Systems and methods for brain-like information processing
원문보기
IPC분류정보
국가/구분
United States(US) Patent
등록
국제특허분류(IPC7판)
G06N-005/00
G06F-001/00
출원번호
US-0968154
(2010-12-14)
등록번호
US-8655797
(2014-02-18)
발명자
/ 주소
Yoder, Lane D.
출원인 / 주소
Yoder, Lane D.
인용정보
피인용 횟수 :
0인용 특허 :
15
초록▼
Logic circuits provide networks to simulate the functions of neural networks of the brain, and can discriminate degrees of state, and combinations of degrees of state, corresponding to a number of neurons. Logic circuits comprise Recursive AND NOT Conjunctions (RANCs), or AND NOT gates. A RANC is a
Logic circuits provide networks to simulate the functions of neural networks of the brain, and can discriminate degrees of state, and combinations of degrees of state, corresponding to a number of neurons. Logic circuits comprise Recursive AND NOT Conjunctions (RANCs), or AND NOT gates. A RANC is a general logic circuit that performs conjunctions for 2n possible combinations of truth values of n propositions. The RANCs function dynamically, with capabilities of excitation and inhibition. Networks of RANCs are capable of subserving a variety of brain functions, including creative and analytical thought processes. A complete n-RANC produces all conjunctions corresponding to the 2n possible combinations of truth values of n propositions.
대표청구항▼
1. A decoder/multiplexer logic circuit capable of performing Boolean and fuzzy logic on conjunctions for 2n possible combinations of truth values of n propositions comprising: one or more AND NOT gates, each AND NOT gate configured to provide a measure of the difference between a first (X) and secon
1. A decoder/multiplexer logic circuit capable of performing Boolean and fuzzy logic on conjunctions for 2n possible combinations of truth values of n propositions comprising: one or more AND NOT gates, each AND NOT gate configured to provide a measure of the difference between a first (X) and second (Y) input value, each in the interval [0,1], wherein the measure of the difference X−Y, is defined by:1) when X=1 and Y=0, the measure of the difference is 1;2) when X is less than or equal to Y, the measure of the difference is 0; and3) when X is greater than Y, the measure of the difference is an increasing function of X and a decreasing function of Y. 2. The logic circuit of claim 1, wherein each AND NOT gate comprises an input for excitation and an input for inhibition. 3. The logic circuit of claim 1, wherein the inputs to the decoder correspond to outputs from retinal cones, and wherein each decoder output generates a neural correlate of color vision. 4. The logic circuit of claim 1, wherein the inputs to the decoder correspond to olfactory receptor outputs, and wherein the outputs of the decoder comprise signals to discriminate odors. 5. The logic circuit of claim 1, wherein each AND NOT gate comprises four transistors. 6. The logic circuit of claim 1, wherein each AND NOT gate comprises an X input and a Y input, the X input coupled to the gates of a first N-channel MOSFET transistor and a first P-channel MOSFET transistor, and the Y input coupled to the gates of a second P-channel MOSFET transistor and a second N-channel MOSFET transistor, wherein the drain of the first N-channel transistor is coupled to the source of the second P-channel transistor, the source of the first P-channel transistor is coupled to a source voltage, the source of each of the first P-channel and second N-channel transistors coupled to ground, and the drains of each of the first and second P-channel and second N-channel transistors are coupled to an output. 7. The logic circuit of claim 1, wherein each AND NOT gate comprises three transistors. 8. The logic circuit of claim 7, wherein each AND NOT gate comprises an X input and a Y input, the X input coupled to the gate of a first P-channel MOSFET transistor and a source of a second P-channel MOSFET transistor, and the Y input coupled to the gates of the second P-channel MOSFET transistor and a first N-channel MOSFET transistor, wherein the source of each of the first P-channel transistor and the first N-channel transistor is coupled to ground, and the drains of each of the first and second P-channel and first N-channel transistors are coupled to an output. 9. The logic circuit of claim 1, wherein each AND NOT gate comprises an X input and a Y input, the X input coupled to a first input of first and second operational amplifiers, and the Y input coupled to second inputs of first and second operational amplifiers, the output of the amplifiers summed to provide an output that is the larger of zero and the sum of X−Y. 10. The logic circuit of claim 9, comprising first and second AND NOT gates configured to form a MAX gate, the max gate comprising a first (X) input and a second (Y) input, wherein: the first input to the first AND NOT gate is interconnected to the X input and the second input to the first AND NOT gate interconnected to the output of the second AND NOT gate,the first input to the second AND NOT gate is interconnected to the output of the first AND NOT gate, and the second input to the second AND NOT gate is interconnected to the Y input,wherein the outputs of the first and second AND NOT gates are inverted and summed thereby providing an output corresponding to the maximum value of the X and Y inputs. 