U.S. patents available from 1976 to present.
U.S. patent applications available from 2005 to present.

Icon_funbox Did You Know...

...that several people are credited with the invention of the flush toilet? Most people have heard of Thomas Crapper (1837-1910), the sanitary engineer who invented the valve-and-siphon arrangement that made the modern toilet possible. Another claimant to "the throne" was British inventor Alexander Cumming who patented a toilet in 1775. Then there's a nameless Minoan (a native of ancient Crete) who lived 4,000 years ago who supposedly was ahead of his time and created the first flush toilet!

Newsletter  PatentStorm News

Make the Most of Our Site

See this month's Top Inventors and Most Cited Patents.

Stay on top of the latest innovations by subscribing to an RSS feed.

Registered users: Manage your profile.

 

Class 706/30 - Recurrent


Subclass of Class 706 - Data processing: artificial intelligence
Definition: Subject matter wherein the architecture comprises feedback
No. of patents: 92
Last issue date: 04/17/2012


    3  
NumberTitleIssue Date
4906865Sample and hold circuit for temporal associations in a neural network
A sample and hold circuit for introducing delayed feedback into an associative memory is described. The circuit continuously samples an output sequence derived from a neural network; then, in response to a clock signal, it holds that output sequence until...
03/06/1990
4901271Computational network
A new associative computation network that is capable of storing multi-bit vectors includes a decision network and a feedback arrangement that, functionally, is separable into serially connected networks. The first network has its inputs connectd to the o...
02/13/1990
4849925Maximum entropy deconvolver circuit based on neural net principles
Disclosed are two modifications of the Tank-Hopfield circuit, each of which enables the deconvolution of a signal in the presence of noise. In each embodiment, the Tank-Hopfield circuit is modified so that the equation for total circuit energy reduces to ...
07/18/1989
4807168Hybrid analog-digital associative neural network
Random access memory is used to store synaptic information in the form of a matrix of rows and columns of binary digits. N rows read in sequence are processed through switches and resistors, and a summing amplifier to N neural amplifiers in sequence, one ...
02/21/1989
4803736Neural networks for machine vision
Network interactions within a Boundary Contour (BC) System, a Feature Contour (FC) System, and an Object Recognition (OR) System are employed to provide a computer vision system capable of recognizing emerging segmentations. The BC System is defined by a ...
02/07/1989
4802103Brain learning and recognition emulation circuitry and method of recognizing events
There is disclosed herein a method and apparatus for learning the characteristics of an event and for recognizing events which have been previously learned. The apparatus is comprised of forward and feedback matrices which process input signals characteri...
01/31/1989
4782460Computing apparatus comprising a programmable resistor
Computing apparatus (e.g., a neural network) advantageously comprises a programmable resistor body comprising typically a multiplicity of resistors Rij. The resistance of any given Rij is changeable from a relatively high resistance ...
11/01/1988
4773024Brain emulation circuit with reduced confusion
There is disclosed herein a recognize only embodiment of a recognition matrix comprised of a forward matrix and a reverse matrix each having a plurality of contacts which cause convergence responses on target lines when an input signal is received by said...
09/20/1988
4752906Temporal sequences with neural networks
A sequence generator employing a neural network having its output coupled to at least one plurality of delay elements. The delayed outputs are fed back to an input interconnection network, wherein they contribute to the next state transition through an ap...
06/21/1988
4737929Highly parallel computation network employing a binary-valued T matrix and single output amplifiers
Advantageous neural network realizations are achieved by employing only negative gain amplifiers and a clipped T matrix having conductances Tij which have only two values. Preferably, one of these values is a preselected value set by the value ...
04/12/1988
4731747Highly parallel computation network with normalized speed of response
Superior performance is achieved by equalizing the time constants of amplifiers used in highly parallel computational networks. In accordance with one aspect of the invention a feedback arrangement is employed with the resistance between the input of each...
03/15/1988
4660166Electronic network for collective decision based on large number of connections between signals
Amplifiers, optionally having complementary (positive and negative) outputs, are connected to a matrix of input and output conductors (where the output conductors are each a pair for the case of complementary amplifier outputs). Each connection is impleme...
04/21/1987
    3  
 
Sign InRegister
Username  
Password   
forgot password?