A Cascadable Random Neural Network Chip with Reconfigurable Topology

Badaroglu, Mustafa
Halıcı, Uğur
Aybay, Isik
Cerkez, Cuneyt
A digital integrated circuit (IC) is realized using the random neural network (RNN) model introduced by Gelenbe. The RNN IC employs both configurable routing and random signaling. In this paper we present the networking/routing aspects as well as the performance results of an RNN network implemented by the RNN IC. In the RNN model, each neuron accumulates arriving signals and can fire if its potential at a given instant of time is strictly positive. Firing occurs at random, the intervals between successive firing instants following an exponential distribution of constant rate. When a neuron fires, it routes the generated pulses to the output lines in accordance with the connection probabilities. The number of neurons in the network is programmable and could be connected to each other with any desired neuron interconnection and this connection could be changed on the fly. The RNN chip architecture is cascadable to generate any network topology. All the parts of the RNN circuit are implemented using a standard digital Complimentary-Metal-Oxide-Semiconductor (CMOS) process.


A temporal neural network model for constructing connectionist expert system knowledge bases
Alpaslan, Ferda Nur (Elsevier BV, 1996-04-01)
This paper introduces a temporal feedforward neural network model that can be applied to a number of neural network application areas, including connectionist expert systems. The neural network model has a multi-layer structure, i.e. the number of layers is not limited. Also, the model has the flexibility of defining output nodes in any layer. This is especially important for connectionist expert system applications.
A Depth-optimal Low-complexity Distributed Wireless Multicast Algorithm
Akyurek, A. Sinan; Uysal, Elif (Oxford University Press (OUP), 2011-06-01)
This paper presents a wireless multicast tree construction algorithm, SWIM (Source-initiated WIreless Multicast). SWIM constructs a tree on which each multicast destination has the minimum possible depth (number of hops from the nearest source). It is proved that SWIM is fully distributed, with a worst case complexity upper-bounded by O(N-3), and an empirically found average complexity of only O(N-2). SWIM forms one shared tree from source(s) to the multicast destinations; yet, as a by-product, it creates a...
An FPGA implementation of real-time electro-optic & IR image fusion
Çölova, İbrahim Melih; Akar, Gözde; Department of Electrical and Electronics Engineering (2010)
In this thesis, a modified 2D Discrete Cosine Transform based electro-optic and IR image fusion algorithm is proposed and implemented on an FPGA platform. The platform is a custom FPGA board which uses ALTERA Stratix III family FPGA. The algorithm is also compared with state of the art image fusion algorithms by means of an image fusion software application GUI developed in Matlab®. The proposed algorithm principally takes corresponding 4x4 pixel blocks of two images to be fused and transforms them by means...
Fast cell determination of the DSMC molecules in multi-stage turbo molecular pump design
Sengil, N.; Edis, Fırat Oğuz (Elsevier BV, 2011-06-01)
In this study, an existing 2D parallel DSMC solver is modified, to analyze the multi-stage turbomolecular pumps more efficiently. Generally, molecule movements are traced cell-by-cell in DSMC solvers both in structured and unstructured meshes in order to determine which cell the DSMC molecule is positioned in. These calculations require time consuming trigonometric operations. If a nonrectangular physical domain can be converted into a rectangular computational domain using curvilinear coordinates, then it ...
A low-order nonlinear amplifier model with distributed delay terms
YÜZER, AHMET HAYRETTİN; Demir, Şimşek (The Scientific and Technological Research Council of Turkey, 2014-01-01)
In this paper, a novel behavioral modeling technique for the characterization of memory effects of amplifiers is proposed. This characterization utilizes asymmetric intermodulation distortion (IMD)components, which are the result of a 2-tone excitation of a nonlinear amplifier. These asymmetric IMD components are represented basically by a power series, where each term in the series has its own time delay term. These time delay terms successfully justify the presence of asymmetry in the intermodulation comp...
Citation Formats
M. Badaroglu, U. Halıcı, I. Aybay, and C. Cerkez, “A Cascadable Random Neural Network Chip with Reconfigurable Topology,” COMPUTER JOURNAL, pp. 289–303, 2010, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/43815.