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.

ps 2001 book proposed many specific problems ranging from generalizing low frequency default morphology to acquiring universally quantified one to one mappings to tracking identity and properties of individuals over time. community really has not engaged in any of these.

This is a red herring. Problem proposals are not solution proposals.

agreed. but we need consensus about what the problems are before we can find solutions not appeals to ever bigger data sets when Bengio recently acknowledged core of what I said about generalization in 2001 it was first time I saw ML leadership really engage core problem.

I disagree that we need a consensus. You're a researcher whose been in the field for decades and has owned several AI companies. If you wanted to publish a solution to one of these problems you could have. A lack of consensus hasn't been holding you back.