Brain learning and recognition emulation circuitry and method of recognizing events

• US 4,802,103 A
• Filed: 06/03/1986
• Issued: 01/31/1989
• Est. Priority Date: 06/03/1986
• Status: Expired due to Term

• Current Assignee: MENO Corporation
• Original Assignee: Synaptics Incorporated
• Inventors: Faggin, Federico, Lynch, Gary S.
• Primary Examiner(s): Ruggiero, Joseph
• Application Number:
  US06/870,241
• Time in Patent Office: 973 Days
• Field of Search: 364/513, 364/148, 364/156, 364/149-152, 364/300, 364/200 MS File, 364/900 MS File, 382/14, 382/15, 382/27, 382/1, 382/36-39, 382/48, 382/50, 307/201
• US Class Current: 706/38
• CPC Class Codes: G06F 18/21 Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
• CPC Class Codes: G06N 3/063 using electronic means
• CPC Class Codes: G06V 10/75 Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries

Abstract

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 characterizing events to be learned by comparing the convergence responses generated by the input signals at successively different levels of convergence threshold. The convergence threshold is altered until an acceptable range of convergence is reached, and then the pattern of convergence is learned. The pattern of convergence is stored for future reference. In recognition mode, the input signals are again processed at successively different convergence threshold levels until an acceptable range of convergence is reached. The pattern of convergence is then compared to the stored convergence patterns of known events to determine if the event is known. Also disclosed are methods of operating the operatus to recognize events whose input signals are cluttered by noise or which have input patterns which are incomplete. Also disclosed are a method and apparatus for learning the differences between a first event and another event with which the first event was confused during the learning mode.

Claims

1. An apparatus for associating an input event with a previously learned event comprising an association matrix having a sparse forward matrix characterized by a plurality of input lines randomly coupled by programmable contacts to a plurality of target lines and further comprising a plurality of programming lines, where each programmable contact is comprised of a select transistor coupled to said input line and to said target line and a floating gate MOS contact transistor coupled to said select transistor and to said programming line, and further comprising means coupled to each of said input lines, programming lines and target lines to place predetermined voltages on these lines during a learning mode to cause the charge stored on the floating gates of selected contact transistors to be altered in accordance with a forward matrix learning rule and for placing predetermined voltages on said input, target and programming lines during a recognition mode for allowing selected select and contact transistors to drain amounts of charge out of selected target lines in accordance with the amount of charge stored on the floating gates of said selected contact transistors.

2. An apparatus as defined in claim 1 further comprising means for implementing a convergence rule for learning and for recognition, said means for implementing a convergence rule further including a means for altering the convergence threshold automatically on successive repetitions of the input event and further comprising a feedback matrix means coupled to all said target lines by a plurality of programmable contacts having the same structure as said contacts in said forward matrix for sensing when convergence has occurred on any particular target line and for programming the charge on the floating gates of contacts in said feedback matrix in accordance with a predetermined feedback matrix learning rule which allows target lines to converge more easily in recognizing an input event when it occurs in the future even though the input event may not be characterized in the future by as much information as the same input event was characterized by when it was first learned.

3. An apparatus for learning of events and recognizing an input event as a previously learned event comprising an association matrix means for using a convergence rule to create an output vector and further comprising means for automatically, repetitively altering the convergence threshold used in implementing said convergence rule while attempting to recognize the same input event until an acceptable level of convergence is achieved and establishing the output vector which results at said acceptable level of convergence as the final output vector on a plurality of output lines, and wherein said association matrix means includes a plurality of target lines for which convergence individually occurs or does not occur where convergence on a target line is defined as a predetermined level of signal on said target line, and further comprising a feedback matrix means including a plurality of feedback lines and further comprising a plurality of programmable contacts between said target lines and said feedback lines and wherein said feedback lines are coupled to said output lines, said feedback matrix means for selectively programming all the contacts in said feedback matrix which couple target lines which have converged to an active feedback line where an active feedback line is defined as a feedback line coupled to an output line corresponding to a target line which has converged, where said output vector is defined as a collection of output lines coupled to a corresponding collection of target lines where some of said target lines may have converged and where some of said target lines may not have converged, and where said programming is done so as to make it easier for the same output vector to occur the next time the same input event which created the input vector occurs even if the input vector is not identical because of missing components.

