Long short-term memory and learning-to-learn in networks of spiking neurons G Bellec, D Salaj, A Subramoney, R Legenstein, W Maass Advances in neural information processing systems 31, 2018 | 266 | 2018 |
A solution to the learning dilemma for recurrent networks of spiking neurons G Bellec, F Scherr, A Subramoney, E Hajek, D Salaj, R Legenstein, ... Nature communications 11 (1), 1-15, 2020 | 137 | 2020 |
Biologically inspired alternatives to backpropagation through time for learning in recurrent neural nets G Bellec, F Scherr, E Hajek, D Salaj, R Legenstein, W Maass arXiv preprint arXiv:1901.09049, 2019 | 68 | 2019 |
Advances in neural information processing systems G Bellec, D Salaj, A Subramoney, R Legenstein, W Maass, S Bengio, ... Curran, Red Hook, NY 31, 787-797, 2018 | 24 | 2018 |
A solution to the learning dilemma for recurrent networks of spiking neurons. bioRxiv G Bellec, F Scherr, A Subramoney, E Hajek, D Salaj, R Legenstein, ... 00000, 738385, 2019 | 10 | 2019 |
A solution to the learning dilemma for recurrent networks of spiking neurons. bioRxiv, 738385 G Bellec, F Scherr, A Subramoney, E Hajek, D Salaj, R Legenstein, ... | 7 | 2019 |
Spike-frequency adaptation provides a long short-term memory to networks of spiking neurons D Salaj, A Subramoney, C Kraišniković, G Bellec, R Legenstein, W Maass bioRxiv, 2020.05. 11.081513, 2020 | 6 | 2020 |
Spike frequency adaptation supports network computations on temporally dispersed information D Salaj, A Subramoney, C Kraisnikovic, G Bellec, R Legenstein, W Maass Elife 10, e65459, 2021 | 5 | 2021 |
Eligibility traces provide a data-inspired alternative to backpropagation through time G Bellec, F Scherr, E Hajek, D Salaj, A Subramoney, R Legenstein, ... | 5 | 2019 |
Biologically inspired alternatives to backpropagation through time for learning in recurrent neural nets. arXiv G Bellec, F Scherr, E Hajek, D Salaj, R Legenstein, W Maass arXiv preprint arXiv:1901.09049, 2019 | 5 | 2019 |
Long short-term memory and learning-to-learn in networks of spiking neurons. arXiv G Bellec, D Salaj, A Subramoney, R Legenstein, W Maass arXiv preprint arXiv:1803.09574, 2018 | 5 | 2018 |
Slow processes of neurons enable a biologically plausible approximation to policy gradient A Subramoney, G Bellec, F Scherr, A Subramoney, E Hajek, D Salaj, ... 33nd NeurIPS workshop, 2019 | 1 | 2019 |
Biologically inspired alternatives to backpropagation through time for learning in recurrent neural networks G Bellec, F Scherr, D Salaj, E Hajek, R Legenstein, W Maass | 1 | |
on STORE-RECALL task. D Salaj, A Subramoney, C Kraišnikovic, G Bellec, R Legenstein, W Maass | | 2021 |
Spike frequency adaptation supports network computations D Salaj, A Subramoney, C Kraišnikovic, G Bellec, R Legenstein, W Maass | | 2020 |
Spike-frequency adaptation contributes long short-term memory to networks of spiking neurons A Subramoney, C Kraisnikovic, D Salaj, GEF Bellec, R Legenstein, ... 2020 Bernstein Conference, 2020 | | 2020 |
Spike frequency adaptation supports network computations on temporally dispersed information Open Website D Salaj, A Subramoney, C Kraisnikovic, G Bellec, R Legenstein, W Maass | | |
Bio-Inspired Neuromorphic AI Methods Enables Privacy Respecting Security and Surveillance N Delilovic, D Salaj | | |
A solution to the learning dilemma for recurrentnetworks of spiking neurons Download PDF Open Website G Bellec, F Scherr, A Subramoney, E Hajek, D Salaj, R Legenstein, ... | | |
Long short-term memory and learning-to-learn in networks of spiking neurons Download PDF G Bellec, D Salaj, A Subramoney, R Legenstein, W Maass | | |