Scientific Publications

@article{struckmeier2023autoencoding,

title = {Autoencoding slow representations for semi-supervised data-efficient regression},

author = {Oliver Struckmeier and Kshitij Tiwari and Ville Kyrki},

url = {https://link.springer.com/article/10.1007/s10994-022-06299-1},

doi = {10.1007/s10994-022-06299-1},

year  = {2023},

date = {2023-01-01},

urldate = {2023-01-01},

journal = {Machine Learning},

pages = {1--19},

publisher = {Springer},

abstract = {The slowness principle is a concept inspired by the visual cortex of the brain. It postulates that the underlying generative factors of a quickly varying sensory signal change on a different, slower time scale. By applying this principle to state-of-the-art unsupervised representation learning methods one can learn a latent embedding to perform supervised downstream regression tasks more data efficient. In this paper, we compare different approaches to unsupervised slow representation learning such as Lp

 norm based slowness regularization and the SlowVAE, and propose a new term based on Brownian motion used in our method, the S-VAE. We empirically evaluate these slowness regularization terms with respect to their downstream task performance and data efficiency in state estimation and behavioral cloning tasks. We find that slow representations show great performance improvements in settings where only sparse labeled training data is available. Furthermore, we present a theoretical and empirical comparison of the discussed slowness regularization terms. Finally, we discuss how the Fréchet Inception Distance (FID), commonly used to determine the generative capabilities of GANs, can predict the performance of trained models in supervised downstream tasks.},

keywords = {Bioinspired},

pubstate = {published},

tppubtype = {article}

}

@article{tiwari2021define,

title = {DeFINE: Delayed feedback-based immersive navigation environment for studying goal-directed human navigation},

author = {Kshitij Tiwari and Ville Kyrki and Allen Cheung and Naohide Yamamoto},

url = {https://link.springer.com/article/10.3758/s13428-021-01586-6},

doi = {10.3758/s13428-021-01586-6},

year  = {2021},

date = {2021-01-01},

urldate = {2021-01-01},

journal = {Behavior Research Methods},

volume = {53},

number = {6},

pages = {2668--2688},

publisher = {Springer},

abstract = {With the advent of consumer-grade products for presenting an immersive virtual environment (VE), there is a growing interest in utilizing VEs for testing human navigation behavior. However, preparing a VE still requires a high level of technical expertise in computer graphics and virtual reality, posing a significant hurdle to embracing the emerging technology. To address this issue, this paper presents Delayed Feedback-based Immersive Navigation Environment (DeFINE), a framework that allows for easy creation and administration of navigation tasks within customizable VEs via intuitive graphical user interfaces and simple settings files. Importantly, DeFINE has a built-in capability to provide performance feedback to participants during an experiment, a feature that is critically missing in other similar frameworks. To show the usability of DeFINE from both experimentalists’ and participants’ perspectives, a demonstration was made in which participants navigated to a hidden goal location with feedback that differentially weighted speed and accuracy of their responses. In addition, the participants evaluated DeFINE in terms of its ease of use, required workload, and proneness to induce cybersickness. The demonstration exemplified typical experimental manipulations DeFINE accommodates and what types of data it can collect for characterizing participants’ task performance. With its out-of-the-box functionality and potential customizability due to open-source licensing, DeFINE makes VEs more accessible to many researchers.



},

keywords = {Bioinspired},

pubstate = {published},

tppubtype = {article}

}

@article{pearson2021multimodal,

title = {Multimodal Representation Learning for Place Recognition Using Deep Hebbian Predictive Coding},

author = {Martin J Pearson and Shirin Dora and Oliver Struckmeier and Thomas C Knowles and Ben Mitchinson and Kshitij Tiwari and Ville Kyrki and Sander Bohte and Cyriel MA Pennartz},

url = {https://www.frontiersin.org/articles/10.3389/frobt.2021.732023/full},

doi = {10.3389/frobt.2021.732023},

year  = {2021},

date = {2021-01-01},

urldate = {2021-01-01},

journal = {Frontiers in Robotics and AI},

volume = {8},

publisher = {Frontiers Media SA},

abstract = {Recognising familiar places is a competence required in many engineering applications that interact with the real world such as robot navigation. Combining information from different sensory sources promotes robustness and accuracy of place recognition. However, mismatch in data registration, dimensionality, and timing between modalities remain challenging problems in multisensory place recognition. Spurious data generated by sensor drop-out in multisensory environments is particularly problematic and often resolved through adhoc and brittle solutions. An effective approach to these problems is demonstrated by animals as they gracefully move through the world. Therefore, we take a neuro-ethological approach by adopting self-supervised representation learning based on a neuroscientific model of visual cortex known as predictive coding. We demonstrate how this parsimonious network algorithm which is trained using a local learning rule can be extended to combine visual and tactile sensory cues from a biomimetic robot as it naturally explores a visually aliased environment. The place recognition performance obtained using joint latent representations generated by the network is significantly better than contemporary representation learning techniques. Further, we see evidence of improved robustness at place recognition in face of unimodal sensor drop-out. The proposed multimodal deep predictive coding algorithm presented is also linearly extensible to accommodate more than two sensory modalities, thereby providing an intriguing example of the value of neuro-biologically plausible representation learning for multimodal navigation.},

keywords = {Bioinspired, Touch Sensing},

pubstate = {published},

tppubtype = {article}

}