4. The apparatus of claim 3 further comprising means for storing said input vector for purposes of replay of said input event and means for automatically altering said convergence threshold on successive of replays of said input event by re-input of said input vector to said association matrix means until recognition occurs in the form of sufficient convergence of a number of target lines occurs, where sufficiency of convergence is defined as a number of converged target lines which lies within a predetermined range.

5. The apparatus of claim 4 wherein said association matrix includes a forward matrix and wherein the forward matrix of said association matrix means is sparsely populated with randomly spaced contacts.

6. An apparatus for associating an input event with a previously learned event comprising an association matrix and further comprising false positive learning means for causing learning to correctly occur in the case of false positive identifications and wherein said association matrix is comprised of a forward matrix means for learning the characteristics of an input event by unidirectional programming of the transfer characteristics of programmable transducers which randomly couple a plurality of input lines to a plurality of target lines and wherein each said transducter causes a response signal on the corresponding said target line of a programmable magnitude when the corresponding said input line is active, said programming occurring in accordance with a predetermined learning rule based upon convergence of the response magnitude above a predetermined, variable convergence threshold of a sufficient number of target lines where said sufficient number lies within a predetermined range, and wherein said learning rule implemented in said forward matrix means by varying said convergence threshold until said sufficient number of converged target lines occurs and then programming all said transducers coupled to converged target lines to create even greater response signal magnitude the next time each said corresponding input line is active, and further comprising a feedback matrix means coupled to all of said target lines by a plurality of programmable transducers coupling each of a plurality of feedback lines where each feedback line is coupled to one of said target lines at an input end and has an a plurality of output ports coupled by said feedback matrix transducters to each of said target lines and having the same structure as said programmable transducers in said forward matrix means, said feedback matrix means for sensing convergence on said target lines and for programming said feedback matrix transducers such that cross-linking between target lines occurs such that if programming of said feedback matrix transducers is based upon a first set of target lines converging said first set or some first subset of said first set of target lines can be made to converge in the future when the same input event which caused said first set of target lines to converge causes some second subset of said first set of target lines to converge.

7. The apparatus of claim 6 wherein the forward matrix means of said association matrix is sparsely populated by contacts having contacts at only between 15 to 25% of the intersections in said forward matrix means and wherein said false positive learning means includes means to adjust said threshold repetitively until the number of converging target lines is within a predetermined range and then for programming said contacts in said forward matrix and said feedback matrix according to the difference pattern between the old set of converging target lines and the new set of converging target lines.

8. The apparatus of claim 7 further comprising means for allowing said association matrix to learn and recognize input events characterized by input signals which each can have more than two values.

9. An apparatus for recognizing an unknown event if it has been previously learned comprising:

means for learning one or more events by comparing the convergence on a plurality of targets caused by input signals characterizing said event which are randomly coupled to said targets by a variable threshold by varying said threshold and reading the same input signals until the amount of convergence is acceptable and then altering the characteristics of said means for learning so as to make it easier for the same convergence pattern to emerge the next time the same input signals characterizing one of the events learned appear; and

means for storing the pattern of convergence on said targets when learning of an event occurs;

means for receiving and storing the input signals from an unidentified event, altering the convergence threshold in successive readings of the input signals from said unidentified event until a predetermined amount of convergence occurs and then for comparing the convergence pattern which emerges when the acceptable level of convergence occurs to the collection of stored patterns and signalling when a match is found.

10. The apparatus of claim 9 further comprising means for causing the recognition process to occur in the learning mode before learning can occur to determine either that the event has already been learned, the event is recognized incorrectly as an event which has already been learned or that the event is unknown.

11. The apparatus as defined in claim 10 further comprising means in said means for learning for identifying when a false identification has been made in the learning process and for causeing the convergence threshold to be altered until the convergence pattern changes by a predetermined amount and then for causing the means for learning to be altered such that the next the same input signals which were incorrectly identified the new convergence pattern is more likely to appear again and for storing the new convergence pattern as the identifying pattern of the event which was incorrectly identified.

12. An apparatus for recognizing an event comprising:

means for receiving a plurality of input signals and for causing convergence responses on a fraction of a plurality of target lines;

means for comparing the convergence response on each target line to a variable convergence threshold and for generating a signal for each target line which converged;

means for altering said convergence threshold until the number of converged target lines is in an acceptable range or stopping the learning process if an acceptable range cannot be reached and for altering said means for receiving so as to make it easier for the target lines to converge the next time the same set of input signals appear in order to learn said event when the number of converged target lines is within an acceptable range;

means to store the pattern of said output signals for learned events; and

means for recognizing unknown events by receiving the input signals characterizing said events and altering said convergence threshold until the number of converged target lines either does or does not reach an acceptable range ad for signalling no recognition if the acceptable range cannot be reached or no match to a stored pattern is found or for identifying the event if a match is found.

