#44 - Data2Vec, training one model with text, audio and image.
An episode of the Life with AI podcast, hosted by Filipe Lauar, titled "#44 - Data2Vec, training one model with text, audio and image." was published on March 31, 2022 and runs 18 minutes.
March 31, 2022 ·18m · Life with AI
Summary
Hey guys, in this episode I talk about Data2Vec, a revolutionary algorithm that is able to learn from 3 different data modalities, audio, text and image and be better or comparable than previous state of the art methods. Also this algorithm uses a self-supervised approach, which means that it doesn’t use labels to the training. If you want to better understand it go listen to the episode! Instagram: https://www.instagram.com/podcast.lifewithai/ Linkedin: https://www.linkedin.com/company/life-with-ai Paper: https://arxiv.org/pdf/2202.03555.pdf Github code and models: https://github.com/pytorch/fairseq/tree/main/examples/data2vec
Episode Description
Hey guys, in this episode I talk about Data2Vec, a revolutionary algorithm that is able to learn from 3 different data modalities, audio, text and image and be better or comparable than previous state of the art methods. Also this algorithm uses a self-supervised approach, which means that it doesn’t use labels to the training. If you want to better understand it go listen to the episode!
Instagram: https://www.instagram.com/podcast.lifewithai/
Linkedin: https://www.linkedin.com/company/life-with-ai
Paper: https://arxiv.org/pdf/2202.03555.pdf
Github code and models: https://github.com/pytorch/fairseq/tree/main/examples/data2vec
Similar Episodes
Jan 15, 2025 ·15m
Jan 15, 2025 ·18m
Dec 8, 2023 ·20m
Oct 25, 2023 ·18m
Oct 21, 2023 ·19m
Sep 16, 2023 ·18m