Claims Analysis
Total Claims: 11
Claim 1
Independent Claim
149 words
Pattern recognition system, comprising: transducer means for sensing a pattern to be recognized and outputting sequential data signals representative of the pattern to be recognized, characterized in that it further comprises an array (12) of interconnected probabilistic Learning elements (14a-14h) of the type that receive sequences of objects and output sequences of recognized states, said array of Learning elements being interconnected to have a number of input Learning elements (14a-14h) and a number of output Learning elements (14c-14h), means (22) for receiving and partitioning the input data between the input Learning elements (14a-14d) of the array, whereby the partitioned input data forms objects provided to the input Learning elements in an overLapping and redundant manner; and means (16) for collecting and combining the recognized state sequences from the output Learning elements (14c-14h) of the array to provide a sequence of recognized patterns as an output of the Learning system.
Claim 2
Dependent Claim
149 words
Pattern recognition system, comprising: transducer means for sensing a pattern to be recognized and outputting sequential data signals representative of the pattern to be recognized, characterized in that it further comprises an array (12) of interconnected probabilistic Learning elements (14a-14h) of the type that receive sequences of objects and output sequences of recognized states, said array of Learning elements being interconnected to have a number of input Learning elements (14a-14h) and a number of output Learning elements (14c-14h), means (22) for receiving and partitioning the input data between the input Learning elements (14a-14d) of the array, whereby the partitioned input data forms objects provided to the input Learning elements in an overLapping and redundant manner; and means (16) for collecting and combining the recognized state sequences from the output Learning elements (14c-14h) of the array to provide a sequence of recognized patterns as an output of the Learning system.
Claim 3
Dependent Claim
181 words
A system as claimed in claim 1, wherein each of said elements includes means (28) for receiving objects, means (80, 152, 154, 156) for storing said received objects, sequences of received objects, previously Learned states, sequences of previously Learned states and predetermined types of knowledge relating to sequences of previously Learned states, previously Learned states and the objects and sequences of objects contained therein whereby information relating to currently received objects is stored as well as statistical information relating to previously Learned states and the objects contained therein, means (32) for correlating the stored current object information with the stored statistical information for assigning probabilities to possible next states in the sequence of recognized states, means (34) responsive to said probabilities of next states for determining the most LikeLy next state, means (102) responsive to the stored information for providing a signal corresponding to the probability that the state has ended, means (188) responsive to the end of state probability signal (I E ) for outputting the most LikeLy next state as a recognized next state in the recognized states sequence.
Claim 4
Dependent Claim
28 words
A system as claimed in claim 1 or 2, wherein the array (12) comprises eight probabilistic Learning elements (14a-14h) arranged in two columns (14a-14d, 14e-14h) of four elements.
Claim 5
Dependent Claim
36 words
A system as claimed in claim 1 or 2, wherein the array is arranged in n+1 columns with each column having K n power Learning eLements, wherein n and K are each integers greater than 1.
Claim 6
Independent Claim
35 words
A system as claimed in any one of the preceding claims, wherein each element (Fig. 5) additionaLLy comprises means (34) for providing a signal corresponding to a rating of confidence in the recognized next state.
Claim 7
Dependent Claim
43 words
A system, as claimed in claim 5, wherein each element additionally comprises means responsive to the signal corresponding to a rating of confidence to cause said element to Learn the recognized state sequence when the rating of confidence exceeds a predetermined threshold LeveL.
Claim 8
Dependent Claim
52 words
A system as claimed in claim 6, wherein the signal corresponding to a rating of confidence from a particuLar Learning element is fed back to the responsive means of the element and to the responsive means of each Learning element having an output connected to a receiving means of the particular element.
Claim 9
Independent Claim
33 words
A system as claimed in any one of the preceding cLaims, additionaLLy comprising a Learning supervision means responsive to external reinforcement signals to cause said elements to Learn the Lastest recognized state sequence.
Claim 10
Dependent Claim
23 words
A system as claimed in claim 8, additionally comprising means for correcting a recognized state sequence prior to initiating an external reinforcement signal.
Claim 11
Independent Claim
24 words
A system as claimed in any one of the preceding claims, wherein the means for collecting and combining includes an error correcting decoding means.