13. A recognition matrix for identifying unknown events from a class of events learned by said matrix comprising:

means for receiving and storing a plurality of input signals charactering an event or object which has been sensed;

a forward matrix means sparsely populated by convergence response generators coupled between randomly selected intersections between a plurality of input lines and a plurality of target lines for receiving from said means receiving and storing a plurality of signals on any of said input lines and for causing convergence responses on selected target lines;

convergence threshold means for establishing a variable convergence threshold at a predetermined level;

comparison means coupled to receive said convergence threshold for comparing the total convergence response on each said target line to said convergence threshold and for generating an output signal for each target line which had a total convergence response which exceeds the current level of said convergence threshold;

means for programming the response circuits in said forward matrix means which are coupled to active input lines and target lines whose convergence response exceeded said convergence threshold so as to alter the convergence responses said response circuits cause the next time said response circuits receive an active input signal when the number of target lines which have sums of convergence responses which exceed the current level of said convergence threshold is within an acceptable range; and

means for altering said convergence threshold under predetermined conditions and for causing said means for receiving and storing to transmit the stored input signals into said forward matrix again and to cause the number of target lines which have sums of convergence responses which exceed said current level of said convergence threshold to again be calculated.

14. A method of learning the characteristics of an event comprising the steps of:

sensing the event using a plurality of sensors each of which senses a particular portion or characteristic of the event;

receiving a set of input signals on a plurality of sensor lines from said sensors and passing them through a matrix characterized by a plurality of said sensor lines and a plurality of target lines where some or all of said sensor lines are coupled to one or more said target lines by response circuits having programmable attributes which define the magnitude of the response on the target line to which said response circuit is coupled when said response circuit receives an active input signal having a predetermined characteristic and where the response circuits are coupled between random pairs of said sensor lines and said target lines and where all said response circuits have their programmable attributes initially set to the same predetermined value, said input signals causing a random spatial distribution of responses on said target lines;

convergence detecting the magnitudes of all the responses on each said target line;

comparing the convergence for each said target line to a convergence threshold value for each target line;

comparing the number of target lines for which the response magnitude sum exceeds said convergence threshold value to a predetermined acceptable range;

altering the convergence threshold value and repeating the above steps until the number of target lines for which the response magnitude sum exceeds the convergence threshold value is within said predetermined acceptable range;

recording the spatial distribution of said responses which characterize the event by altering the programmable attribute of each said response circuit which caused a response on a target line so as to increase the magnitude of response which will be caused by each said response circuit so altered the next time said response circuit receives an active input signal.

15. The method of claim 14 comprising the step of altering the characteristics of selected ones of a plurality of feedback response circuits coupled between the outputs of all said comparators which do said comparison step and selected ones of said target lines so that each target line which has a sum of response magnitudes which exceeds said convergence threshold causes, through the action of one or more of said plurality of feedback response circuits, a feedback response on selected ones of said target lines.

16. The method of claim 15 comprising the step of initially programming of said feedback response circuits to have its programmable characteristic such that no feedback response on any target line can be caused and further comprising the step of programming the feedback response circuits when recording the spatial distribution of responses which characterize the event such that each said target line which has a sum of response magnitudes which exceeds said convergence threshold causes the programmable characteristic of selected ones of said plurality of feedback response circuits to be altered so as to cause a feedback convergence response on each of said target lines which has a sum of response magnitudes which exceeds said convergence threshold.

17. A method of learning an event comprising the steps of:

(1) calculating the convergence on each of a plurality of targets upon which a plurality of input signals randomly cause convergence responses through the action of convergence response circuits coupled to said targets by comparing the total convergence response for each target to a variable convergence threshold;

(2) repeating step 1 for the same input signals and for succesively different convergence thresholds until the number of converged targets is either within an acceptable range or not within an acceptable range and a predetermined limit for the convergence threshold is reached; and

(3) altering the characteristics of the response circuits when an acceptable number of converged targets is found such that, the next time an input signal pattern appears for the same event, the same convergence pattern is more likely to occur even if the input signal pattern includes spurious inputs or even if part of the input signals in the input signal pattern which characterize the event are missing; and

storing the convergence pattern for any event which is so learned.

