This work compares 7,560 reservoir designs, all combinations of six design factors, each built as many random reservoirs, on recalling the majority or the parity of a few input bits seen several steps earlier, to study random Boolean networks as reservoirs.
Abstract
Reservoir computing shifts the focus from training a system's internal dynamics to designing dynamics that expose useful computational capabilities via linear projection. We study random Boolean networks as reservoirs: cellular automata with random recurrent wiring and a random rule at each node. Their main parameter is the connectivity, the mean number of edges into a node. Without input, these networks pass from ordered to chaotic dynamics at a connectivity of 2, where their dynamics are expected to facilitate computation. How the input is connected is itself a design factor: if the input shares the network's edges, the connectivity sets both the dynamics and how many nodes receive the input, the input fan-out. We set the input fan-out separately and compare 7,560 reservoir designs, all combinations of six design factors, each built as many random reservoirs, on recalling the majority or the parity of a few input bits seen several steps earlier. The optimal connectivity falls from 2.5 to 1.75-2 as more nodes receive the input, but hardly depends on the task or on the other design factors, except self-loops, which connect a node to itself and raise the optimal connectivity. A measure computed from the reservoir states without a trained readout peaks at a connectivity that also falls with the fan-out and rises with self-loops, but does not replace training a readout. Reservoirs of one design vary widely, so a design should be judged by its typical reservoir.
Reservoir computing has established itself as a computationally efficient alternative to fully trained recurrent neural networks using a fixed high-dimensional nonlinear substrate to map temporal input into a feature space for a simple readout. Here, we argue that reservoir computing can be realized entirely within a c...
Max Potratzki, T. D. de Jong, M. Small et al.· Chaos· 0 citations
Two methods that exploit modularity within networks are proposed: selecting the top 10% of influential nodes in each module based on structural metrics, and identifying a subset of the FVS by prioritizing the highest-ranked nodes within each module.
F. Nasrollahi, E. Newby, Réka Albert· Scientific Reports· 1 citation
A fixed network of McCulloch-Pitts threshold units with weights in {-1,0,1} can hold other threshold networks in its state and run them: the state is a ring of banks of records, each record a unit of a stored network, and each step evaluates one record. We use such a network to carry out von Neumann's universal constru...
Echo State Networks (ESNs) are fundamentally important from the conceptual perspective of AI, because they provide simple and tractable frameworks for understanding temporal information processing, memory, and learning in dynamical systems. They are composed by an interconnected reservoir whose connectivity matrix rema...
A. Provata, Markos Syroukis, J. Hizanidis· 0 citations
We explore how synchronization in coupled oscillator networks may be employed to perform a variety of computing tasks. These systems are becoming more attractive as an alternative to conventional digital computers due to the increasing energy demands of the latter, particularly for large-scale problems in machine learn...
We study a discrete-time stochastic model for the spiking activity of a network of $n$ interacting neurons partitioned into $k$ communities. The interaction network is a random directed weighted graph generated by a Stochastic Block Model with $k+1$ edge types ($k$ intra-community, $1$ inter-community). Each edge is pr...
Thiago H. N. Coelho, Leonardo F. R. Ribeiro, G. Iacobelli et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.