Andreas Knoblauch
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Andreas Knoblauch has a total of 21 co-authors. Here are the top co-authors by number of shared publications:
Edgar Körner
Honda Research Institute Europe GmbH
4 shared publicationsFriedrich T. Sommer
Redwood Center for Theoretical Neuroscience, University of California at Berkeley Berkeley, CA, USA
3 shared publicationsGünther Palm
Ulm University
3 shared publicationsUrsula Körner
Honda Research Institute Europe GmbH
3 shared publicationsMarc-Oliver Gewaltig
The Blue Brain Project, Ecole Polytechnique Federale de Lausanne Lausanne, Switzerland
2 shared publications- Anders Lansner
KTH Royal Institute of Technology
1 shared publication
Latest Publications
- Open Access
- 31 July 2026
- Published by Springer Nature in Cognitive Computation
- Vol. 18 (1) , 94
Benchmarking Local Hebbian Learning Rules for Memory Storage and Prototype Extraction
Associative memory or content-addressable memory is an important component function in computer science and information processing, and at the same time a key concept in cognitive and computational brain science. Many different neural network architectures and learning rules have been proposed to model the brain’s associative memory while investigating key component functions like figure-ground segmentation, perceptual reconstruction and rivalry. A less investigated but equally important capability of associative memory is prototype extraction where the training set comprises distorted prototype instances and the task is to recall the correct generating prototype given a new distorted instance. In this paper, we benchmark the associative memory function of seven different Hebbian learning rules employed in non-modular and modular recurrent networks with winner-take-all dynamics operating on moderately sparse binary patterns. We measure pattern storage and weight information capacity, prototype extraction capabilities, and sensitivity to correlations in data. The original additive Hebb rule comes out with worst capacity, covariance learning proves to be robust but with moderate capacity, and the Bayesian-Hebbian learning rules show highest capacity in almost all conditions tested.
- 31 July 2026
- Published by Springer Nature in Cognitive Computation
- Vol. 18 (1) , 94
Open AccessBenchmarking Local Hebbian Learning Rules for Memory Storage and Prototype Extraction
Associative memory or content-addressable memory is an important component function in computer science and information processing, and at the same time a key concept in cognitive and computational brain science. Many different neural network architectures and learning rules have been proposed to model the brain’s associative memory while investigating key component functions like figure-ground segmentation, perceptual reconstruction and rivalry. A less investigated but equally important capability of associative memory is prototype extraction where the training set comprises distorted prototype instances and the task is to recall the correct generating prototype given a new distorted instance. In this paper, we benchmark the associative memory function of seven different Hebbian learning rules employed in non-modular and modular recurrent networks with winner-take-all dynamics operating on moderately sparse binary patterns. We measure pattern storage and weight information capacity, prototype extraction capabilities, and sensitivity to correlations in data. The original additive Hebb rule comes out with worst capacity, covariance learning proves to be robust but with moderate capacity, and the Bayesian-Hebbian learning rules show highest capacity in almost all conditions tested.
- Open Access
- 3 March 2025
- Published by Center for Open Science in PsyArXiv
Face Processing in Humans and DCNNs: Comparing the Reliance on Holistic and Local Feature-Based Information
It is intensively debated whether Deep Convolutional Neural Networks (DCNNs) constitute appropriate models for human vision. Here, we investigated whether DCNNs show a typical characteristic of human face perception, namely holistic processing. In Experiment 1, we compared unfamiliar face matching performance between a DCNN trained on face recognition and N = 32 human participants for different types of face images: Normal faces (with intact holistic and local feature-based information), Mooney faces (with intact holistic and degraded local feature-based information), and scrambled faces (with intact local feature-based information and degraded holistic information). The DCNN showed significantly larger performance decrements for both Mooney and scrambled faces than human participants. In Experiment 2, we trained three DCNN architectures on face recognition, one with unrestricted field size and two with field sizes restricted to approximately 1/9 and 1/16 of the input image, respectively. Subsequently, we compared unfamiliar face matching performance between these DCNNs and N = 36 human participants who viewed face images either in an unrestricted fashion or through a movable spotlight- like viewing aperture covering approximately 1/9 or 1/16 of the face images. While human face matching accuracy was substantially impaired by restricting the visual input with apertures, DCNN performance was not affected by restriction of the receptive field size. These results suggest that (a) DCNNs are able to achieve high face matching accuracy without using holistic information (b) the reliance of holistic information in DCNNs depends on the specific optimization conditions under which models are trained.
