HackerPapers

arXiv:1801.04016cs.LG

Theoretical Impediments to Machine Learning With Seven Sparks from the Causal Revolution

Judea Pearl

Abstract

Current machine learning systems operate, almost exclusively, in a statistical, or model-free mode, which entails severe theoretical limits on their power and performance. Such systems cannot reason about interventions and retrospection and, therefore, cannot serve as the basis for strong AI. To achieve human level intelligence, learning machines need the guidance of a model of reality, similar to the ones used in causal inference tasks. To demonstrate the essential role of such models, I will present a summary of seven tasks which are beyond reach of current machine learning systems and which have been accomplished using the tools of causal modeling.

arXiv comments
8 pages, 3 figures
Journal reference
DOI
Subjects
cs.LGMachine Learning cs.AIArtificial Intelligence stat.MLMachine Learning (Statistics)

On Hacker News

Linked by 4 identifiable commenters in 4 comments across 4 threads, from Jan 2018 to Jul 2025. Found in 1 HN submission from Jan 2018 to Jan 2018. Open submission discussions.

Comments linking this paper, per year.

Discussed in comments4 threads

  1. AGI Is Mathematically Impossible (3): Kolmogorov Complexity 1 comment

    • Okay, read the abstract and Intro. Recently, in the paper "What Has a Foundation Model Found? Using Inductive Bias to Probe for World Models" your thesis of Ai's lack of capacity to abstract or at least extract understanding from noisy data was largely experimentally confirmed.…

      marvin-hansenView on HNParent context

  2. Artificial Intelligence with Erlang: The Domain of Relatives (2007) 1 comment

    • Check out this paper by Turin-award winner Judea Pearl for fundamental limitations of current approaches to ML: https://arxiv.org/abs/1801.04016

      vokolkView on HNParent context

  3. Ask HN: What are the best MOOCs you've taken? 1 comment
  4. Alibaba neural network defeats human in global reading test 1 comment

    • Great result. At my job I manage a machine learning team and so I am fairly much all-in for deep learning to solve practical problems. That said, I think the path to 'real' AGI lies in some combination of DL, probabilistic graph models, symbolic systems, and something we have…

      mark_l_watsonView on HNParent context

Submitted to Hacker News

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