attempts to fool our society and create fake information. Yet, much of their success can be traced back to the study of _representation learning_ as a superset of deep learning.
This presentation will first cover a brief overview of representation learning, followed by a few noteworthy methods. The second part provides an explanation of what GANs are and what they can do, up to the current state of the art. Before the conclusion, a use case for unsupervised learning methods is presented in the context of information extraction from medical images.