11. The logic circuit of claim 10 further comprising a first and second MAX gate, and first and second memory bits configured as a flip flop circuit comprising a first (S) input and a second (R) input, wherein: the first input to the first MAX gate is interconnected to the S input and the second input to the first MAX gate is interconnected to the output of the second memory bit;the first input to the second MAX gate is interconnected to the output of the first memory bit and the second input to the second MAX gate is interconnected to the R input;the output of the first MAX gate is inverted and interconnected to an input of the first memory bit, the first memory bit configured to output the difference between a logical one and the inverted output of the first MAX gate;the output of the second MAX gate is inverted and interconnected to an input of the second memory bit, the second memory bit configured to output the difference between the inverted second MAX gate output and logical one, the output of the second memory bit is thereby configured to output the first (S) input until the second (R) input is a logical one. 12. The logic circuit of claim 10, further comprising a plurality of MAX gates and a plurality of inputs, the plurality of inputs interconnected to respective inputs of MAX gates, and the plurality of MAX gates interconnected to provide an output that corresponds to an input of the plurality of inputs having a maximum value. 13. The logic circuit of claim 1, comprising a plurality of AND NOT gates configured to receive a plurality of inputs and output the maximum value of the plurality of inputs, thereby functioning as a fuzzy OR gate. 14. A decoder/multiplexer logic circuit, with n inputs and 2n outputs for any positive integer n, capable of performing Boolean and fuzzy logic comprising: a plurality of AND NOT gates, each configured to provide a measure of the difference between a first (X) and second (Y) input value, each in the interval [0,1], wherein the measure of the difference X−Y is defined by:1) when X=1 and Y=0, the measure of the difference is 1;2) when X is less than or equal to Y, the measure of the difference is 0; and3) when X is greater than Y, the measure of difference is an increasing function of X and a decreasing function of Ythe plurality of AND NOT gates configured to provide for each subset of input values an output that is a measure of the difference between a first number that is the minimun of the subset and a second number that is a maximum of the inputs not in the subset. 15. The logic circuit of claim 14, wherein each AND NOT gate comprises an input for excitation and an input for inhibition. 16. The logic circuit of claim 14, wherein one or more of the AND NOT gates comprises four transistors. 17. The logic circuit of claim 14, wherein one or more of the AND NOT gates comprises an X input coupled to the gates of a first N-channel MOSFET transistor and a first P-channel MOSFET transistor, and a Y input coupled to the gates of a second P-channel MOSFET transistor and a second N-channel MOSFET transistor, wherein the drain of the first N-channel transistor is coupled to the source of the second P-channel transistor, the source of the first P-channel transistor is coupled to a source voltage, the source of each of the first P-channel and second N-channel transistors coupled to ground, and the drains of each of the first and second P-channel and second N-channel transistors are coupled to an output. 18. The logic circuit of claim 14, wherein one or more of the AND NOT gates comprises three transistors. 19. The logic circuit of claim 18, wherein one or more of the AND NOT gates comprises an X input coupled to the gate of a first P-channel MOSFET transistor and a source of a second P-channel MOSFET transistor, and a Y input coupled to the gates of the second P-channel MOSFET transistor and a first N-channel MOSFET transistor, wherein the source of each of the first P-channel transistor and the first N-channel transistor is coupled to ground, and the drains of each of the first and second P-channel and first N-channel transistors are coupled to an output. 20. The logic circuit of claim 14, wherein one or more of the AND NOT gates comprises an X input coupled to a first input of first and second operational amplifiers, and a Y input coupled to second inputs of first and second operational amplifiers, the output of the amplifiers summed to provide an output that is the larger of zero and the sum of X−Y.
Said Labreche FR; Hicham Amine FR; Tze Tsung Tan FR; Fran.cedilla.ois Loubet FR, Classifying apparatus using a combination of statistical methods and neuronal networks, designed in particular for odour recognition.
Giles C. Lee ; Omlin Christian Walter ; Thornber Karvel Kuhn, Deterministic encoding of fuzzy finite state automata in continuous recurrent neural networks.
Rahman Sayeedur C. (San Francisco CA) Khan Emdadur R. (San Jose CA), Neural-fuzzy logic control system with adjustable fuzzy logic membership functions.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.