18. A method of recognizing an unidentified event which has been previously learned comprising the steps of:

(1) learn one or more events in the manner described in claim 17;

(2) calculating the convergence on a plurality of targets caused by a plurality of input signals which characterize the unidentified event and which cause convergence responses on random ones of said targets through the action of convergence response circuits by comparing the total convergence response on each target to a variable convergence threshold;

(3) repeating step 2 with the same input signals but succesively different convergence thresholds until the number of targets which have converged is either within an acceptable range or not within an acceptable range and a predetermined limit for the convergence threshold is reached; and

(4) comparing the convergence pattern for the unidentified event to all the stored convergence patterns for learned events when the acceptable range of convergence has been reached.

19. The method of claim comprising the steps of:

performing the recognition process of claim 18 at the beginning of each learning process to determine if the event to be learned has either been already learned, falsely identified as already learned or is an unknown event;

if the event to be learned has been falsely identified as already learned, altering the convergence threshold in successive steps using the same input signals until the convergence pattern changes by a predetermined amount;

altering the characteristics of selected ones of the response circuits so as to learn the differences of the falsely identified event from the event is was confused with.

20. A method of recognizing an event which has been learned before from a plurality of input signals which characterize said event comprising the steps of:

(1) causing a learning matrix such as that used in claim 9 to learn the characteristics of a plurality of events by programming said matrix in accordance with the method of claim 17;

(2) sensing an unknown event, and storing a plurality of data characterizing said event in a storage means;

(3) adjusting said convergence threshold to be a predetermined value, and exiting the recognition process if the convergence threshold has reached a lower limit;

(4) transmitting on said sensor lines into said matrix from said storage means a plurality of input signals which characterize said event;

(5) counting the number of said target lines which have sums of response magnitudes which exceed said convergence threshold, i.e., have converged, to arrive at a size for the response to the input signals and comparing said size to an acceptance range;

(6) if the size of said response is zero, returning to step (3) to adjust the convergence threshold to a new lower value and continuing to process commencing with step (4);

(7) if the size of said response is greater than a predetermined number, exiting the recognition process and indicating that said event cannot be recognized;

(8) if the size of said response is within said acceptance range, comparing the pattern of target lines which have converged to the known patterns of target lines which converge when inputs signals characterizing one of said events which have been learned by said matrix are input to said matrix;

(9) if the pattern of target lines which have converged matches one of the known pattern, exiting said recognition process and generating a signal identifying the event;

(10) if none of the events in steps 7 through 9 occurs, returning to step 3, adjusting the threshold to a new lower value and repeat the steps defined above starting with step 4 until an exit from the process occurs.

21. A circuit for a recognition system emulating brain cortex comprising:

an input conductor;

a column conductor adjacent to or crossing but not electrically contacting said input conductor;

a capacitor coupled between said column conductor and a first reference voltage source;

switching means for selectively coupling said capacitor to a second voltage source to precharge it to a predetermined value;

a forward matrix contact structure comprising an electrically programmable non volatile memory cell including a select transistor having its select gate coupled to said input conductor and having its drain coupled to said column conductor and a floating gate transistor having its drain coupled to the source of said select transistor and its source selectively coupled to said second reference voltage source through the channel of a programming transistor which has a gate for receiving a signal to render the channel non conductive during programming;

a Schmidt trigger having a variable trigger threshold and having an input for receiving a theta signal controlling the level of said variable trigger threshold and having a trigger input coupled to said column conductor and having an output; and

a monostable multivibrator having its trigger input coupled to the output of said Schmidt trigger and having an output.

22. The apparatus of claim 21 further comprising programming means coupled to the top gate of said floating gate transistor to the gate of said programming transistor and to said column conductor for applying the proper voltage conditions to cause programming of charge on the floating gate of said floating gate transitor when an event is to be learned.

23. The apparatus of claim 22 further comprising a feedback line coupled to said programming means and to the gate of the select transistor in a feedback contact structure identical to the forward matrix contact structure having the drain of its select transistor coupled to said column conductor and having the top gate of the floating gate transistor in said feedback contact structure coupled to said programming means and having its source for coupling to said second reference voltage source through said programming transistor and further comprising means in said programming means for causing the proper voltage conditions for programming of said floating gate transistor in said feedback contact structure when an event is to be learned.

