004 Datenverarbeitung; Informatik
Refine
Year of publication
Document Type
- Article (19) (remove)
Has Fulltext
- yes (19)
Is part of the Bibliography
- no (19)
Keywords
- synaptic plasticity (4)
- Fisher information (3)
- Hebbian learning (3)
- objective functions (3)
- deep learning (2)
- generating functionals (2)
- homeostatic adaption (2)
- CBM detector (1)
- CLVisc (1)
- Deep learning (1)
Institute
- Physik (19) (remove)
Zellulare Nichtlineare Netzwerke (CNN) wurden 1988 von Chua und Yang (Chua und Yang, 1988) eingeführt. Diese Netzwerke sind dadurch gekennzeichnet, dass eine Zelle, die die kleinste Einheit eines CNN darstellt, nur mit Zellen innerhalb einer bestimmten Umgebung verbunden ist. üblicherweise sind Art und Stärke der Wechselwirkung zwischen zwei Zellen eines CNN translationsinvariant, d.h. sie hängen nur von der relativen Lage beider Zellen zueinander ab. Im Vordergrund aktueller Arbeiten stehen auf derartigen Netzwerken basierende schaltungstechnische Realisierungen mit bis zu 176x144 Zellen, die eine direkte Verbindung zu zweidimensionalen optischen Sensor-Anordnungen aufweisen. Über einen separaten Speicherbereich können die Zellkopplungen eines Netzwerks verändert werden, wodurch eine adaptive Verarbeitung von mehrdimensionalen Sensorsignalen ermöglicht wird. Das kürzlich vorgestellte so genannte EyeRis System (Anafocus Ltd.) enthält zusätzlich noch einen Standardprozessor und stellt (bei einer Größe vergleichbar mit der einer Kreditkarte) daher ein vollständiges superschnelles System zur Informationsverarbeitung dar. In diesem Beitrag sollen, nach einem kurzen Überblick über die Eigenschaften von CNN, aktuelle Realisierungen und exemplarisch eine neuere eigene Anwendung vorgestellt und besprochen werden.
Poster presentation: The brain is autonomously active and this self-sustained neural activity is in general modulated, but not driven, by the sensory input data stream [1,2]. Traditionally one has regarded this eigendynamics as resulting from inter-modular recurrent neural activity [3]. Understanding the basic modules for cognitive computation is, in this view, the primary focus of research and the overall neural dynamics would be determined by the the topology of the intermodular pathways. Here we examine an alternative point of view, asking whether certain aspects of the neural eigendynamics have a central functional role for overall cognitive computation [4,5]. Transiently stable neural activity is regularly observed on the cognitive time-scale of 80–100 ms, with indications that neural competition [6] plays an important role in the selection of the transiently stable neural ensembles [7], also denoted winning coalitions [8]. We report on a theory approach which implements these two principles, transient-state dynamics and neural competition, in terms of an associative neural network with clique encoding [9]. A cognitive system [10] with a non-trivial internal eigendynamics has two seemingly contrasting tasks to fulfill. The internal processes need to be regular and not chaotic on one side, but sensitive to the afferent sensory stimuli on the other side. We show, that these two contrasting demands can be reconciled within our approach based on competitive transient-state dynamics, when allowing the sensory stimuli to modulate the competition for the next winning coalition. By testing the system with the bars problem, we find an emerging cognitive capability. Only based on the two basic architectural principles, neural competition and transient-state dynamics, with no explicit algorithmic encoding, the system performs on its own a non-linear independent component analysis of input data stream. The system has rudimentary biological features. All learning is local Hebbian-style, unsupervised and online. It exhibits an ever-ongoing eigendynamics and at no time is the state or the value of synaptic strengths reset or the system restarted; there is no separation between training and performance. We believe that this kind of approach – cognitive computation with autonomously active neural networks – to be an emerging field, relevant both for system neuroscience and synthetic cognitive systems.
