3 citations · 4 across the 7 of their papers we have counts for
7 papers
SpikingGamma: Surrogate-Gradient Free and Temporally Precise Online Training of Spiking Neural Networks with Smoothed Delays
Roel Koopman, Sebastian Otte, Sander Bohté
Neuromorphic hardware implementations of Spiking Neural Networks (SNNs) promise energy-efficient, low-latency AI through sparse, event-driven computation. Yet, training SNNs under…
The Resurrection of the ReLU
Coşku Can Horuz, Geoffrey Kasenbacher, Saya Higuchi +7
Modeling sophisticated activation functions within deep learning architectures has evolved into a distinct research direction. Functions such as GELU, SELU, and SiLU offer smooth g…
WARP-LCA: Efficient Convolutional Sparse Coding with Locally Competitive Algorithm
Geoffrey Kasenbacher, Felix Ehret, Gerrit Ecke +1
The locally competitive algorithm (LCA) can solve sparse coding problems across a wide range of use cases. Recently, convolution-based LCA approaches have been shown to be highly e…
Understanding the Convergence in Balanced Resonate-and-Fire Neurons
Saya Higuchi, Sander M. Bohte, Sebastian Otte
Resonate-and-Fire (RF) neurons are an interesting complementary model for integrator neurons in spiking neural networks (SNNs). Due to their resonating membrane dynamics they can e…
Flexible and Efficient Surrogate Gradient Modeling with Forward Gradient Injection
Sebastian Otte
Automatic differentiation is a key feature of present deep learning frameworks. Moreover, they typically provide various ways to specify custom gradients within the computation gra…
Balanced Resonate-and-Fire Neurons
Saya Higuchi, Sebastian Kairat, Sander M. Bohte +1
The resonate-and-fire (RF) neuron, introduced over two decades ago, is a simple, efficient, yet biologically plausible spiking neuron model, which can extract frequency patterns wi…
Representation Learning of Multivariate Time Series using Attention and Adversarial Training
Leon Scharwächter, Sebastian Otte
A critical factor in trustworthy machine learning is to develop robust representations of the training data. Only under this guarantee methods are legitimate to artificially genera…