Syed Atiqur Rahman

DVCC-Based Non-linear Feedback Neural Circuit for Solving System of Linear Equations

A neural circuit to solve a system of simultaneous linear equations is presented. The circuit employs non-linear feedback to achieve a transcendental energy function that ensures fast convergence to the exact solution while enjoying reduction in hardware complexity over existing schemes. A new building block for analog signal processing, the digitally controlled differential voltage current conveyor (DC-DVCC) is introduced and is utilized for the non-linear synaptic interconnections between neurons. The proof of the energy function has been given and it is shown that the gradient network converges exactly to the solution of the system of equations. PSPICE simulation results are presented for linear systems of equations of various sizes and are found to be in close agreement with the algebraic solution. The use of CMOS DC-DVCCs and operational amplifiers facilitates monolithic integration.

A novel current-mode non-linear feedback neural circuit for solving linear equations

A novel current-mode neural circuit employing non-linear feedback to solve a system of simultaneous linear equations is presented. The circuit has an associated transcendental energy function that ensures fast convergence to the exact solution while enjoying a resistor-less implementation. The hardware complexity of the proposed scheme compares favourably with existing voltage-mode neural circuits for the same task. PSPICE simulation results are presented for a chosen set of equations and are found to be in agreement with the algebraic solution.

A DVCC-based non-linear analog circuit for solving linear programming problems

This paper presents a neural circuit for solving linear programming problem (LPP). The objective is to minimize a first order cost function subject to linear constraints. The dynamic analog circuit, consisting of N identical units for N variable problem, can solve the general LPP and always converges to the optimal solution in constant time, irrespective of the initial conditions, which is of the order of its time constant. The proposed circuit employs non-linear feedback, in the form of Differential Voltage Current Conveyor (DVCC) based unipolar comparators, to introduce transcendental terms in the energy function ensuring fast convergence to the solution. Further, the use of resistors to generate weighted inputs to the neurons is avoided. Instead, DVCCs are utilized to directly generate the required scaled currents. PSPICE simulation results are presented for a chosen optimization problem and are found to agree with the algebraic solution.

A Neuromorphic Majority Function Circuit with O(n) Area Complexity in 180 nm CMOS

An artificial neuron with a step activation function is first designed and verified. Thereafter, a synaptic weight generation circuitry is designed to provide a suitable sum current to the activation function neuron to achieve the task of majority function generation for digital logic inputs. HSPICE simulations are performed to verify the proposed theoretical framework, with the proposed network correctly yielding the appropriate low or high digital logic state corresponding to the input combinations applied. Superiority of the proposed circuit in terms of transistor area required is also demonstrated. The transistor count increase linearly with the number of variables in the case of the proposed circuit; whereas for conventional static CMOS implementations an exponential increase in transistor count is exhibited.

MO-OTA based recurrent neural network for solving simultaneous linear equations

A non-linear feedback neural network based CMOS compatible circuit to solve a system of simultaneous linear equations is presented. The circuit has an associated transcendental energy function that ensures fast convergence to the solution. The use of multi-output OTAs ensures that synaptic weight resistance are eliminated thereby reducing the circuit complexity over existing schemes. PSPICE simulation results are presented for two chosen sets of equations and are found to agree with the algebraic solutions.

Integrable non-linear feedback analog circuit for solving linear equations

A CMOS compatible neural circuit, employing non-linear feedback, to solve a system of simultaneous linear equations is presented. The circuit has an associated energy function comprising of transcendental terms that ensure fast convergence to the solution. The use of multi-output OTAs ensures that synaptic weight resistances are eliminated thereby reducing the circuit complexity over existing schemes. PSPICE simulation results are presented for two chosen sets of equations and are found to be in close agreement with the algebraic solutions.

Non-linear Feedback Neural Network for Solution of Quadratic Programming Problems

quadratic programming problems. The objective is tominimize a quadratic cost function subject to linearconstraints. The proposed circuit employs nonlinearfeedback, in the form of unipolar comparators, to introducetranscendental terms in the energy function ensuring fastconvergence to the solution. The proof of validity of the energy function is also provided. The hardware complexity of the proposed circuit comparesfavorably with other proposed circuits for the same task. PSPICE simulation results arepresented for a chosen optimization problem and are foundto agree with the algebraic solution.

A Non–Linear Feedback Neural Network for Graph Coloring

A feedback neural network for solving graph coloring problem is presented. The circuit has an associated transcendental energy function that ensures fast convergence to the exact solution. Hardware and PSPICE simulation results on random and benchmark problems have been presented. Test results are compared with existing techniques for graph coloring to show that the proposed neural network model provides a significant reduction in the number of colors while enjoying a simple and efficient circuit implementation. General Terms Neural Networks, Graph Coloring.

Graph Coloring using a feedback neural network with transconducting synaptic interconnections

A non-linear feedback neural network for graph colouring problems is presented. The proposed circuit employs non-linear feedback, in the form of unipolar comparators realized using OTAs and diodes, to introduce transcendental terms in the energy function ensuring fast convergence to the solution. PSPICE simulation results on various random graphs have been presented.

A non-linear neural circuit for solving system of simultaneous linear equations

A feedback neural network based CMOS compatible circuit to solve a system of simultaneous linear equations is presented. The circuit has an associated transcendental energy function that ensures fast convergence to the exact solution while enjoying reduction in hardware complexity over existing schemes. HSPICE simulation results are presented for a chosen set of equations and are found to agree exactly with the algebraic solution.