24. An array comprised of a plurality of the structures like that of claim 23 wherein each said input conductor intersects with but does not electrically contact each column conductor but where only a random, small percentage of the intersections of said input conductors and said column conductors are coupled forward matrix contact structures as defined in claim 23 and wherein each column conductor has a Schmidt trigger, a monostable multivibrator, programming means and a feedback line coupled thereto and wherein each feedback line intersects with each column conductor with each intersection couple a feedback contact structure as defined in claim 23.

25. The apparatus of claim 24 further comprising a flip flops coupled to the monostable multivibrator of each column conductor so as to be set to a predetermined logic state each time said monostable multivibrator outputs a pulse and further comprising comparator means for storing patterns, in the learning mode, of flip flops which have been set when an event is to be learned and, in the recognition mode, for comparing the pattern of said flip flops which have been set to said predetermined logic state when a wave of input signals characterizing an event to be recognized have been applied to said input conductors said comparison being made to the patterns of logic states which said flip flops have assumed for previously learned events.

26. The apparatus of claim 25 further comprising control means in and controlling said programming means for causing each said event to be recognized to be stored in an input buffer coupled to said input lines and for setting said theta signal at a predetermined level and causing the input signals stored in said input buffer and characterizing the event to be recognized to be applied to said input lines in a first wave and for causing the number of flip flops which have been set to be calculated after said first wave of input signals have been processed and for continuously causing the theta signal to be adjusted and the same wave of input signals to be applied to said input conductors by said input buffer until the number of flip flops which have been set is within an acceptable range, and for causing said comparison means to perform its comparison when said acceptable range has been reached and for preventing comparison when the acceptable range cannot be reached for any theta signal in a predetermined range.

27. An apparatus as defined in claim 26 wherein said control means causes a recognition procedure to be performed in the learning mode before any learning programming by said programming means is triggered by said control means.

28. An apparatus as defined in claim 27 wherein said control means causes the programming means to program the appropriate forward matrix contact structures and the feedback contact structures after a no recognition exit from said recognition procedure and after the theta signal has been adjusted from the level it had when the no recognition exit occurred until the number of flip flops which have been set is within an acceptable range and for causing the pattern of said flip flops which are set when the acceptable range has been reached to be stored in said comparator means.

29. An apparatus as defined in claim 28 wherein said control means functions to recognize when a false positive identification has occurred and to further adjust said theta signal and to cause the same inputs signals which were falsely recognized to again be applied by said input buffer to said input conductors until the number of flip flops which are set assumes a new value which is greater by a predetermined range than the number which were set in response to the input signals when they were first falsely identified and further comprising false positive programming means in said programming means for each said column conductor for causing selected ones of said forward matrix contact structures and said feedback contact structures to be programmed after the predetermined range of newly set flip flops has been reached by adjustment of the theta signal so that the difference characteristics of the falsely identified event may be learned.

30. The apparatus of claim 29 wherein said control means also causes the learning-procedure to be exited with no learning in the case of a false positive identification where the predetermined range of newly set flip flops cannot be reached by adjustment of said theta signal.

31. A circuit for emulating the function of certain areas of the brain comprising:

a plurality of input conductors;

an output conductor;

charge storage means coupled to said output conductor for storing charge;

a convergence memory means associated with random pairs of said input conductors and said output conductor for storing a predetermined convergence value in response to a learn signal;

coupling means coupled between the same random pairs of said input conductors and said output conductor as said convergence memory means each for draining a variable amount of charge out of said charge storage means when an input signal appears on the associated said input conductor of the pair of conductors to which said coupling means is coupled where the amount of charge drained depends upon said convergence value stored in the associated one of said convergence memory means;

trigger means for triggering when the charge on said charge storage means reaches a certain level and outputting a predetermined output signal; and

programming means for supplying said learn signal to only the ones of said convergence memory means which are associated with an input conductor which received a predetermined input signal and only if said trigger means has triggered.

32. An array comprising:

a plurality of input lines;

a plurality of column conductors adjacent to or crossing said input lines but not electrically contacting them;

a plurality of capacitors each having one terminal coupled to one of said column conductors and another terminal coupled to a first reference voltage source;

switching means for selectively coupling each said capacitor to a second voltage source at a predetermined time;

a plurality of first means each coupled between ramdomly selected input conductors and randomly selected column conductors for draining a predetermined amount of charge out of the capacitors coupled to the selected column conductors when input signals arrives on the corresponding input conductor or conductors coupled to said column conductor by one or more first means;

a plurality of Schmidt triggers each having a variable trigger threshold each having a trigger input coupled to one of said column conductors and each having an output; and

a plurality of monostable multivibrators each having its trigger input coupled to the output of one of said Schmidt triggers and each having a recognition output.

