Patent US2055370A successfully refreshed from Google Patents.
Patent US5440670A successfully refreshed from Google Patents.
US5440670A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Error control system and method
Assignee: Texas Instruments Inc
•
Filing: 1994-01-03
•
Granted: 1995-08-08
•
Expires: 2014-01-03
Abstract
Abstract Code word generation by recursive reverse flows in a neural network, and transmission systems encoding using such code words. The neural network (30) may be an array of operational amplifiers (34) as neurons with inverted amplifier output feedback through resistors (32) as the interconnection strengths to the amplifier inputs. The inversion of the amplifier output implies the dynamical flow of the neuron states is away from stored vectors; this contrasts with Hopfield networks which have a dynamical flow to stored states and thus an associative memory function. The method of generating code words recursively uses this reverse dynamical flow with previously generated code words as the stored vectors. That is, the already generated code words define the stored vectors in a neural network, then the reverse dynamical flow finds a new vector away from the stored vectors, and lastly this new vector defines the next code word and the cycle repeats with the augmented set of stored vectors.
Inventors
- 👤 Gary A. Frazier
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-05 13:10
CPC Classifications
G; G06; G06F; G06F11/00; G06F11/07; G06F11/08; H; H03; H03M; H03M13/00; H03M13/65; H03M13/6597; H04; H04L; H04L1/00; H04L1/004; H04L1/0045; H04L25/00; H04L25/02; H04L25/03; H04L25/03006; H04L25/03165
Claims Analysis
Total Claims: 8
Claim 1
Independent Claim
47 words
A method of information transmission, comprising the steps of: (a) recursively generating code words in a neural network as successive states resulting from reverse dynamic flows; (b) encoding symbols by said code words; (c) transmitting said code words; and (d) decoding said transmitted code words into symbols.
Claim 2
Independent Claim
47 words
A method of information transmission, comprising the steps of: (a) recursively generating code words in a neural network as successive states resulting from reverse dynamic flows; (b) encoding symbols by said code words; (c) transmitting said code words; and (d) decoding said transmitted code words into symbols.
Claim 3
Dependent Claim
238 words
The method of claim 1, wherein: (a) said code words include a sequence of K N-bit binary words; and (b) said recursive generation includes the steps of: (i) providing a neural network with N neurons, each neuron has two states with output values 0 and 1, interconnection strengths T ij connecting the output of the jth neuron to an input of the ith neuron, and dynamical evolution given by V.sub.i →1 if Σ.sub.j T.sub.ij V.sub.j <θ.sub.i and V.sub.i →0 if Σ.sub.j T.sub.ij V.sub.j >θ.sub.i where V i is the output value of the ith neuron and θ i is a threshold; (ii) providing an initial N-bit binary code word U 1 with components U j 1 . (iii) setting said interconnection strengths T ij =U i 1 .1 U j 1 for all i and j except setting T ii =0; (iv) inputting U 1 into said neural network, and letting said neural network evolve to a stable state V; (v) taking said stable state V to define a new binary code word U 2 ; (vi) updating said interconnection strengths by adding U i 2 U j 2 to the current T ij for all i and j except i=j; (vii) repeating steps (iv)-(vi) with U k replaced by U k+1 for k=1, 2, . . . , K-1; and (viii) taking U 1 , U 2 , . . . U K as said code words.
Claim 4
Dependent Claim
26 words
The method of claim 2, wherein: (a) said providing an initial N-bit binary code word U 1 of claim 2 step (b)(ii) is by random selection.
Claim 5
Dependent Claim
184 words
The method of claim 1, wherein: (a) said code words include a sequence of K N-bit binary words; and (b) said recursive generation includes the steps of: (i) providing a Hopfield neural network with N neurons but with dynamical evolution away from stored states defining the interconnection strengths; (ii) providing an initial N-bit binary code word U 1 ; (iii) setting the interconnection strengths of said neural network T ij =U i 1 U j 1 for all i and j except setting T ii =0; (iv) inputting U 1 into said neural network, and letting said neural network evolve to a stable state V; (v) taking said stable state V to define a new binary code word U 2 ; (vi) updating said interconnection strengths by adding U i 2 U j 2 to the current T ij for all i and j except i=j; (vii) repeating steps (iv)-(vi) with U k replaced by U k+1 for k=1, 2, . . . , K-1; and (viii) taking said U 1 , U 2 , . . . U k as said code words.
Claim 6
Dependent Claim
21 words
The method of claim 4, wherein: (a) said providing an initial N-bit binary code word U 1 is by random selection.
Claim 7
Dependent Claim
65 words
An information transmission system, comprising: (a) a neural network for recusively generating a set of code words as successive states resulting from reverse dynamic flows; (b) an encoder for encoding symbols by said set of code words; (c) a transmission channel, coupled between said encoder and a decoder, for transmitting said code words; and (d) said decoder for decoding said transmitted code words into symbols.
Claim 8
Dependent Claim
65 words
An information transmission system, comprising: (a) a neural network for recusively generating a set of code words as successive states resulting from reverse dynamic flows; (b) an encoder for encoding symbols by said set of code words; (c) a transmission channel, coupled between said encoder and a decoder, for transmitting said code words; and (d) said decoder for decoding said transmitted code words into symbols.
References Cited (Backward Citations)
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 1998-08-07 | 1999-02-06 | 1999-08-08 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2002-08-07 | 2003-02-06 | 2003-08-08 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2006-08-07 | 2007-02-06 | 2007-08-08 | $7700.00 | Window Closed / Lapsed |