- 3 March 2025
- Published by Center for Open Science in PsyArXiv
Open AccessFace Processing in Humans and DCNNs: Comparing the Reliance on Holistic and Local Feature-Based Information
It is intensively debated whether Deep Convolutional Neural Networks (DCNNs) constitute appropriate models for human vision. Here, we investigated whether DCNNs show a typical characteristic of human face perception, namely holistic processing. In Experiment 1, we compared unfamiliar face matching performance between a DCNN trained on face recognition and N = 32 human participants for different types of face images: Normal faces (with intact holistic and local feature-based information), Mooney faces (with intact holistic and degraded local feature-based information), and scrambled faces (with intact local feature-based information and degraded holistic information). The DCNN showed significantly larger performance decrements for both Mooney and scrambled faces than human participants. In Experiment 2, we trained three DCNN architectures on face recognition, one with unrestricted field size and two with field sizes restricted to approximately 1/9 and 1/16 of the input image, respectively. Subsequently, we compared unfamiliar face matching performance between these DCNNs and N = 36 human participants who viewed face images either in an unrestricted fashion or through a movable spotlight- like viewing aperture covering approximately 1/9 or 1/16 of the face images. While human face matching accuracy was substantially impaired by restricting the visual input with apertures, DCNN performance was not affected by restriction of the receptive field size. These results suggest that (a) DCNNs are able to achieve high face matching accuracy without using holistic information (b) the reliance of holistic information in DCNNs depends on the specific optimization conditions under which models are trained.
- Open Access
Neural auto-association with optimal Bayesian learning
Neural associative memories are single layer perceptrons with fast synaptic learning typically storing discrete associations between pairs of neural activity patterns. Previous works have analyzed the optimal networks under naive Bayes assumptions of independent pattern components and heteroassociation, where the task is to learn associations from input to output patterns. Here I study the optimal Bayesian associative network for auto-association where input and output layers are identical. In particular, I compare performance to different variants of approximate Bayesian learning rules, like the BCPNN (Bayesian Confidence Propagation Neural Network), and try to explain why sometimes the suboptimal learning rules achieve higher storage capacity than the (theoretically) optimal model. It turns out that performance can depend on subtle dependencies of input components violating the ``naive Bayes'' assumptions. This includes patterns with constant number of active units, iterative retrieval where patterns are repeatedly propagated through recurrent networks, and winners-take-all activation of the most probable units. Performance of all learning rules can improve significantly if they include a novel adaptive mechanism to estimate noise in iterative retrieval steps (ANE). The overall maximum storage capacity is achieved again by the Bayesian learning rule with ANE.
Open AccessNeural auto-association with optimal Bayesian learning
Neural associative memories are single layer perceptrons with fast synaptic learning typically storing discrete associations between pairs of neural activity patterns. Previous works have analyzed the optimal networks under naive Bayes assumptions of independent pattern components and heteroassociation, where the task is to learn associations from input to output patterns. Here I study the optimal Bayesian associative network for auto-association where input and output layers are identical. In particular, I compare performance to different variants of approximate Bayesian learning rules, like the BCPNN (Bayesian Confidence Propagation Neural Network), and try to explain why sometimes the suboptimal learning rules achieve higher storage capacity than the (theoretically) optimal model. It turns out that performance can depend on subtle dependencies of input components violating the ``naive Bayes'' assumptions. This includes patterns with constant number of active units, iterative retrieval where patterns are repeatedly propagated through recurrent networks, and winners-take-all activation of the most probable units. Performance of all learning rules can improve significantly if they include a novel adaptive mechanism to estimate noise in iterative retrieval steps (ANE). The overall maximum storage capacity is achieved again by the Bayesian learning rule with ANE.
- 19 December 2024
- Published by Springer Nature
- p. 97-121
Rationale Funktionen und Stetigkeit
- 19 December 2024
- Published by Springer Nature
- p. 377-425
Kombinatorik und Wahrscheinlichkeitsrechnung
- 19 December 2024
- Published by Springer Nature
- p. 79-95
Grenzwerte von Folgen und Reihen
- 19 December 2024
- Published by Springer Nature
- p. 167-194
Die komplexe Exponentialfunktion und die trigonometrischen Funktionen
- 19 December 2024
- Published by Springer Nature
- p. 167-194
Die komplexe Exponentialfunktion und die trigonometrischen Funktionen
- 19 December 2024
- Published by Springer Nature
- p. 123-147
Differentialrechnung
- 19 December 2024
- Published by Springer Nature
- p. 251-325
Fortgeschrittene Methoden der linearen Algebra
- 19 December 2024
- Published by Springer Nature
- p. 251-325
Fortgeschrittene Methoden der linearen Algebra
- 19 December 2024
- Published by Springer Nature
- p. 1-43
Mathematische und logische Grundlagen