Deep Learning: A Critical Appraisal · HackerPapers discussions

Deep Learning: A Critical Appraisal — mentioned by chubot

Fri, 28 Nov 2025 16:39:16 GMT

I read Deep Learning: A Critical Appraisal ? in 2018, and just went back and skimmed it https://arxiv.org/abs/1801.00631 Here are some of the points Is deep learning approaching a wall? - He doesn't make a concrete prediction, which seems like a hedge to avoid looking silly later. Similarly, I noticed a hedge in this post: Of course it ain’t over til it’s over. Maybe pure scaling ... will somehow magically yet solve ... --- But the paper isn't wrong either: Deep learning thus far is data hungry - yes, absolutely Deep learning thus far is shallow and has limited capacity for transfer - yes…

Paper and discussion history. A mention is not an endorsement.

Deep Learning: A Critical Appraisal — mentioned by ninjin

Sun, 15 Jun 2025 02:20:43 GMT

Marcus comes with a very standard cognitive science criticism of statistical approaches to artificial intelligence, many parts of which dates back to the late 50s from when the field was born and moved to distance itself from behaviourism. The worst part to me is not that his criticism is entirely wrong, but rather that it is obvious and yet peddled as something that those of us that develop statistical approaches are completely ignorant of. To make matters worse, instead of developing alternative approaches (like plenty of my colleagues in cognitive science do!), he simply reiterates pretty…

Paper and discussion history. A mention is not an endorsement.

Deep Learning: A Critical Appraisal — mentioned by randcraw

Mon, 15 Jun 2020 16:32:34 GMT

For a rather complete view of what deep learning still does not do, I recommend the work of Gary Marcus and Ernest Davis. While seeming solely critical, I think they make very good points about the limits inherent in deep learning as we know it now, and how it needs to grow to overcome those deficits. "Rebooting AI" https://www.penguinrandomhouse.com/books/603982/rebooting-ai... And a few articles, for audiences both popular and technical: Deep Learning: A Critical Appraisal https://arxiv.org/abs/1801.00631 The Next Decade in AI https://arxiv.org/pdf/2002.06177.pdf How to Build AI We Can…

Paper and discussion history. A mention is not an endorsement.

Deep Learning: A Critical Appraisal — mentioned by chubot

Sun, 10 Nov 2019 17:55:14 GMT

I feel like anyone drawing a line from deep learning to general AI also has this problem. And that appears to be a large part of Silicon Valley. While I wasn't entirely convinced by a lot of arguments in the philosophy of mind as an undergrad 20 years ago, it definitely addresses problems "in the zeitgiest" now, e.g. with self-driving cars, etc. And the conversation there is of a higher level than I see now. I think taking a tiny bit of undergrad psychology, philosophy, and cognitive science, would help a lot of people think more clearly about AI. I didn't necessarily think that was true when…

Paper and discussion history. A mention is not an endorsement.

Deep Learning: A Critical Appraisal — HN submission

Fri, 03 May 2019 07:30:12 GMT

Deep Learning: A Critical Appraisal (2018)

77 points; 41 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Deep Learning: A Critical Appraisal — mentioned by randcraw

Wed, 23 Jan 2019 19:31:28 GMT

It's far too early to render a judgment on the long term potential of DL toward building Commander Data, both pro and con. But after some 60 years of AI research we understand the problem space pretty well, and we can see also that DL has shown little or no promise toward serving many of the component processes necessary to deliver General AI/AGI. (And just because you can federate and combine DL networks like you can NAND gates doesn't mean they are turing equivalent to the human brain. It's fundamental to claims of such turing-AI-equivalency that we have absolutely no idea yet how to do…

Paper and discussion history. A mention is not an endorsement.

Deep Learning: A Critical Appraisal — HN submission

Sat, 02 Jun 2018 21:43:01 GMT

Deep learning: a critical appraisal

147 points; 61 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Deep Learning: A Critical Appraisal — mentioned by shoguning

Fri, 20 Apr 2018 22:32:38 GMT

AFAIK, these are all implementations of deep learning or similar, not a fundamentally new architecture. We'll continue to see these as DL matures, but it doesn't address the shortcomings of the technique. For more perspective: https://arxiv.org/abs/1801.00631

Paper and discussion history. A mention is not an endorsement.

Deep Learning: A Critical Appraisal — HN submission

Thu, 08 Feb 2018 02:25:40 GMT

Deep Learning: A Critical Appraisal [pdf]

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Deep Learning: A Critical Appraisal — HN submission

Sat, 13 Jan 2018 18:06:02 GMT

Deep Learning: A Critical Appraisal

3 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Deep Learning: A Critical Appraisal — HN submission

Fri, 12 Jan 2018 13:17:14 GMT

Deep Learning, a critical appraisal

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Deep Learning: A Critical Appraisal — HN submission

Mon, 08 Jan 2018 05:23:25 GMT

Deep Learning: A Critical Appraisal

3 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Deep Learning: A Critical Appraisal — HN submission

Fri, 05 Jan 2018 17:58:47 GMT

Deep Learning: A Critical Appraisal by Gary Marcus

3 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Deep Learning: A Critical Appraisal — HN submission

Fri, 05 Jan 2018 14:29:17 GMT

Deep learning: a critical appraisal [pdf]

4 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Deep Learning: A Critical Appraisal — HN submission

Thu, 04 Jan 2018 13:40:28 GMT

Deep Learning: A Critical Appraisal [pdf]

4 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Deep Learning: A Critical Appraisal — HN submission

Wed, 03 Jan 2018 01:52:46 GMT

Deep Learning: A Critical Appraisal

5 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.