Gary Marcus

@GaryMarcus I would like in fact to hear a solid and testable proposal based on your 20 years of insisting how ML is not on the right track (as you said in an earlier tweet in this week), instead of another essay.https://twitter.com/GaryMarcus/status/1200613819518599169 …

The solid proposal is that we need to search a different part of model space, as described in detail in 2001, where I made several specifics proposals about important challenges that the ML community simply has refused (for the most part) to engage with. I can't do it on my own.

@GaryMarcus "search a different part of model space" is not a testable proposal, nor your whole book from 2001 is. I wanted to hear what that different part is, in equations or pseudo code.

- look at relationships between variables, a la ILP and MLNs and some recent work in differentiable programming - include a type-token distinction - don’t waste your time with bags of features; only consider architectures with structured representations - learn a common sense db