Challenges for cognitive decoding using deep learning methods
Not on the map. Why?
Abstract (arXiv)
In cognitive decoding, researchers aim to characterize a brain region's representations by identifying the cognitive states (e.g., accepting/rejecting a gamble) that can be identified from the region's activity. Deep learning (DL) methods are highly promising for cognitive decoding, with their unmatched ability to learn versatile representations of complex data. Yet, their widespread application in cognitive decoding is hindered by their general lack of interpretability as well as difficulties in applying them to small datasets and in ensuring their reproducibility and robustness. We propose to approach these challenges by leveraging recent advances in explainable artificial intelligence and transfer learning, while also providing specific recommendations on how to improve the reproducibility and robustness of DL modeling results.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 88 of its 156 references that are in the map. First posted on arXiv 16 Aug 2021.
Builds on
88 of 156 references.
References · 88
- 2017Attention Is All You Needcited by 60,361
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
- 2020Language Models are Few-Shot Learnerscited by 32,419
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
- 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
- 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
- 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
- 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
- 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
- 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
- 2017Axiomatic Attribution for Deep Networkscited by 3,384
38 more
- 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,884
- 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,877
- 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,371
- 2013Visualizing and Understanding Convolutional Networkscited by 2,290
- 2020Shortcut Learning in Deep Neural Networkscited by 1,969
- 2020The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalizationcited by 1,850
- 2015A large annotated corpus for learning natural language inferencecited by 1,847
- 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,628
- 2019Do ImageNet Classifiers Generalize to ImageNet?cited by 1,515
- 2016Neural Architecture Search with Reinforcement Learningcited by 1,499
- 2017Learning Important Features Through Propagating Activation Differencescited by 1,458
- 2015Show, Attend and Tell: Neural Image Caption Generation with Visual Attentioncited by 1,423
- 2017Towards A Rigorous Science of Interpretable Machine Learningcited by 1,416
- 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,380
- 2020WILDS: A Benchmark of in-the-Wild Distribution Shiftscited by 1,375
- 2017Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)cited by 1,319
- 2019Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalizationcited by 1,247
- 2014How transferable are features in deep neural networks?cited by 1,225
- 2018Sanity Checks for Saliency Mapscited by 1,156
- 2017SmoothGrad: removing noise by adding noisecited by 1,109
- 2015Effective Approaches to Attention-based Neural Machine Translationcited by 1,026
- 2014Striving for Simplicity: The All Convolutional Netcited by 990
- 2019Attention is not Explanationcited by 929
- 2017Revisiting Unreasonable Effectiveness of Data in Deep Learning Eracited by 919
- 2019AugMix: A Simple Data Processing Method to Improve Robustness and Uncertaintycited by 901
- 2019Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inferencecited by 876
- 2018A Convergence Theory for Deep Learning via Over-Parameterizationcited by 787
- 2019Big Transfer (BiT): General Visual Representation Learningcited by 769
- 2017Deep Reinforcement Learning that Matterscited by 754
- 2020Self-supervised Learning: Generative or Contrastivecited by 694
- 2017Interpretable Explanations of Black Boxes by Meaningful Perturbationcited by 612
- 2020Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?cited by 599
- 2018Do Better ImageNet Models Transfer Better?cited by 565
- 2020Captum: A unified and generic model interpretability library for PyTorchcited by 547
- 2018Towards Robust Interpretability with Self-Explaining Neural Networkscited by 505
- 2021Dynabench: Rethinking Benchmarking in NLPcited by 459
- 2015Evaluating the visualization of what a Deep Neural Network has learnedcited by 419
- 2019Is Attention Interpretable?cited by 389
50 most cited of 88 All 88 (JSON)
Built on by
Citing papers per year: 2021: 1; 2022: 2.
3 papers.