Filters








14,841 Hits in 5.5 sec

Compositional neural-network modeling of complex analog circuits

Ramin M. Hasani, Dieter Haerle, Christian F. Baumgartner, Alessio R. Lomuscio, Radu Grosu
2017 2017 International Joint Conference on Neural Networks (IJCNN)  
We introduce CompNN, a compositional method for the construction of a neural-network (NN) capturing the dynamic behavior of a complex analog multiple-input multiple-output (MIMO) system.  ...  To the best of our knowledge, CompNN is the first method to learn the NN of an analog integrated circuit (MIMO system) in a compositional fashion.  ...  ACKNOWLEDGMENTS We would like to thank Infineon for training, mentoring and provision of the tool landscape.  ... 
doi:10.1109/ijcnn.2017.7966126 dblp:conf/ijcnn/HasaniHBLG17 fatcat:6mw6wyt3v5epjlh4ci3tjcy344

Analog computation via neural networks

Hava T Siegelmann, Eduardo D Sontag
1994 Theoretical Computer Science  
Sontag, Analog computation via neural networks, Theoretical Computer Science 131 (1994) 331-360. 0304-3975/94/$07.00 0 1994-Elsevier Science B.V. All rights reserved SSDI 0304-3975(93)E0165-Z  ...  Introduction "Neural networks" have attracted much attention lately as models of analog computation.  ...  We pursue a particular approach to analog computation, based on dynamical systems of the type used in neural networks research.  ... 
doi:10.1016/0304-3975(94)90178-3 fatcat:nd5xeibb2jec5c7stfcjwd4j5m

Page 466 of Mathematical Reviews Vol. , Issue 96a [page]

1996 Mathematical Reviews  
Summary: “We survey some of the central results in the complexity theory of discrete neural networks, with pointers to the literature.  ...  Our main emphasis is on the computational power of various acyclic and cyclic network models, but we also discuss briefly the complexity aspects of synthesizing networks from examples of their behavior  ... 

Concept Learning in Neuromorphic Vision Systems: What Can We Learn from Insects?

Fredrik Sandin, Asad I. Khan, Adrian G. Dyer, Anang Hudaya M. Amin, Giacomo Indiveri, Elisabetta Chicca, Evgeny Osipov
2014 Journal of Software Engineering and Applications  
Sandin et al. 388 of prototype circuits for concept learning, which eventually may also help us to understand the more complex learning circuits of the human brain.  ...  The relatively low complexity of insect sensory-motor systems makes them an interesting model for the further development of bio-inspired computing architectures, in particular for resource-constrained  ...  AK thank Ahmet Sekercioglu and Alexander Senior for their assistance in the preparation of this paper. AGD thanks ARC DP0878968/DP0987989 for funding support. F. Sandin et al.  ... 
doi:10.4236/jsea.2014.75035 fatcat:4ifa2hwahbgjzob3im23hpfoam

On higher order computations, rewiring the connectome, and non-von Neumann computer architecture [article]

Stanislaw Ambroszkiewicz
2020 arXiv   pre-print
Static neural circuits correspond to first order computable functions. Synapse creation (activation) between them correspond to the mathematical notion of function composition.  ...  First order computations in the brain are done by static neural circuits, whereas higher order computations are done by dynamic reconfigurations of the links (synapses) between the neural circuits.  ...  Since the architecture of human brain is definitely different than von Neumann computer architecture (see von Neumann 1958 [39] and 1966 [40] ), the mechanisms for rewiring the connectome (i.e. the  ... 
arXiv:1603.02238v4 fatcat:lee62juwunekvh7hbzq4wu7p5q

Analog Circuit Fault Diagnosis Using a Novel Variant of aConvolutional Neural Network

Liang Han, Feng Liu, Kaifeng Chen
2021 Algorithms  
Aiming to accurately diagnose the faults of analog circuits, this paper proposes a novel variant of a convolutional neural network, namely, a multi-scale convolutional neural network with a selective kernel  ...  Analog circuits play an important role in modern electronic systems.  ...  Due to the complexity of the analog circuit fault mechanism and the diversity of failure modes, how to efficiently and accurately diagnose the fault of the analog circuit has always been a hot area of  ... 
doi:10.3390/a15010017 fatcat:wpft7xzaefctlcd2gpnonpet6a

Failure and power utilization system models of differential equations by polynomial neural networks

Ladislav Zjavka, Ajith Abraham
2013 13th International Conference on Hybrid Intelligent Systems (HIS 2013)  
Reliability modeling of electronic circuits can be best performed by the stressor -susceptibility interaction model.  ...  Differential polynomial neural network is a new type of neural network, which constructs and substitutes an unknown general sum partial differential equation with a total sum of fractional polynomial terms  ...  DIFFERENTIAL POLYNOMIAL NEURAL NETWORK Multi-layered networks forms composite polynomial functions (Figure 4 .).  ... 
doi:10.1109/his.2013.6920496 dblp:conf/his/ZjavkaA13 fatcat:lfmudjb2d5e6zik4g6ka2vhre4

Radically Compositional Cognitive Concepts [article]

Toby B. St Clere Smithe
2019 arXiv   pre-print
As a case study, we sketch how to translate from compositional narrative concepts to neural circuits and back again.  ...  We describe how these tools grant us a means to overcome complexity and improve interpretability, and supply a rigorous common language for scientific modelling, analogous to the type theories of computer  ...  Thus we can model narrative as a 'conceptual' state-space model (Figure 1 (b)-(d)). Next, we map this onto a prototypical neural circuit. 4 From compositional concepts to compositional circuits ...  ... 
arXiv:1911.06602v1 fatcat:fcukpo4gbraedjltg54bubp6xq

