5 papers
Winner-Take-All bottlenecks enforce disentangled symbolic representations in multi-task learning
Julian Gutheil, Simon Hitzginger, Robert Legenstein
Winner-take-all (WTA) networks constitute a central circuit motif in cortical networks of the brain. In addition, WTA-like activations are abundant in modern deep learning models i…
Advancing Spatio-Temporal Processing in Spiking Neural Networks through Adaptation
Maximilian Baronig, Romain Ferrand, Silvester Sabathiel +1
Implementations of spiking neural networks on neuromorphic hardware promise orders of magnitude less power consumption than their non-spiking counterparts. The standard neuron mode…
A Scalable Hybrid Training Approach for Recurrent Spiking Neural Networks
Maximilian Baronig, Yeganeh Bahariasl, Ozan Ãzdenizci +1
Recurrent spiking neural networks (RSNNs) can be implemented very efficiently in neuromorphic systems. Nevertheless, training of these models with powerful gradient-based learning…
Adversarially Robust Spiking Neural Networks with Sparse Connectivity
Mathias Schmolli, Maximilian Baronig, Robert Legenstein +1
Deployment of deep neural networks in resource-constrained embedded systems requires innovative algorithmic solutions to facilitate their energy and memory efficiency. To further e…
Privacy-Aware Lifelong Learning
Ozan Ãzdenizci, Elmar Rueckert, Robert Legenstein
Lifelong learning algorithms enable models to incrementally acquire new knowledge without forgetting previously learned information. Contrarily, the field of machine unlearning foc…