📝 Guest post: How to Select Better ConvNet Architectures for Image Classification Tasks*There's no go-to formula for any ML project. A huge part of improving machine learning systems is experimenting until you find a solution that works well for your use case. However, an overwhelming amount of tools and model architectures are available for computer vision tasks.
TheSequence
Recap
Interviews
Justin Harris/Microsoft"My vision is for people to be compensated for the data they provide while keeping models free to use"
Joe Doliner/CEO of Pachydermon developing a canonical ML stack and main challenges for mainstream developer adoption
Mike Del Balso/Tecton"There is too much depth in this space for feature stores to be just a “feature”