mlsanityData to 14 Oct 2026

Metaphors We Learn By

arXiv 2211.06441 ↗First posted 11 Nov 2022cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Gradient based learning using error back-propagation (``backprop'') is a well-known contributor to much of the recent progress in AI. A less obvious, but arguably equally important, ingredient is parameter sharing - most well-known in the context of convolutional networks. In this essay we relate parameter sharing (``weight sharing'') to analogy making and the school of thought of cognitive metaphor. We discuss how recurrent and auto-regressive models can be thought of as extending analogy making from static features to dynamic skills and procedures. We also discuss corollaries of this perspective, for example, how it can challenge the currently entrenched dichotomy between connectionist and ``classic'' rule-based views of computation.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 24 of its 39 references that are in the map. First posted on arXiv 11 Nov 2022.

Builds on

24 of 39 references.

References · 24

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  2. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  3. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  4. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
  5. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,386
  6. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,162
  7. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,745
  8. 2021Decision Transformer: Reinforcement Learning via Sequence Modelingcited by 1,546
  9. 2022Competition-Level Code Generation with AlphaCodecited by 1,462
  10. 2022Solving Quantitative Reasoning Problems with Language Modelscited by 1,392
  11. 2022LaMDA: Language Models for Dialog Applicationscited by 1,220
  12. 2017The "something something" video database for learning and evaluating visual common sensecited by 1,103
12 more
  1. 2021Show Your Work: Scratchpads for Intermediate Computation with Language Modelscited by 886
  2. 2022A Generalist Agentcited by 808
  3. 2014Neural Turing Machinescited by 644
  4. 2013DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognitioncited by 424
  5. 2014Memory Networkscited by 363
  6. 2014CNN Features off-the-shelf: an Astounding Baseline for Recognitioncited by 316
  7. 2015Learning Visual Features from Large Weakly Supervised Datacited by 165
  8. 2021Pretrained Transformers as Universal Computation Enginescited by 162
  9. 2017The Consciousness Priorcited by 107
  10. 2014Learning to Executecited by 106
  11. 2021Learning to See by Looking at Noisecited by 92
  12. 2021Teaching Autoregressive Language Models Complex Tasks By Demonstrationcited by 15

Built on by

Not cited yet.