[图书][B] An analog VLSI system for stereoscopic vision
M Mahowald - 1994 - books.google.com
An Analog VLSI System for Stereoscopic Vision investigates the interaction of the physical
medium and the computation in both biological and analog VLSI systems by synthesizing a …
medium and the computation in both biological and analog VLSI systems by synthesizing a …
Survey of neural network technology for automatic target recognition
MW Roth - IEEE Transactions on neural networks, 1990 - ieeexplore.ieee.org
A review is presented of ATR (automatic target recognition), and some of the highlights of
neural network technology developments that have the potential for making a significant …
neural network technology developments that have the potential for making a significant …
[图书][B] Neuroscience and connectionist theory
MA Gluck, DE Rumelhart - 2013 - books.google.com
Written for cognitive scientists, psychologists, computer scientists, engineers, and
neuroscientists, this book provides an accessible overview of how computational network …
neuroscientists, this book provides an accessible overview of how computational network …
[PDF][PDF] Vision chips or seeing silicon
A Moini - … for High Performance Integrated Technologies and …, 1997 - sl-div-bi-pb.web.cern.ch
Smart vision systems will be an inevitable component of future intelligent systems.
Conventional vision systems, based on the system level integration (or even chip level …
Conventional vision systems, based on the system level integration (or even chip level …
Resistive grid image filtering: input/output analysis via the CNN framework
The cellular neural network framework developed by LO Chua and L. Yang (IEEE Trans.
Circuits Syst., vol. 32, Oct. 1988) is used to analyze the image filtering operation performed …
Circuits Syst., vol. 32, Oct. 1988) is used to analyze the image filtering operation performed …
Seeing chips: Analog VLSI circuits for computer vision
C Koch - Neural Computation, 1989 - direct.mit.edu
Vision is simple. We open our eyes and, instantly, the world surrounding us is perceived in
all its splendor. Yet Artificial Intelligence has been trying with very limited success for over 20 …
all its splendor. Yet Artificial Intelligence has been trying with very limited success for over 20 …
A deep learning theory for neural networks grounded in physics
B Scellier - arXiv preprint arXiv:2103.09985, 2021 - arxiv.org
In the last decade, deep learning has become a major component of artificial intelligence.
The workhorse of deep learning is the optimization of loss functions by stochastic gradient …
The workhorse of deep learning is the optimization of loss functions by stochastic gradient …
Neuromorphic vision sensors
R Etienne-Cummings, J Van der Spiegel - Sensors and Actuators A …, 1996 - Elsevier
A review of current trends in biologically based computational visual sensors, also known as
neuromorphic sensors, is presented. Neuromorphic sensors attempt to mimic the sensing …
neuromorphic sensors, is presented. Neuromorphic sensors attempt to mimic the sensing …
CMOS resistive fuses for image smoothing and segmentation
PC YU, SJ Decker, HS Lee, CG Sodini… - IEICE Transactions on …, 1992 - search.ieice.org
A two-terminal nonlinear element called a resistive fuse is described. Its application in image
smoothing and segmentation is explained. Two types CMOS resistive fuses were designed …
smoothing and segmentation is explained. Two types CMOS resistive fuses were designed …
The" softmax" nonlinearity: Derivation using statistical mechanics and useful properties as a multiterminal analog circuit element
IM Elfadel, JL Wyatt Jr - Advances in neural information …, 1993 - proceedings.neurips.cc
We use mean-field theory methods from Statistical Mechanics to derive the" softmax"
nonlinearity from the discontinuous winner (cid: 173) take-all (WTA) mapping. We give two …
nonlinearity from the discontinuous winner (cid: 173) take-all (WTA) mapping. We give two …