mlsanityData to 14 Oct 2026

Neither hype nor gloom do DNNs justice

arXiv 2312.05355 ↗First posted 8 Dec 2023cs.LG cs.CV q-bio.NCcited by 40

Not on the map. Why?

Abstract (arXiv)

Neither the hype exemplified in some exaggerated claims about deep neural networks (DNNs), nor the gloom expressed by Bowers et al. do DNNs as models in vision science justice: DNNs rapidly evolve, and today's limitations are often tomorrow's successes. In addition, providing explanations as well as prediction and image-computability are model desiderata; one should not be favoured at the expense of the other.

Key facts. Cited by 40 papers in the map (data through 14 Oct 2026). Builds on 61 of its 369 references that are in the map. First posted on arXiv 8 Dec 2023.

Builds on

61 of 369 references.

References · 61

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  4. 2020Language Models are Few-Shot Learnerscited by 32,419
  5. 2022Training language models to follow instructions with human feedbackcited by 15,971
  6. 2013Intriguing properties of neural networkscited by 5,155
  7. 2020Shortcut Learning in Deep Neural Networkscited by 1,969
  8. 2019Invariant Risk Minimizationcited by 1,854
  9. 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,432
  10. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 776
  11. 2016End-to-end Optimized Image Compressioncited by 696
  12. 2023Scaling Vision Transformers to 22 Billion Parameterscited by 694
38 more
  1. 2017Dynamic Routing Between Capsulescited by 689
  2. 2021Towards Out-Of-Distribution Generalization: A Surveycited by 436
  3. 2017Wild Patterns: Ten Years After the Rise of Adversarial Machine Learningcited by 414
  4. 2019The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervisioncited by 372
  5. 2016Assessing the Ability of LSTMs to Learn Syntax-Sensitive Dependenciescited by 354
  6. 2019Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Comingcited by 336
  7. 2018Understanding disentangling in β-VAEcited by 335
  8. 2020ThreeDWorld: A Platform for Interactive Multi-Modal Physical Simulationcited by 250
  9. 2018Targeted Syntactic Evaluation of Language Modelscited by 242
  10. 2018Colorless green recurrent networks dream hierarchicallycited by 213
  11. 2016Deep Predictive Coding Networks for Video Prediction and Unsupervised Learningcited by 204
  12. 2018A mathematical theory of semantic development in deep neural networkscited by 186
  13. 2021Partial success in closing the gap between human and machine visioncited by 185
  14. 2020Liquid Time-constant Networkscited by 161
  15. 2019MNIST-C: A Robustness Benchmark for Computer Visioncited by 138
  16. 2021How to represent part-whole hierarchies in a neural networkcited by 123
  17. 2017The Consciousness Priorcited by 107
  18. 2018Learning long-range spatial dependencies with horizontal gated-recurrent unitscited by 98
  19. 2020Convolutional Neural Networks as a Model of the Visual System: Past, Present, and Futurecited by 83
  20. 2018Adversarial Examples that Fool both Computer Vision and Time-Limited Humanscited by 73
  21. 2020Self-supervised learning through the eyes of a childcited by 61
  22. 2022Harmonizing the object recognition strategies of deep neural networks with humanscited by 59
  23. 2021Active Inference in Robotics and Artificial Agents: Survey and Challengescited by 52
  24. 2022The neuroconnectionist research programmecited by 48
  25. 2022Predictive Coding: Towards a Future of Deep Learning beyond Backpropagation?cited by 45
  26. 2018Cognitive computational neurosciencecited by 43
  27. 2018Learning to Play with Intrinsically-Motivated Self-Aware Agentscited by 35
  28. 2022Do better ImageNet classifiers assess perceptual similarity better?cited by 34
  29. 2018Humans can decipher adversarial imagescited by 31
  30. 2019Disentangling neural mechanisms for perceptual groupingcited by 28
  31. 2018Task-Driven Convolutional Recurrent Models of the Visual Systemcited by 27
  32. 2020Recurrent neural circuits for contour detectioncited by 23
  33. 2021Capturing the objects of vision with neural networkscited by 21
  34. 2018Deep Convolutional Neural Networks in the Face of Caricature: Identity and Image Revealedcited by 16
  35. 2018Distinct patterns of syntactic agreement errors in recurrent networks and humanscited by 13
  36. 2021Understanding the computational demands underlying visual reasoningcited by 13
  37. 2017Understanding trained CNNs by indexing neuron selectivitycited by 12
  38. 2017Fixing a Broken ELBOcited by 12

50 most cited of 61 All 61 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 13; 2025: 14; 2026: 12.

