Michael Hersche

Orcid: 0000-0003-3065-7639

According to our database1, Michael Hersche authored at least 35 papers between 2018 and 2024.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2024
On the Expressiveness and Length Generalization of Selective State-Space Models on Regular Languages.
CoRR, 2024

Towards Learning to Reason: Comparing LLMs with Neuro-Symbolic on Arithmetic Relations in Abstract Reasoning.
CoRR, 2024

On the Role of Noise in Factorizers for Disentangling Distributed Representations.
CoRR, 2024

Probabilistic Abduction for Visual Abstract Reasoning via Learning Rules in Vector-symbolic Architectures.
CoRR, 2024

Terminating Differentiable Tree Experts.
Proceedings of the Neural-Symbolic Learning and Reasoning - 18th International Conference, 2024

Towards Learning Abductive Reasoning Using VSA Distributed Representations.
Proceedings of the Neural-Symbolic Learning and Reasoning - 18th International Conference, 2024

12 mJ Per Class On-Device Online Few-Shot Class-Incremental Learning.
Proceedings of the Design, Automation & Test in Europe Conference & Exhibition, 2024

Zero-Shot Classification Using Hyperdimensional Computing.
Proceedings of the Design, Automation & Test in Europe Conference & Exhibition, 2024

2023
A neuro-vector-symbolic architecture for solving Raven's progressive matrices.
Nat. Mac. Intell., April, 2023

Raw data related to In-memory factorization of holographic perceptual representations.
Dataset, February, 2023

Few-Shot Continual Learning Based on Vector Symbolic Architectures.
Proceedings of the Compendium of Neurosymbolic Artificial Intelligence, 2023

Neuro-vector-symbolic architectures: Exploring computation in superposition for perception, reasoning, and combinatorial search.
PhD thesis, 2023

TCNCA: Temporal Convolution Network with Chunked Attention for Scalable Sequence Processing.
CoRR, 2023

Factorizers for Distributed Sparse Block Codes.
CoRR, 2023

MIMONets: Multiple-Input-Multiple-Output Neural Networks Exploiting Computation in Superposition.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Solving Raven's Progressive Matrices via a Neuro-vector-symbolic Architecture.
Proceedings of the 17th International Workshop on Neural-Symbolic Learning and Reasoning, 2023

Decoding Superpositions of Bound Symbols Represented by Distributed Representations.
Proceedings of the 17th International Workshop on Neural-Symbolic Learning and Reasoning, 2023

VSA-based Positional Encoding Can Replace Recurrent Networks in Emergent Symbol Binding.
Proceedings of the 17th International Workshop on Neural-Symbolic Learning and Reasoning, 2023

2022
In-memory factorization of holographic perceptual representations.
CoRR, 2022

In-memory Realization of In-situ Few-shot Continual Learning with a Dynamically Evolving Explicit Memory.
Proceedings of the 48th IEEE European Solid State Circuits Conference, 2022

Constrained Few-shot Class-incremental Learning.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

2021
Energy Efficient In-Memory Hyperdimensional Encoding for Spatio-Temporal Signal Processing.
IEEE Trans. Circuits Syst. II Express Briefs, 2021

Near-channel classifier: symbiotic communication and classification in high-dimensional space.
Brain Informatics, 2021

Mixed-Precision Quantization and Parallel Implementation of Multispectral Riemannian Classification for Brain-Machine Interfaces.
Proceedings of the IEEE International Symposium on Circuits and Systems, 2021

ECG-TCN: Wearable Cardiac Arrhythmia Detection with a Temporal Convolutional Network.
Proceedings of the 3rd IEEE International Conference on Artificial Intelligence Circuits and Systems, 2021

2020
Binarization Methods for Motor-Imagery Brain-Computer Interface Classification.
IEEE J. Emerg. Sel. Topics Circuits Syst., 2020

EEG-TCNet: An Accurate Temporal Convolutional Network for Embedded Motor-Imagery Brain-Machine Interfaces.
Proceedings of the 2020 IEEE International Conference on Systems, Man, and Cybernetics, 2020

Q-EEGNet: an Energy-Efficient 8-bit Quantized Parallel EEGNet Implementation for Edge Motor-Imagery Brain-Machine Interfaces.
Proceedings of the IEEE International Conference on Smart Computing, 2020

An Accurate EEGNet-based Motor-Imagery Brain-Computer Interface for Low-Power Edge Computing.
Proceedings of the 2020 IEEE International Symposium on Medical Measurements and Applications, 2020

Integrating event-based dynamic vision sensors with sparse hyperdimensional computing: a low-power accelerator with online learning capability.
Proceedings of the ISLPED '20: ACM/IEEE International Symposium on Low Power Electronics and Design, 2020

Compressing Subject-specific Brain-Computer Interface Models into One Model by Superposition in Hyperdimensional Space.
Proceedings of the 2020 Design, Automation & Test in Europe Conference & Exhibition, 2020

Evolvable Hyperdimensional Computing: Unsupervised Regeneration of Associative Memory to Recover Faulty Components.
Proceedings of the 2nd IEEE International Conference on Artificial Intelligence Circuits and Systems, 2020

Binary Models for Motor-Imagery Brain-Computer Interfaces: Sparse Random Projection and Binarized SVM.
Proceedings of the 2nd IEEE International Conference on Artificial Intelligence Circuits and Systems, 2020

2018
Exploring Embedding Methods in Binary Hyperdimensional Computing: A Case Study for Motor-Imagery based Brain-Computer Interfaces.
CoRR, 2018

Fast and Accurate Multiclass Inference for MI-BCIs Using Large Multiscale Temporal and Spectral Features.
Proceedings of the 26th European Signal Processing Conference, 2018


  Loading...