Understanding the dynamics of recurrent neural networks is crucial for explaining how the brain processes information. In the neocortex, a range of different plasticity mechanisms are shaping recurrent networks into effective information processing circuits that learn appropriate representations for time-varying sensory stimuli. However, it has been difficult to mimic these abilities in artificial neural network models. Here we introduce SORN, a self-organizing recurrent network. It combines three distinct forms of local plasticity to learn spatio-temporal patterns in its input while maintaining its dynamics in a healthy regime suitable for learning. The SORN learns to encode information in the form of trajectories through its high-dimensional state space reminiscent of recent biological findings on cortical coding. All three forms of plasticity are shown to be essential for the network's success. Keywords: synaptic plasticity, intrinsic plasticity, recurrent neural networks, reservoir computing, time series prediction
Generating functionals may guide the evolution of a dynamical system and constitute a possible route for handling the complexity of neural networks as relevant for computational intelligence.We propose and explore a new objective function, which allows to obtain plasticity rules for the afferent synaptic weights. The adaption rules are Hebbian, self-limiting, and result from the minimization of the Fisher information with respect to the synaptic flux. We perform a series of simulations examining the behavior of the new learning rules in various circumstances.The vector of synaptic weights aligns with the principal direction of input activities, whenever one is present. A linear discrimination is performed when there are two or more principal directions; directions having bimodal firing-rate distributions, being characterized by a negative excess kurtosis, are preferred. We find robust performance and full homeostatic adaption of the synaptic weights results as a by-product of the synaptic flux minimization. This self-limiting behavior allows for stable online learning for arbitrary durations.The neuron acquires new information when the statistics of input activities is changed at a certain point of the simulation, showing however, a distinct resilience to unlearn previously acquired knowledge. Learning is fast when starting with randomly drawn synaptic weights and substantially slower when the synaptic weights are already fully adapted.
We present an effective model for timing-dependent synaptic plasticity (STDP) in terms of two interacting traces, corresponding to the fraction of activated NMDA receptors and the concentration in the dendritic spine of the postsynaptic neuron. This model intends to bridge the worlds of existing simplistic phenomenological rules and highly detailed models, thus constituting a practical tool for the study of the interplay of neural activity and synaptic plasticity in extended spiking neural networks. For isolated pairs of pre- and postsynaptic spikes, the standard pairwise STDP rule is reproduced, with appropriate parameters determining the respective weights and timescales for the causal and the anticausal contributions. The model contains otherwise only three free parameters, which can be adjusted to reproduce triplet nonlinearities in hippocampal culture and cortical slices. We also investigate the transition from time-dependent to rate-dependent plasticity occurring for both correlated and uncorrelated spike patterns.
The Fisher information constitutes a natural measure for the sensitivity of a probability distribution with respect to a set of parameters. An implementation of the stationarity principle for synaptic learning in terms of the Fisher information results in a Hebbian self-limiting learning rule for synaptic plasticity. In the present work, we study the dependence of the solutions to this rule in terms of the moments of the input probability distribution and find a preference for non-Gaussian directions, making it a suitable candidate for independent component analysis (ICA). We confirm in a numerical experiment that a neuron trained under these rules is able to find the independent components in the non-linear bars problem. The specific form of the plasticity rule depends on the transfer function used, becoming a simple cubic polynomial of the membrane potential for the case of the rescaled error function. The cubic learning rule is also an excellent approximation for other transfer functions, as the standard sigmoidal, and can be used to show analytically that the proposed plasticity rules are selective for directions in the space of presynaptic neural activities characterized by a negative excess kurtosis.
Changes in the efficacies of synapses are thought to be the neurobiological basis of learning and memory. The efficacy of a synapse depends on its current number of neurotransmitter receptors. Recent experiments have shown that these receptors are highly dynamic, moving back and forth between synapses on time scales of seconds and minutes. This suggests spontaneous fluctuations in synaptic efficacies and a competition of nearby synapses for available receptors. Here we propose a mathematical model of this competition of synapses for neurotransmitter receptors from a local dendritic pool. Using minimal assumptions, the model produces a fast multiplicative scaling behavior of synapses. Furthermore, the model explains a transient form of heterosynaptic plasticity and predicts that its amount is inversely related to the size of the local receptor pool. Overall, our model reveals logistical tradeoffs during the induction of synaptic plasticity due to the rapid exchange of neurotransmitter receptors between synapses.
The state-of-the-art pattern recognition method in machine learning (deep convolution neural network) is used to identify the equation of state (EoS) employed in the relativistic hydrodynamic simulations of heavy ion collisions. High-level correlations of particle spectra in transverse momentum and azimuthal angle learned by the network act as an effective EoS-meter in deciphering the nature of the phase transition in QCD. The EoS-meter is model independent and insensitive to other simulation inputs including the initial conditions and shear viscosity for hydrodynamic simulations. Through this study we demonstrate that there is a traceable encoder of the dynamical information from the phase structure that survives the evolution and exists in the final snapshot of heavy ion collisions and one can exclusively and effectively decode these information from the highly complex final output with machine learning when traditional methods fail. Besides the deep neural network, the performance of traditional machine learning classifiers are also provided.