CogXAI

Cognitive neuroscience inspired techniques for eXplainable AI
(BMBF, 2019-2023)

The CogXAI project aimed to improve the explainability and transparency of deep neural networks (DNNs) by transferring methods and insights from cognitive neuroscience into AI research. The project pursued two complementary goals: the creation of post‑hoc explanation methods inspired by cognitive neuroscience, and the design of inherently interpretable neural‑network architectures. The first goal led to the introduction of Neuron Activation Profiles (NAPs). A NAP records how a network responds to distinct groups of inputs, allowing researchers to compare activation patterns across classes or conditions. Because a NAP aggregates responses over many examples, it provides a global explanation that does not rely on visualisation of individual inputs. The project also developed a visualisation technique for these profiles, inspired by brain‑activity maps. By re‑ordering neurons according to similarity of activation, the method produces topographic activation maps that display the internal state of a network in a spatially organised manner, facilitating intuitive interpretation of hidden layers.

The second goal involved translating principles from predictive coding and active inference into neural‑network design. Our team produced predictive‑coding KNNs that employ exact error‑backpropagation without requiring a global error signal. In deeper variants, the architecture enforces a strictly local information flow, so that each layer can be inspected independently. These designs enable a new form of interpretability: local error signals and layer‑wise activations can be examined without reference to the entire network. In addition, the project explored active‑learning and planning models that adaptively adjust their internal representations during inference, further aligning network behaviour with cognitive processes.

In summary, CogXAI advanced the explainability of deep neural networks by combining cognitive‑neuroscience‑inspired analysis tools with novel, locally interpretable architectures. Beyond fundamental research, the project maintained a strong practical focus through collaborations with associated industry partners in two high-impact domains: speech assistance systems (Fraunhofer IIS) and autonomous driving (Motor Ai GmbH).

final project report

website of the funding initiative

Associated Project Partners

References

2025

  1. Relation of Activity and Confidence When Training Deep Neural Networks
    Valerie Krug, Christopher Olson, and Sebastian Stober
    In Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2025
  2. Investigating Inclusivity of Whisper for Dysfluent Speech
    Evelyn Starzew, Suhita Ghosh, and Valerie Krug
    In 12th edition of the Disfluency in Spontaneous Speech Workshop (DiSS 2025), Sep 2025
  3. Intersectional Bias Quantification in Facial Image Processing with Pre-Trained ImageNet Classifiers
    Valerie Krug, Florian Röhrbein, and Sebastian Stober
    In 2025 International Joint Conference on Neural Networks (IJCNN), Jun 2025
  4. Assessing Intersectional Bias in Representations of Pre-Trained Image Recognition Models
    Valerie Krug and Sebastian Stober
    arXiv, 2025

2024

  1. Exploration of Interpretability Techniques for Deep COVID-19 Classification Using Chest X-ray Images
    Soumick Chatterjee, Fatima Saad, Chompunuch Sarasaen, Suhita Ghosh, Valerie Krug, Rupali Khatun, Rahul Mishra, Nirja Desai, Petia Radeva, Georg Rose, Sebastian Stober, Oliver Speck, and Andreas Nürnberger
    Journal of Imaging, Feb 2024

2023

  1. Visualizing Deep Neural Networks with Topographic Activation Maps
    Valerie Krug, Raihan Kabir Ratul, Christopher Olson, and Sebastian Stober
    In HHAI 2023: Augmenting Human Intellect, Jun 2023
  2. Visualizing Bias in Activations of Deep Neural Networks as Topographic Maps
    Valerie Krug, Christopher Olson, and Sebastian Stober
    In Proceedings of the 1st Workshop on Fairness and Bias in AI (AEQUITAS 2023) co-located with 26th European Conference on Artificial Intelligence (ECAI 2023) Kraków, Poland, 2023
  3. Relation of Activity and Confidence when Training Deep Neural Networks
    Valerie Krug, Christopher Olson, and Sebastian Stober
    In Uncertainty meets Explainability, Workshop at ECML-PKDD 2023, Torino, Italy, 2023
  4. Visualizing Deep Neural Networks with Topographic Activation Maps
    Valerie Krug, Raihan Kabir Ratul, Christopher Olson, and Sebastian Stober
    In VeriLearn 2023: Workshop on Verifying Learning AI Systems, co-located with 26th European Conference on Artificial Intelligence (ECAI 2023) Kraków, Poland, 2023

2022

  1. Visualizing Deep Neural Networks with Topographic Activation Maps
    Andreas Krug, Raihan Kabir Ratul, and Sebastian Stober
    arXiv preprint arXiv:2204.03528, Apr 2022
  2. CogXAI ANNalyzer: Cognitive Neuroscience Inspired Techniques for eXplainable AI
    Maral Ebrahimzadeh, Valerie Krug, and Sebastian Stober
    In 23rd International Society for Music Information Retrieval Conference (ISMIR’22) - Late Breaking & Demo Papers, 2022
  3. Generalized Predictive Coding: Bayesian Inference in Static and Dynamic Models
    André Ofner, Beren Millidge, and Sebastian Stober
    In NeurIPS 2022 Workshop on Shared Visual Representations in Human & Machine Intelligence (SVRHM’22), 2022

