Darjan Salaj
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Darjan Salaj has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Anand Subramoney
Royal Holloway, University of London
2 shared publications - Robert Legenstein
Institute of Machine Learning and Neural Computation, Graz University of Technology, Graz, Austria
2 shared publications - Wolfgang Maass
Institute of Machine Learning and Neural Computation, Graz University of Technology, Graz, Austria
2 shared publications - Ceca Kraišniković
Graz University of Technology
1 shared publication Elias Hajek
Institute of Theoretical Computer Science, Graz University of Technology, Inffeldgasse 16b, Graz, Austria
1 shared publication- Franz Scherr
Institute of Theoretical Computer Science, Graz University of Technology, Graz, Austria
1 shared publication
Latest Publications
- Open Access
- 26 July 2021
- Published by eLife Sciences Publications, Ltd in eLife
- Vol. 10
Spike frequency adaptation supports network computations on temporally dispersed information
For solving tasks such as recognizing a song, answering a question, or inverting a sequence of symbols, cortical microcircuits need to integrate and manipulate information that was dispersed over time during the preceding seconds. Creating biologically realistic models for the underlying computations, especially with spiking neurons and for behaviorally relevant integration time spans, is notoriously difficult. We examine the role of spike frequency adaptation in such computations and find that it has a surprisingly large impact. The inclusion of this well-known property of a substantial fraction of neurons in the neocortex – especially in higher areas of the human neocortex – moves the performance of spiking neural network models for computations on network inputs that are temporally dispersed from a fairly low level up to the performance level of the human brain.
- 26 July 2021
- Published by eLife Sciences Publications, Ltd in eLife
- Vol. 10
Open AccessSpike frequency adaptation supports network computations on temporally dispersed information
For solving tasks such as recognizing a song, answering a question, or inverting a sequence of symbols, cortical microcircuits need to integrate and manipulate information that was dispersed over time during the preceding seconds. Creating biologically realistic models for the underlying computations, especially with spiking neurons and for behaviorally relevant integration time spans, is notoriously difficult. We examine the role of spike frequency adaptation in such computations and find that it has a surprisingly large impact. The inclusion of this well-known property of a substantial fraction of neurons in the neocortex – especially in higher areas of the human neocortex – moves the performance of spiking neural network models for computations on network inputs that are temporally dispersed from a fairly low level up to the performance level of the human brain.
- Top Cited PapersOpen Access
- 17 July 2020
- Published by Springer Nature in Nature Communications
- Vol. 11 (1) , 1-15
A solution to the learning dilemma for recurrent networks of spiking neurons
Recurrently connected networks of spiking neurons underlie the astounding information processing capabilities of the brain. Yet in spite of extensive research, how they can learn through synaptic plasticity to carry out complex network computations remains unclear. We argue that two pieces of this puzzle were provided by experimental data from neuroscience. A mathematical result tells us how these pieces need to be combined to enable biologically plausible online network learning through gradient descent, in particular deep reinforcement learning. This learning method–called e-prop–approaches the performance of backpropagation through time (BPTT), the best-known method for training recurrent neural networks in machine learning. In addition, it suggests a method for powerful on-chip learning in energy-efficient spike-based hardware for artificial intelligence.
- 17 July 2020
- Published by Springer Nature in Nature Communications
- Vol. 11 (1) , 1-15
Top Cited PapersOpen AccessA solution to the learning dilemma for recurrent networks of spiking neurons
Recurrently connected networks of spiking neurons underlie the astounding information processing capabilities of the brain. Yet in spite of extensive research, how they can learn through synaptic plasticity to carry out complex network computations remains unclear. We argue that two pieces of this puzzle were provided by experimental data from neuroscience. A mathematical result tells us how these pieces need to be combined to enable biologically plausible online network learning through gradient descent, in particular deep reinforcement learning. This learning method–called e-prop–approaches the performance of backpropagation through time (BPTT), the best-known method for training recurrent neural networks in machine learning. In addition, it suggests a method for powerful on-chip learning in energy-efficient spike-based hardware for artificial intelligence.