Darjan Salaj

Darjan Salaj

Auto-generated profile, based on publicly available information

Darjan Salaj

Institute of Theoretical Computer Science, Graz University of Technology, Graz, Austria

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
17 July 2020 in Nature Communications
Verified
Journal Article
Open access
PDF file
GBGuillaume Bellec
Guillaume Bellec
FSFranz Scherr
Franz Scherr
ASAnand Subramoney
Anand Subramoney
EHElias Hajek
Elias Hajek
DSDarjan Salaj
Darjan Salaj
WMWolfgang Maass
Wolfgang Maass
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.

26 July 2021 in eLife
Verified
Journal Article
Open access
DSDarjan Salaj
Darjan Salaj
ASAnand Subramoney
Anand Subramoney
CKCeca Kraisnikovic
Ceca Kraisnikovic
GBGuillaume Bellec
Guillaume Bellec
RLRobert Legenstein
Robert Legenstein
WMWolfgang Maass
Wolfgang Maass
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.