Published On Apr 2, 2021
Machine Learning Monthly covers the latest and greatest (but not always the latest) in machine learning of the previous month. This month we see things like multimodal modelling (modelling multiple sources of data types such as images combined with text) and self-supervised learning taking centre stage.
Machine Learning Monthly March 2021 - https://zerotomastery.io/blog/machine...
EfficientNetV2 - https://arxiv.org/abs/2104.00298
Learn:
Beginner-friendly Machine Learning - https://dbourke.link/mlcourse
TensorFlow for Deep Learning - https://dbourke.link/ZTMTFcourse
Connect elsewhere:
Web - https://dbourke.link/web
Twitch - / mrdbourke
ArXiv channel (past streams) - / @danielbourkearxiv2821
Get email updates on my work - https://dbourke.link/newsletter
Timestamps:
0:00 - Intro/hello/dancing
0:54 - My work from the past month
2:21 - Why is machine learning hard? By Zayd Enam
4:13 - Software 2.0 by Andrej Karpathy
4:32 - Start with less fancy networks by Victor Sanh
6:50 - Airbnb’s Multimodal model for images, text and structured data
10:16 - Learning from Videos by Facebook AI
13:10 - Self-supervised Learning: The dark matter of intelligence by Yann LeCun
15:48 - SEER: A new state of the art for self-supervised computer vision
18:39 - Paper of the month: ResNets are back baby!!!
21:55 - ...and they’re gone, welcome EfficientNetV2
24:03 - Super-powered Speech tools: Coqui & SpeechBrain
26:03 - The Deep Bootstrap Framework
30:27 - Summary/outro/more dancing
#machinelearningmonthly #machinelearning