Self-Organised Learning in the Chialvo-Bak Model MSc Project
نویسنده
چکیده
A review of the Chialvo-Bak model is presented, for the two-layer neural network topology. A novel Markov Chain representation is proposed that yields several important analytical quantities and supports a learning convergence argument. The power law regime is re-examined under this new representation and is found to be limited to learning under small mapping changes. A parallel between the power law regime and the biological neural avalanches is proposed. A mechanism to avoid the permanent tagging of synaptic weights of the selective punishment rule is proposed.
منابع مشابه
Adaptivity and `Per learning'
One of the key points addressed by Per Bak in his models of brain function was that biological neural systems must be able not just to learn, but also to adapt—to quickly change their behaviour in response to a changing environment. I discuss this in the context of various simple learning rules and adaptive problems, centred around the Chialvo-Bak ‘minibrain’ model [Neurosci. 90 (1999) 1137–1148].
متن کاملOrder-disorder transition in the Chialvo-Bak `minibrain' controlled by network geometry
We examine a simple biologically-motivated neural network, the three-layer version of the Chialvo-Bak ‘minibrain’ [Neurosci. 90 (1999) 1137], and present numerical results which indicate that a non-equilibrium phase transition between ordered and disordered phases occurs subject to the tuning of a control parameter. Scale-free behaviour is observed at the critical point. Notably, the transition...
متن کاملar X iv : c on d - m at / 9 51 01 27 v 1 2 3 O ct 1 99 5 1 / f - noise in the Bak - Sneppen model
We calculate time correlation functions in the Bak-Sneppen model (Phys. Rev. Lett. 71 4083 (1993)), a model showing self-organised criticality. For a random neighbour version of the model, analytical results are presented, while on a one dimensional lattice we give numerical results. The power spectrum of these correlation functions shows 1/f-behaviour in both cases.
متن کاملPresenting A Causal Model for Factors Affecting Self-Regulated Learning Among MSc Students of Paramedical Sciences in Shahid Beheshti University of Medical Sciences
Introduction: In recent decades, self-regulated learning has been identified as an important factor in academic achievement and performance. The aim of this study was to present a causal model for factors affecting self-regulated learning among MSc students of Paramedical Sciences in Shahid Beheshti University of Medical Sciences. Methods: In this descriptive correlational study, the data were ...
متن کاملBidirectional communication in neural networks moderated by a Hebb-like learning rule
We demonstrate that our recently introduced stochastic Hebb-like learning rule [7] is capable of learning the problem of timing in general network topologies generated by an algorithm of Watts and Strogatz [20]. We compare our results with a learning rule proposed by Bak and Chialvo [2, 4] and obtain not only a significantly better convergence behavior but also a dependence of the presentation ...
متن کامل