Darjan Salaj
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Darjan Salaj has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Anand Subramoney
Royal Holloway, University of London
2 shared publications - Guillaume Bellec
Institute for Theoretical Computer Science Graz University of Technology Austria
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 - Elias Hajek
TU Graz, Institute for Theoretical Computer Science
1 shared publication - Franz Scherr
TU Graz, Institute for Theoretical Computer Science
1 shared publication
Latest Publications
- Open Access
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. But in spite of extensive research, it has remained open how they can learn through synaptic plasticity to carry out complex network computations. We argue that two pieces of this puzzle were provided by experimental data from neuroscience. A new mathematical insight 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 new learning method – called e-prop – approaches the performance of BPTT (backpropagation through time), the best known method for training recurrent neural networks in machine learning. In addition, it suggests a method for powerful on-chip learning in novel energy-efficient spike-based hardware for AI.
Open 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. But in spite of extensive research, it has remained open how they can learn through synaptic plasticity to carry out complex network computations. We argue that two pieces of this puzzle were provided by experimental data from neuroscience. A new mathematical insight 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 new learning method – called e-prop – approaches the performance of BPTT (backpropagation through time), the best known method for training recurrent neural networks in machine learning. In addition, it suggests a method for powerful on-chip learning in novel energy-efficient spike-based hardware for AI.
- Open Access
Long short-term memory and learning-to-learn in networks of spiking neurons
Recurrent networks of spiking neurons (RSNNs) underlie the astounding computing and learning capabilities of the brain. But computing and learning capabilities of RSNN models have remained poor, at least in comparison with artificial neural networks (ANNs). We address two possible reasons for that. One is that RSNNs in the brain are not randomly connected or designed according to simple rules, and they do not start learning as a tabula rasa network. Rather, RSNNs in the brain were optimized for their tasks through evolution, development, and prior experience. Details of these optimization processes are largely unknown. But their functional contribution can be approximated through powerful optimization methods, such as backpropagation through time (BPTT). A second major mismatch between RSNNs in the brain and models is that the latter only show a small fraction of the dynamics of neurons and synapses in the brain. We include neurons in our RSNN model that reproduce one prominent dynamical process of biological neurons that takes place at the behaviourally relevant time scale of seconds: neuronal adaptation. We denote these networks as LSNNs because of their Long short-term memory. The inclusion of adapting neurons drastically increases the computing and learning capability of RSNNs if they are trained and configured by deep learning (BPTT combined with a rewiring algorithm that optimizes the network architecture). In fact, the computational performance of these RSNNs approaches for the first time that of LSTM networks. In addition RSNNs with adapting neurons can acquire abstract knowledge from prior learning in a Learning-to-Learn (L2L) scheme, and transfer that knowledge in order to learn new but related tasks from very few examples. We demonstrate this for supervised learning and reinforcement learning.
Open AccessLong short-term memory and learning-to-learn in networks of spiking neurons
Recurrent networks of spiking neurons (RSNNs) underlie the astounding computing and learning capabilities of the brain. But computing and learning capabilities of RSNN models have remained poor, at least in comparison with artificial neural networks (ANNs). We address two possible reasons for that. One is that RSNNs in the brain are not randomly connected or designed according to simple rules, and they do not start learning as a tabula rasa network. Rather, RSNNs in the brain were optimized for their tasks through evolution, development, and prior experience. Details of these optimization processes are largely unknown. But their functional contribution can be approximated through powerful optimization methods, such as backpropagation through time (BPTT). A second major mismatch between RSNNs in the brain and models is that the latter only show a small fraction of the dynamics of neurons and synapses in the brain. We include neurons in our RSNN model that reproduce one prominent dynamical process of biological neurons that takes place at the behaviourally relevant time scale of seconds: neuronal adaptation. We denote these networks as LSNNs because of their Long short-term memory. The inclusion of adapting neurons drastically increases the computing and learning capability of RSNNs if they are trained and configured by deep learning (BPTT combined with a rewiring algorithm that optimizes the network architecture). In fact, the computational performance of these RSNNs approaches for the first time that of LSTM networks. In addition RSNNs with adapting neurons can acquire abstract knowledge from prior learning in a Learning-to-Learn (L2L) scheme, and transfer that knowledge in order to learn new but related tasks from very few examples. We demonstrate this for supervised learning and reinforcement learning.