33. An array as defined in claim 32 further comprising a programming means coupled between the recognition outputs of the monostable multivibrators and each said first means coupled to said column conductors for changing the amount of charge drained out of the capacitor corresponding to the associated column conductor by selected ones of said first means the next time the selected first means receive an input signal.

34. The apparatus of claim 33 further comprising feedback lines coupled to the recognition output of said monostable multivibrators of each column conductor through said programming means each said feedback conductor coupled to each said column conductor by second means for draining a predetermined amount of charge out of the corresponding column conductor when said feedback conductor carries a signal from said monostable multivibrator indicating the Schmidt trigger threshold has been exceeded.

35. The apparatus of claim 34 further comprising control means coupled to said programming means for causing in the recognition mode input signals characterizing the event to be recognized to be input repeatedly and for adjusting the threshold level of each Schmidt trigger until the number of Schmidt triggers which have triggered is in an acceptable range and for then comparing the pattern of Schmidt triggers which have triggered to known patterns of previously learned events, and, in the learning mode for causing the input signals of an event to be learned to be repeatedly input while varying the threshold level until the number of Schmidt triggers which have triggered is within an acceptable range and then for causing said programming means to program all first means coupled to input signal lines which are active and to column conductors which have had their Schmidt triggers trigger and for causing the pattern of Schmidt triggers which have triggered to be saved for future reference in the recognition mode.

37. An apparatus for learning events comprised of the apparatus as defined in claim 36 and further comprising:

means in said control means for causing the sequence of recognition events defined in claim 35 to be performed as the first action when an event is to be learned, and for determining whether or not recognition occurred, and, if no recognition occurred, for repeatedly causing the input signals for said event to be learned to be input from said input buffer with successively different thresholds until the number of said target conductors which have converged is within an predetermined range and for then causing predetermined learning control signals to be generated; and

programming means coupled to said comparison means, to said target conductors and to said convergence contact means and to said feedback convergence response generating means and to said control means to receive said learning control signals and to cause the proper conditions to exist so as to alter the characteristics of the convergence response generating means and said feedback convergence response generating means so that the next time convergence responses are generated by either or both of the convergence response generating means and/or the feedback convergence response generating means, the magnitude of the response so generated is greater, and for causing the pattern of converged target lines to be stored for future reference in recognition mode.

38. The apparatus of claim 37 further comprising means in said control means for determining if any recognition which occurrs during learning mode is correct or incorrect and if correct for signalling that the event has already been learned and that the apparatus is ready to learn a new event, and if incorrect, for altering the threshold on successive inputs of the same input signals characterizing the event incorrectly recognized until a predetermined range of newly converged target conductors appears and then for generating false positive learning control signals and wherein said programming means includes means for receiving said false positive learning control signals and for altering the characteristics of selected ones of said convergence response generating means and said feedback convergence response generating means to cause learning of the difference pattern of convergence of said target conductors.

36. An apparatus for recognizing degraded information characterizing an event for which characterizing information has been previously learned by said apparatus comprising:

an input buffer for storing a plurality of data characterizing an event and for converting said data into input signals which reflect the values of said data on a plurality of output lines;

a plurality of convergence target conductors;

a plurality of input conductors coupled to said output lines;

a forward matrix of a plurality of convergence response generating means coupled to randomly selected pairs of input conductors and target conductors for receiving incoming signals on each input conductor and causing convergence responses on one or more target conductors;

convergence detecting means for each said convergence target conductor for convergence detecting the convergence responses for each said target conductor;

comparison means for comparing the convergence sum for each target conductor to a convergence threshold signal at a threshold input and for generating an output signal on an output line for each said convergence target conductor which indicates whether its convergence sum exceeded said threshold that is has converged; and

a feedback matrix comprised of a plurality of feedback lines each coupled to one of said output lines from said comparison means to a plurality of feedback convergence response generating means coupled to each target conductor for causing feedback convergence responses on each of the target conductors coupled by a feedback convergence response generating means to a feedback line carrying an active output signal;

control means coupled to said threshold input of said comparison means for causing said input signals to be repeatedly input at different levels of said threshold for said comparison means from said input buffer and to alter said threshold from an initial value which minimizes the number of target conductors which have converged to successively different values which tend to cause successively more target conductors to converge until an predetermined range of convergence among target conductors is reached, and then for causing the pattern of converged target conductors to be compared to known stored patterns of events which have been previously learned.