40 papers.

Sort:

By area:

  1. 2026There Will Be a Scientific Theory of Deep Learningcited by 29
  2. 2024Human-like object concept representations emerge naturally in multimodal large language modelscited by 25
  3. 2025We Can't Understand AI Using our Existing Vocabularycited by 25
  4. 2024The 3D-PC: a benchmark for visual perspective taking in humans and machinescited by 16
  5. 2025Brain-Model Evaluations Need the NeuroAI Turing Testcited by 13
  6. 2025Do computer vision foundation models learn the low-level characteristics of the human visual system?cited by 12
  7. 2025EncQA: Benchmarking Vision-Language Models on Visual Encodings for Chartscited by 12
  8. 2024Poisson Variational Autoencodercited by 11
  9. 2024Position: An Inner Interpretability Framework for AI Inspired by Lessons from Cognitive Neurosciencecited by 11
  10. 2025Better artificial intelligence does not mean better models of biologycited by 10
  11. 2024Visualization Literacy of Multimodal Large Language Models: A Comparative Studycited by 9
  12. 2024MindSet: Vision. A toolbox for testing DNNs on key psychological experimentscited by 8
28 more
  1. 2025Contour Integration Underlies Human-Like Visioncited by 6
  2. 2025Adopting a human developmental visual diet yields robust, shape-based AI visioncited by 5
  3. 2024Human-Like Geometric Abstraction in Large Pre-trained Neural Networkscited by 4
  4. 2024Computational Models to Study Language Processing in the Human Brain: A Surveycited by 4
  5. 2025Visual Language Models show widespread visual deficits on neuropsychological testscited by 3
  6. 2026The Lipreading Gap: Do VSR Models Perceive Visual Speech Like Human Lipreaders?cited by 3
  7. 2024Unveiling the Human-like Similarities of Automatic Facial Expression Recognition: An Empirical Exploration through Explainable AIcited by 2
  8. 2025Visual Image Reconstruction from Brain Activity via Latent Representationcited by 2
  9. 2023Layerwise complexity-matched learning yields an improved model of cortical area V2cited by 1
  10. 2024Visual Reasoning in Object-Centric Deep Neural Networks: A Comparative Cognition Approachcited by 1
  11. 2025Seeing Eye to AI? Applying Deep-Feature-Based Similarity Metrics to Information Visualizationcited by 1
  12. 2025Can Biologically Plausible Temporal Credit Assignment Rules Match BPTT for Neural Similarity? E-prop as an Examplecited by 1
  13. 2026Low-Pass Filtering Improves Behavioral Alignment of Vision Modelscited by 1
  14. 2026Multi-Level Bidirectional Biomimetic Learning for EEG-Based Visual Decodingcited by 1
  15. 2024Comparing supervised learning dynamics: Deep neural networks match human data efficiency but show a generalisation lagcited by 0
  16. 2024A theory of neural emulatorscited by 0
  17. 2024Parametric PerceptNet: A bio-inspired deep-net trained for Image Quality Assessmentcited by 0
  18. 2025TDSNNs: Competitive Topographic Deep Spiking Neural Networks for Visual Cortex Modelingcited by 0
  19. 2025A biological vision inspired framework for machine perception of abutting grating illusory contourscited by 0
  20. 2025Realist and Pluralist Conceptions of Intelligence and Their Implications on AI Researchcited by 0
  21. 2026Human-AI Divergence in Ego-centric Action Recognition under Spatial and Spatiotemporal Manipulationscited by 0
  22. 2026Non-identifiability of Explanations from Model Behavior in Deep Networks of Image Authenticity Judgmentscited by 0
  23. 2026Computational Lesions in Multilingual Language Models Separate Shared and Language-specific Brain Alignmentcited by 0
  24. 2026Not Too Generative, Not Too Discriminative: The Human Alignment Sweet Spotcited by 0
  25. 2026Updating the standard neuron model in artificial neural networkscited by 0
  26. 2026Modeling the Impact of Visual Brand Language on Attention, Object Recognition, and Memory Retrievalcited by 0
  27. 2026Which Attention Heads are like the Human Head? Not the Ones that Computecited by 0
  28. 2026Anthropomorphism in the age of Large Language Models: An overview of potential risks and mitigationscited by 0