2,278 research outputs found
The color phi phenomenon: Not so special, after all?
No full textWe show how anomalous time reversal of stimuli and their associated responses can exist in very small connectionist models. These networks are built from dynamical toy model neurons which adhere to a minimal set of biologically plausible properties. The appearance of a “ghost” response, temporally and spatially located in between responses caused by actual stimuli, as in the phi phenomenon, is demonstrated in a similar small network, where it is caused by priming and long-distance feedforward paths. We then demonstrate that the color phi phenomenon can be present in an echo state network, a recurrent neural network, without explicitly training for the presence of the effect, such that it emerges as an artifact of the dynamical processing. Our results suggest that the color phi phenomenon might simply be a feature of the inherent dynamical and nonlinear sensory processing in the brain and in and of itself is not related to consciousness.SCOPUS: ar.jinfo:eu-repo/semantics/publishe
Reptricket. Förord till Lars Gustafsson: Mot noll
No full textIntroduction to a collection of philosophical essays by Swedish author Lars Gustafsson (b. 1936)
Author Functions in Lars Kepler\u27s The Hypnotist: An Analysis
No full textThis paper examines Foucault\u27s notion of the author function as it pertains to Lars Kepler\u27s bestselling 2011 crime thriller, The Hypnotist. Lars Kepler is the pseudonym of a Swedish husband-wife writing duo, making him the perfect subject for analysis centering on illusory notion of the author. This paper will answer these questions: Who is the true author of The Hypnotist? What factors influence the author function of this bestelling novel? And what can The Hypnotist phenomenon tell us about the relationships between authors and their readers? This paper will demonstrate that no literary works may be ascribed to an individual person, and that authors hold no privileged knowledge of the works they produce, because authors cease to be authors the moment pen is lifted from page
SupportHDC: Hyperdimensional Computing with Scalable Hypervector Sparsity
No full textThe authors thank Lars Keuninckx for useful discussions. This research received funding from the Flemish Government under the "Onderzoeksprogramma Artificiele Intelligentie (AI) Vlaanderen" programme and the European Union's ECSEL Joint Undertaking under grant agreement no 826655 - project TEMPO
Improving the Accuracy of Spiking Neural Networks for Radar Gesture Recognition Through Preprocessing
No full textThis work was supported in part by the Flanders Artificial Intelligence (AI) Research Program
ConvSNN: A surrogate gradient spiking neural framework for radar gesture recognition
No full textsponsorship: The authors thank Andre Bourdoux, Ilja Ocket, Federico Corradi and Lars Keuninckx for the discussions and guidance, and the Flanders AI research program for partially supporting this work. (Flanders AI research program)status: Publishe
Event Camera Data Classification Using Spiking Networks with Spike-Timing-Dependent Plasticity
No full textsponsorship: We would like to thank Dr. Lars Keuninckx for the helpful discussion. The research leading to these results has received funding from the Flemish Government (AI Research Program) and the European Union's ECSEL Joint Undertaking under grant agreement n degrees 826655 -project TEMPO. (Flemish Government (AI Research Program), European Union's ECSEL Joint Undertaking|826655)status: Publishe
Improving the Accuracy of Spiking Neural Networks for Radar Gesture Recognition Through Preprocessing
No full textEvent-based neural networks are currently being explored as efficient solutions for performing AI tasks at the extreme edge. To fully exploit their potential, event-based neural networks coupled to adequate preprocessing must be investigated. Within this context, we demonstrate a 4-b-weight spiking neural network (SNN) for radar gesture recognition, achieving a state-of-the-art 93% accuracy within only four processing time steps while using only one convolutional layer and two fully connected layers. This solution consumes very little energy and area if implemented in event-based hardware, which makes it suited for embedded extreme-edge applications. In addition, we demonstrate the importance of signal preprocessing for achieving this high recognition accuracy in SNNs compared to deep neural networks (DNNs) with the same network topology and training strategy. We show that efficient preprocessing prior to the neural network is drastically more important for SNNs compared to DNNs. We also demonstrate, for the first time, that the preprocessing parameters can affect SNNs and DNNs in antagonistic ways, prohibiting the generalization of conclusions drawn from DNN design to SNNs. We demonstrate our findings by comparing the gesture recognition accuracy achieved with our SNN to a DNN with the same architecture and similar training. Unlike previously proposed neural networks for radar processing, this work enables ultralow-power radar-based gesture recognition for extreme-edge devices.sponsorship: This work was supported in part by the Flanders Artificial Intelligence (AI) Research Program. (Flanders Artificial Intelligence (AI) Research Program)status: Publishe
- …