2021

  1. Analyzing and Visualizing Deep Neural Networks for Speech Recognition with Saliency-Adjusted Neuron Activation Profiles
    Andreas Krug, Maral Ebrahimzadeh, Jost Alemann, Jens Johannsmeier, and Sebastian Stober
    Electronics, Jun 2021
  2. Predictive coding, precision and natural gradients
    Andre Ofner, Raihan Kabir Ratul, Suhita Ghosh, and Sebastian Stober
    arXiv preprint arXiv:2111.06942, Nov 2021
  3. PredProp: Bidirectional Stochastic Optimization with Precision Weighted Predictive Coding
    André Ofner and Sebastian Stober
    arXiv preprint arXiv:2111.08792, Nov 2021
  4. Differentiable Generalised Predictive Coding
    André Ofner and Sebastian Stober
    arXiv preprint arXiv:2112.0337, Dec 2021
  5. Hierarchical Predictive Coding and Interpretable Audio Analysis-Synthesis
    André Ofner, Johannes Schleiss, and Sebastian Stober
    In 15th International Symposium on Computer Music Multidisciplinary Research (CMMR’21), 2021

2020

  1. Gradient-Adjusted Neuron Activation Profiles for Comprehensive Introspection of Convolutional Speech Recognition Models
    Andreas Krug and Sebastian Stober
    arXiv preprint arXiv:2002.08125, 2020
  2. Balancing Active Inference and Active Learning with Deep Variational Predictive Coding for EEG
    André Ofner and Sebastian Stober
    In IEEE International Conference on Systems, Man, and Cybernetics (SMC 2020), 2020
  3. PredNet and Predictive Coding: A Critical Review
    Roshan Prakash Rane, Edit Szügyi, Vageesh Saxena, André Ofner, and Sebastian Stober
    In Proceedings of the 2020 International Conference on Multimedia Retrieval, Dublin, Ireland, 2020
  4. Modeling perception with hierarchical prediction: Auditory segmentation with deep predictive coding locates candidate evoked potentials in EEG
    André Ofner and Sebastian Stober
    In 21st International Society for Music Information Retrieval Conference (ISMIR’20), 2020

2019

  1. Visualizing Deep Neural Networks for Speech Recognition with Learned Topographic Filter Maps
    Andreas Krug and Sebastian Stober
    In Proceedings of the 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, 2019
  2. Siri visualisiert
    Andreas Krug and Sebastian Stober
    In Proceedings of the 2019 NaWik Symposium Karlsruhe, 2019
  3. Hybrid Variational Predictive Coding as a Bridge between Human and Artificial Cognition
    André Ofner and Sebastian Stober
    The 2019 Conference on Artificial Life, 2019
  4. Knowledge transfer in coupled predictive coding networks
    André Ofner and Sebastian Stober
    In Bernstein Conference 2019, 2019
  5. Predictive Coding Based Vision For Autonomous Cars
    Roshan Prakash Rane, André Ofner, Shreyas Gite, and Sebastian Stober
    In Computational Cognition 2019 Workshop, 2019

2018

  1. Neuron Activation Profiles for Interpreting Convolutional Speech Recognition Models
    Andreas Krug, René Knaebel, and Sebastian Stober
    In NeurIPS 2018 Interpretability and Robustness for Audio, Speech and Language Workshop (IRASL’18), 2018
  2. Introspection for Convolutional Automatic Speech Recognition
    Andreas Krug and Sebastian Stober
    In Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, 2018
  3. Hybrid Active Inference
    André Ofner and Sebastian Stober
    arXiv preprint arXiv:1810.02647, 2018
  4. Towards Bridging Human and Artificial Cognition: Hybrid Variational Predictive Coding of the Physical World, the Body and the Brain
    André Ofner and Sebastian Stober
    In NeurIPS 2018 Workshop on Modeling the Physical World, 2018

2017

  1. Transfer Learning for Speech Recognition on a Budget
    Julius Kunze, Louis Kirsch, Ilia Kurenkov, Andreas Krug, Jens Johannsmeier, and Sebastian Stober
    In 2n Workshop on Representation Learning for NLP at the Annual Meeting of the Association for Computational Linguistics (ACL’17), 2017
  2. Adaptation of the Event-Related Potential Technique for Analyzing Artificial Neural Nets
    Andreas Krug and Sebastian Stober
    In Conference on Cognitive Computational Neuroscience (CCN’17), 2017