21 papers · ranked by Valyu relevance
Wei Mark Fang
Spiking Neural Networks (SNNs) have attracted enormous research interest due to temporal information processing capability, low power consumption, and high biological plausibility. However, the formulation of efficient and high-performance learning algorithms for SNNs is still challenging. Most existing learning…
Chuang Liu, Yang Chen, Chang Seok Bang
Spiking neural networks (SNNs) have emerged as a promising paradigm for energy-efficient neuromorphic computing, particularly when processing asynchronous event streams from dynamic vision sensors (DVSs). However, SNNs often suffer from limited representational capacity and suboptimal feature recalibration compared to…
Cong Shi, Li Wang, Haoran Gao, Min Tian + 1 more
Spiking neural networks (SNNs) have garnered significant attention due to their computational patterns resembling biological neural networks. However, when it comes to deep SNNs, how to focus on critical information effectively and achieve a balanced feature transformation both temporally and spatially becomes a…
Amadeus Maes, Mauricio Barahona, Claudia Clopath
Learning to produce spatiotemporal sequences is a common task the brain has to solve. The same neural substrate may be used by the brain to produce different sequential behaviours. The way the brain learns and encodes such tasks remains unknown as current computational models do not typically use realistic…
Alireza Alemi, Christian K. Machens, Sophie Denève, Jean-Jacques Slotine
'Jean-Jacques Slotine'] Understanding how recurrent neural circuits can learn to implement dynamical systems is a fundamental challenge in neuroscience. The credit assignment problem, i.e. determining the local contribution of each synapse to the network's global output error, is a major obstacle in deriving…
Pau Vilimelis Aceituno, Matilde Tristany Farinha, Reinhard Loidl, Benjamin F. Grewe
'Benjamin F. Grewe'] A key driver of mammalian intelligence is the ability to represent incoming sensory information across multiple abstraction levels. For example, in the visual ventral stream, incoming signals are first represented as low-level edge filters and then transformed into high-level object…
Pau Vilimelis Aceituno, Matilde Tristany Farinha, Reinhard Loidl, Benjamin F. Grewe
A key driver of mammalian intelligence is the ability to represent incoming sensory information across multiple abstraction levels. For example, in the visual ventral stream, incoming signals are first represented as low-level edge filters and then transformed into high-level object representations. These same…
Dominik Thalmeier, Marvin Uhlmann, Hilbert J. Kappen, Raoul-Martin Memmesheimer + 1 more
'Raoul-Martin Memmesheimer' 'Matthias Bethge'] Providing the neurobiological basis of information processing in higher animals, spiking neural networks must be able to learn a variety of complicated computations, including the generation of appropriate, possibly delayed reactions to inputs and the self-sustained…
Chaofei Hong
Conventional modeling approaches have found limitations in matching the increasingly detailed neural network structures and dynamics recorded in experiments to the diverse brain functionalities. On another approach, studies have demonstrated to train spiking neural networks for simple functions using supervised…
Aditya Gilra, Wulfram Gerstner, Peter Latham
The brain needs to predict how the body reacts to motor commands, but how a network of spiking neurons can learn non-linear body dynamics using local, online and stable learning rules is unclear. Here, we present a supervised learning scheme for the feedforward and recurrent connections in a network of heterogeneous…
Christian Albers, Maren Westkott, Klaus Pawelzik
Precise spatio-temporal patterns of neuronal action potentials underly e.g. sensory representations and control of muscle activities. However, it is not known how the synaptic efficacies in the neuronal networks of the brain adapt such that they can reliably generate spikes at specific points in time. Existing…
Artur Luczak, Yoshimasa Kubo
The brain is using a learning algorithm which is yet to be discovered. Here we demonstrate that the ability of a neuron to predict its expected future activity may be an important missing component to understand learning in the brain. We show that comparing predicted activity with the actual activity can provide an…
Dominik Thalmeier, Marvin Uhlmann, Hilbert J. Kappen, Raoul-Martin Memmesheimer
'Raoul-Martin Memmesheimer'] Providing the neurobiological basis of information processing in higher animals, spiking neural networks must be able to learn a variety of complicated computations, including the generation of appropriate, possibly delayed reactions to inputs and the self-sustained generation of complex…
Owen Marschall, Cristina Savin
Despite the success of dynamical systems as accounts of circuit computation and observed behavior, our understanding of how dynamical systems evolve over learning is very limited. Here we develop a computational framework for extracting core dynamical systems features of recurrent circuits across learning and analyze…
Luca Saglietti, Federica Gerace, Alessandro Ingrosso, Carlo Baldassi + 1 more
'Riccardo Zecchina'] Stochastic neural networks are a prototypical computational device able to build a probabilistic representation of an ensemble of external stimuli. Building on the relationship between inference and learning, we derive a synaptic plasticity rule that relies only on delayed activity correlations…
Harsha Gurnani, Weixuan Liu, Bingni W. Brunton
Neural activity has been observed to lie on low-dimensional manifolds, constraining what new behaviors can be easily learned. We propose that beyond this geometric constraint, learning on fast timescales is limited by how neural activity can flow over time within these manifolds—i.e., by the system’s underlying…
Sophie Denève, Alireza Alemi, Ralph Bourdoukan
Understanding how the brain learns to compute functions reliably, efficiently and robustly with noisy spiking activity is a fundamental challenge in neuroscience. Most sensory and motor tasks can be described as dynamical systems and could presumably be learned by adjusting connection weights in a recurrent biological…
George L. Chadderdon, Samuel A. Neymotin, Cliff C. Kerr, William W. Lytton + 1 more
'William W. Lytton' 'Gennady Cymbalyuk'] Sensorimotor control has traditionally been considered from a control theory perspective, without relation to neurobiology. In contrast, here we utilized a spiking-neuron model of motor cortex and trained it to perform a simple movement task, which consisted of rotating a…
М. Г. Киселев
At present, implementation of learning mechanisms in spiking neural networks (SNN) cannot be considered as a solved scientific problem despite plenty of SNN learning algorithms proposed. It is also true for SNN implementation of reinforcement learning (RL), while RL is especially important for SNNs because of its close…
ARIF ULLAH, Pavlo O. Dral
Nonadiabatic quantum dynamics are important for understanding light-harvesting processes, but their propagation with traditional methods can be rather expensive. Here we present a one-shot trajectory learning approach that allows to directly make ultra-fast prediction of the entire trajectory of the reduced density…
Sanjar Adilov
Generative neural networks have shown promising results in de novo drug design. Recent studies suggest that one of the efficient ways to produce novel molecules matching target properties is to model SMILES sequences using deep learning in a way similar to language modeling in natural language processing. In this…