Particle swarm optimization over non-polynomial metamodels for fast process variation resilient design of Nano-CMOS PLL

Oleg Garitselov, Saraju Mohanty, Elias Kougianos, Geng Zheng
2012 Proceedings of the great lakes symposium on VLSI - GLSVLSI '12  
Neural network based non-polynomial metamodels that handle large numbers of design parameters, are used to predict the statistical process variation effects instead of exhaustive Monte Carlo simulations  ...  The physical design of a Phase Locked Loop (PLL) is considered as a case study circuit.  ...  PROCESS VARIATION ANALYSIS USING NEURAL NETWORK METAMODELS Non-polynomial metamodeling using feed forward neural networks Neural network models are composed of a mass of fairly simple computational elements  ... 
doi:10.1145/2206781.2206843 dblp:conf/glvlsi/GaritselovMKZ12 fatcat:ioggazglxzfuba6azgfzllcgyq

Fast-Accurate Non-Polynomial Metamodeling for Nano-CMOS PLL Design Optimization

Oleg Garitselov, Saraju P. Mohanty, Elias Kougianos
2012 2012 25th International Conference on VLSI Design  
This paper presents non-polynomial metamodels (surrogate models) using neural networks to reduce the design optimization time of complex nano-CMOS circuit with no sacrifice on accuracy.  ...  The physical design aware neural networks are trained and used as metamodels to predict frequency, locking time, and power of a PLL circuit.  ...  In [14] , a Hopfield neural network model is used to represent digital circuit behavior.  ... 
doi:10.1109/vlsid.2012.90 dblp:conf/vlsid/GaritselovMK12 fatcat:wdoe5oo4krgqrab4d3tnsk6orq

Analog VLSI Biophysical Neurons and Synapses With Programmable Membrane Channel Kinetics

Theodore Yu, Gert Cauwenberghs
2010 IEEE Transactions on Biomedical Circuits and Systems  
We present and characterize an analog VLSI network of 4 spiking neurons and 12 conductance-based synapses, implementing a silicon model of biophysical membrane dynamics and detailed channel kinetics in  ...  Index Terms-Neuromorphic engineering, reconfigurable neural and synaptic dynamics, silicon neurons, subthreshold metal-oxide semiconductor (MOS), translinear circuits.  ...  The difficulty of realizing the complex functional form of the Hodgkin-Huxley membrane currents and channel variables in analog circuits has motivated alternative realizations by simplifications in the  ... 
doi:10.1109/tbcas.2010.2048566 pmid:23853338 fatcat:s4fmvmbkwfei3m4ayrnokwyl2m

Compiled code simulation of analog and mixed-signal systems using piecewise linear modeling of nonlinear parameters: A case study for modulator simulation

Hui Zhang, Simona Doboli, Hua Tang, Alex Doboli
2007 Integration  
The paper presents a technique for automatically creating PWL models through model extraction from trained neural networks.  ...  This paper presents a method for fast time-domain simulation of analog systems with nonlinear parameters. Specifically, the paper focuses on £ ¥ ¤ analog-to-digital converters (ADC).  ...  Then, the simulation behavior of complex analog circuits were obtained using the extracted, piecewise linear models.  ... 
doi:10.1016/j.vlsi.2005.09.001 fatcat:hy6vtg46jzc4riiujebddsirle

Implementing neural architectures using analog VLSI circuits

M.A.C. Maher, S.P. Deweerth, M.A. Mahowald, C.A. Mead
1989 IEEE Transactions on Circuits and Systems  
A methodology for building these systems in CMOS VLSI technology has been developed using analog micropower circuit elements that can be hierarchically combined.  ...  Using this methodology, experimental VLSI chips of visual and motor subsystems have been designed and fabricated.  ...  Modeling biological systems presents many challenges to the analog circuit designer.  ... 
doi:10.1109/31.31311 fatcat:kvgytesmk5etjmgwqmycvdorei

Using Improved BP Neural Network and Concept Lattice to Construction Smart Sensors System

Hongsheng Xu, Ruiling Zhang
2013 Sensors & Transducers  
This paper uses the implicit structure of three layers of BP neural network to build intelligent sensor network model is improved to complete the prediction of sensor information.  ...  The paper presents using improved BP neural network and concept lattice model to construction of smart sensors system.  ...  Acknowledgements This paper is supported by the National Natural Science Funds of China (61272015), and also is supported by the science and technology research major project of Henan province Education  ... 
doaj:9f83b28c66124073854849e99c1a503a fatcat:2swp7a3c45emhjukforcvxwele

Spike-Based MAX Networks for Nonlinear Pooling in Hierarchical Vision Processing

Fopefolu O. Folowosele, R. Jacob Vogelstein, R. Etienne-Cummings
2007 2007 IEEE Biomedical Circuits and Systems Conference  
hierarchical model of visual information processing using large-scale arrays of identical silicon neurons.  ...  Complex cells in the visual cortex utilize a maximum (MAX) operation to pool the outputs of simple cells to achieve feature specificity and invariance.  ...  of software for studying real-time operations of cortical, large-scale neural networks.  ... 
doi:10.1109/biocas.2007.4463313 fatcat:wxdrcryukbezrgm2cqgzksolqu
« Previous Showing results 1 — 15 out of 14,841 results