HackerPapers

arXiv:1801.00631cs.AI

Deep Learning: A Critical Appraisal

Gary Marcus

Abstract

Although deep learning has historical roots going back decades, neither the term "deep learning" nor the approach was popular just over five years ago, when the field was reignited by papers such as Krizhevsky, Sutskever and Hinton's now classic (2012) deep network model of Imagenet. What has the field discovered in the five subsequent years? Against a background of considerable progress in areas such as speech recognition, image recognition, and game playing, and considerable enthusiasm in the popular press, I present ten concerns for deep learning, and suggest that deep learning must be supplemented by other techniques if we are to reach artificial general intelligence.

arXiv comments
1 figure
Journal reference
DOI
Subjects
cs.AIArtificial Intelligence cs.LGMachine Learning stat.MLMachine Learning (Statistics)

On Hacker News

Linked by 4 identifiable commenters in 6 comments across 6 threads, from Apr 2018 to Nov 2025. Found in 10 HN submissions from Jan 2018 to May 2019. Open submission discussions.

Comments linking this paper, per year.

Discussed in comments6 threads

  1. A trillion dollars (potentially) wasted on gen-AI 1 comment

    • 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…

      chubotView on HNParent context

  2. Seven replies to the viral Apple reasoning paper and why they fall short 1 comment

    • 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…

      ninjinView on HNParent context

  3. An understanding of AI’s limitations is starting to sink in 1 comment

    • 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…

      randcrawView on HNParent context

  4. It’s impossible to see the world as it is, argues a neuroscientist [video] 1 comment

    • 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…

      chubotView on HNParent context

  5. What are the limits of deep learning? 1 comment

    • 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…

      randcrawView on HNParent context

  6. The AI Revolution Hasn’t Happened Yet 1 comment

    • 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

      shoguningView on HNParent context

Submitted to Hacker News

Connected through shared HN threads, not inferred similarity or a recommendation.