ELMo
Data Skeptic29 Maalis 2019

ELMo

ELMo (Embeddings from Language Models) introduced the idea of deep contextualized word representations. It extends previous ideas like word2vec and GloVe. The ELMo model is a neural network able to map natural language into a vector space. This vector space, out of box, proved to be incredibly useful in a wide variety of seemingly unrelated NLP tasks like sentiment analysis and name entity recognition.

Jaksot(590)

Listener Survey Review

Listener Survey Review

In this episode, Kyle and Linhda review the results of our recent survey. Hear all about the demographic details and how we interpret these results.

11 Elo 202023min

Human Computer Interaction and Online Privacy

Human Computer Interaction and Online Privacy

Moses Namara from the HATLab joins us to discuss his research into the interaction between privacy and human-computer interaction.

27 Heinä 202032min

Authorship Attribution of Lennon McCartney Songs

Authorship Attribution of Lennon McCartney Songs

Mark Glickman joins us to discuss the paper Data in the Life: Authorship Attribution in Lennon-McCartney Songs.

20 Heinä 202033min

GANs Can Be Interpretable

GANs Can Be Interpretable

Erik Härkönen joins us to discuss the paper GANSpace: Discovering Interpretable GAN Controls. During the interview, Kyle makes reference to this amazing interpretable GAN controls video and it's accompanying codebase found here. Erik mentions the GANspace collab notebook which is a rapid way to try these ideas out for yourself.

11 Heinä 202026min

Sentiment Preserving Fake Reviews

Sentiment Preserving Fake Reviews

David Ifeoluwa Adelani joins us to discuss Generating Sentiment-Preserving Fake Online Reviews Using Neural Language Models and Their Human- and Machine-based Detection.

6 Heinä 202028min

Interpretability Practitioners

Interpretability Practitioners

Sungsoo Ray Hong joins us to discuss the paper Human Factors in Model Interpretability: Industry Practices, Challenges, and Needs.

26 Kesä 202032min

Facial Recognition Auditing

Facial Recognition Auditing

Deb Raji joins us to discuss her recent publication Saving Face: Investigating the Ethical Concerns of Facial Recognition Auditing.

19 Kesä 202047min

Robust Fit to Nature

Robust Fit to Nature

Uri Hasson joins us this week to discuss the paper Robust-fit to Nature: An Evolutionary Perspective on Biological (and Artificial) Neural Networks.

12 Kesä 202038min

Suosittua kategoriassa Tiede

rss-mita-tulisi-tietaa
utelias-mieli
tiedekulma-podcast
hippokrateen-vastaanotolla
rss-lihavuudesta-podcast
rss-poliisin-mieli
rss-totta-vai-tuubaa
radio-antro
menologeja-tutkimusmatka-vaihdevuosiin
rss-duodecim-lehti
rss-metsanomistaja-podcast
docemilia
rss-astetta-parempi-elama-podcast
rss-radplus
rss-ilmasto-kriisissa