Linear bilateral CMOS resistor for neural-type circuits

Sellami, L.; Singh, Shyam; Newcomb, R.W.; Moon, Gyu

doi:10.1109/mwscas.1997.662327

Cited by 20 publications

(7 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To test this hypothesis, we compare the homogenous memristive networks (HP, and PEO-PANI) to networks solely comprised of linear resistors (e.g. [13]) and constant-weighted elements. Extending the hypothesis to heterogeneous networks, we seek to confirm that varied memristive behaviours can be harnessed by the evolutionary design process to provide further advantages, specifically that (i) certain functionality can be more easily achieved by certain memristor types (ii) combinations of memristor types are beneficial to the networks.…”

Section: Introductionmentioning

confidence: 99%

Evolution of Plastic Learning in Spiking Networks via Memristive Connections

Howard

Gale

Bull

et al. 2012

IEEE Trans. Evol. Computat.

View full text Add to dashboard Cite

This article presents a spiking neuroevolutionary system which implements memristors as plastic connections, i.e. whose weights can vary during a trial. The evolutionary design process exploits parameter self-adaptation and variable topologies, allowing the number of neurons, connection weights, and inter-neural connectivity pattern to emerge. By comparing two phenomenological real-world memristor implementations with networks comprised of (i) linear resistors (ii) constant-valued connections, we demonstrate that this approach allows the evolution of networks of appropriate complexity to emerge whilst exploiting the memristive properties of the connections to reduce learning time. We extend this approach to allow for heterogeneous mixtures of memristors within the networks; our approach provides an in-depth analysis of network structure. Our networks are evaluated on simulated robotic navigation tasks; results demonstrate that memristive plasticity enables higher performance than constant-weighted connections in both static and dynamic reward scenarios, and that mixtures of memristive elements provide performance advantages when compared to homogeneous memristive networks.

show abstract

Section: Introductionmentioning

confidence: 99%

Evolution of Plastic Learning in Spiking Networks via Memristive Connections

Howard

Gale

Bull

et al. 2012

IEEE Trans. Evol. Computat.

View full text Add to dashboard Cite

show abstract

“…The structure of the proposed active resistor is based on three important blocks: a voltage-current squarer, a current square-root circuit and a current-pass circuit, named 2 x , and I , respectively on the block diagram from Figure 1.…”

Section: A the Block Diagram Of The Fgmos Active Resistormentioning

confidence: 99%

“…The first generation of MOS active resistors [1], [2] used MOS transistors working in the linear region. The main disadvantage is that the realised active resistor is inherently nonlinear and the distortion components were complex functions on MOS technological parameters.…”

Section: Introductionmentioning

confidence: 99%

Improved Linearity Active Resistor with Increased Frequency Response for VLSI Applications

Popa¹

2006

2006 IEEE International Conference on Automation, Quality and Testing, Robotics

View full text Add to dashboard Cite

An original active resistor circuit will be presented in this paper. The main advantages of the new proposed implementation are the improved linearity, the small area consumption and the improved frequency response. The frequency response of the circuit is very good as a result of operating all MOS transistors in the saturation region. The circuit is implemented in m 35 0 µ . CMOS technology, the SPICE simulation confirming the theoretical estimated results and showing a linearity error under a percent for an extended input range and a small value of the supply voltage. Index Terms-active resistor, linearity error, squaring and square-root circuits, complementary functions

show abstract

“…The first generation of MOS active resistors [1,2] used MOS transistors working in the linear region, having the main disadvantages of an equivalent resistance inherently nonlinear and of obtaining distortion components that are complex functions on MOS technological parameters. A better design of CMOS active resistors is based on MOS transistors working in saturation .…”

Section: Introductionmentioning

confidence: 99%

Low-voltage low-power improved linearity CMOS active resistor circuits

Manolescu

Popa

2009

Analog Integr Circ Sig Process

View full text Add to dashboard Cite

A tutorial of CMOS active resistor circuits will be presented in this paper. The main advantages of the proposed implementations are the improved linearity, the small area consumption and the improved frequency response. In order to improve their linearity, improved performances linearization techniques will be proposed, with additional care for compensating the errors introduced by second-order effects. Design techniques for minimizing the silicon area consumption will be further presented and FGMOS (Floating Gate MOS) transistors will be used for this purpose. The frequency response of the circuits is very good as a result of biasing all MOS transistors in the saturation region and of a current-mode operation of an important part of their blocks. Additionally, small changing in each design allows to obtain negative controllable equivalent resistance circuits. The circuits are implemented in CMOS technology, SPICE simulations confirming the theoretical estimated results, showing small values of the linearity error (under 0.15% for the best design) for an extended input range and for a supply voltage equal with ±3 V. The proposed circuits respond to low-voltage low-power requirements, their design being adapted to the continuous degradation of the model quality associated with the evolution toward latest nanotechnologies.

show abstract

Linear bilateral CMOS resistor for neural-type circuits

Cited by 20 publications

References 11 publications

Evolution of Plastic Learning in Spiking Networks via Memristive Connections

Evolution of Plastic Learning in Spiking Networks via Memristive Connections

Improved Linearity Active Resistor with Increased Frequency Response for VLSI Applications

Low-voltage low-power improved linearity CMOS active resistor circuits

Contact Info

Product

Resources

About