An Energy Efficient Additive Neural Network

Date

2017-05-18

Author

Afrasiyabi, Arman
Nasır, Barış
Yildiz, Ozan
Yarman Vural, Fatoş Tunay
ÇETİN, AHMET ENİS

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

139
views

0
downloads

In this paper, we propose a new energy efficient neural network with the universal approximation property over space of Lebesgue integrable functions. This network, called additive neural network, is very suitable for mobile computing. The neural structure is based on a novel vector product definition, called ef-operator, that permits a multiplier-free implementation. In ef-operation, the "product" of two real numbers is defined as the sum of their absolute values, with the sign determined by the sign of the product of the numbers. This "product" is used to construct a vector product in n-dimensional Euclidean space. The vector product induces the lasso norm. The proposed additive neural network successfully solves the XOR problem. The experiments on MNIST dataset show that the classification performances of the proposed additive neural networks are very similar to the corresponding multi-layer perceptron.

Subject Keywords

Energy efficient, Efficient ANN, Neural network, Machine learning, Multiplierless ann, Mnist, Xor

URI

https://hdl.handle.net/11511/53149

Conference Name

25th Signal Processing and Communications Applications Conference (SIU)

Collections

Department of Computer Engineering, Conference / Seminar

Suggestions

OpenMETU
Core

An adaptive, energy-aware and distributed fault-tolerant topology-control algorithm for heterogeneous wireless sensor networks Deniz, Fatih; Bagci, Hakki; KÖRPEOĞLU, İBRAHİM; Yazıcı, Adnan (2016-07-01) This paper introduces an adaptive, energy-aware and distributed fault-tolerant topology control algorithm, namely the Adaptive Disjoint Path Vector (ADPV) algorithm, for heterogeneous wireless sensor networks. In this heterogeneous model, we have resource-rich supernodes as well as ordinary sensor nodes that are supposed to be connected to the supernodes. Unlike the static alternative Disjoint Path Vector (DPV) algorithm, the focus of ADPV is to secure supernode connectivity in the presence of node failures...
A neuro-fuzzy MAR algorithm for temporal rule-based systems Sisman, NA; Alpaslan, Ferda Nur; Akman, V (1999-08-04) This paper introduces a new neuro-fuzzy model for constructing a knowledge base of temporal fuzzy rules obtained by the Multivariate Autoregressive (MAR) algorithm. The model described contains two main parts, one for fuzzy-rule extraction and one for the storage of extracted rules. The fuzzy rules are obtained from time series data using the MAR algorithm. Time-series analysis basically deals with tabular data. It interprets the data obtained for making inferences about future behavior of the variables. Fu...
Artificial-neural-network prediction of hexagonal lattice parameters for non-stoichiometric apatites Kockan, Umit; Ozturk, Fahrettin; Evis, Zafer (2014-01-01) In this study, hexagonal lattice parameters (a and c) and unit-cell volumes of non-stoichiometric apatites of M-10(TO4)(6)X-2 are predicted from their ionic radii with artificial neural networks. A multilayer-perceptron network is used for training. The results indicate that the Bayesian regularization method with four neurons in the hidden layer with a tansig activation function and one neuron in the output layer with a purelin function gives the best results. It is found that the errors for the predicted ...
An alternative simple solution of the sextic anharmonic oscillator and perturbed coulomb problems IKHDAİR, SAMEER; Sever, Ramazan (World Scientific Pub Co Pte Lt, 2007-10-01) Utilizing an appropriate ansatz to the wave function, we reproduce the exact bound-state solutions of the radial Schrodinger equation to various exactly solvable sextic an-harmonic oscillator and confining perturbed Coulomb models in D-dimensions. We show that the perturbed Coulomb problem with eigenvalue E can be transformed to a sextic anharmonic oscillator problem with eigenvalue P. We also check the explicit relevance of these two related problems in higher-space dimensions. It is shown that exact solut...
Quantum mechanical computation of billiard systems with arbitrary shapes Erhan, İnci; Taşeli, Hasan; Department of Mathematics (2003) An expansion method for the stationary Schrodinger equation of a particle moving freely in an arbitrary axisymmeric three dimensional region defined by an analytic function is introduced. The region is transformed into the unit ball by means of coordinate substitution. As a result the Schrodinger equation is considerably changed. The wavefunction is expanded into a series of spherical harmonics, thus, reducing the transformed partial differential equation to an infinite system of coupled ordinary differenti...

Citation Formats

A. Afrasiyabi, B. Nasır, O. Yildiz, F. T. Yarman Vural, and A. E. ÇETİN, “An Energy Efficient Additive Neural Network,” presented at the 25th Signal Processing and Communications Applications Conference (SIU), Antalya, Turkey, 2017, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/53149.