Information processing system using threshold passive modification

Claim 1

An information processing system comprising, in combination: a. a plurality (n) of input terminals 1, 2 . . . ,j . . . , N adapted to receive N input signals s 1 , s 2 . . . ,s j . . . ,s N , respectively; b. a plurality (n) of output terminals 1, 2 . . . , i . . . , n adapted to present n output responses r 1 ,r 2 . . . ,r i . . . , r n , respectively; c. a plurality of junction elements, called mnemonders, each mnemonder coupling one of said input terminals (input j) with one of said output terminal (output i) and providing a transfer of information from input j to output i in dependence upon the signal s j appearing at the input j and upon the mnemonder transfer function A ij ; and d. means for modifying the transfer function A ij of at least one of said mnemonders, when in a learning mode, in dependence upon the product of at least one of said input signals and one of said output responses; wherein modifications to the transfer functions of the mnemonders, when in a learning mode, take the form: A.sub.ij (t)=γA.sub.ij (t-1)+δA.sub.ij (t) where δA ij (t) has the form: δA.sub.ij (t)=η(r.sub.i)r.sub.i s.sub.j where A ij (t) is the new (modified) transfer function, A ij (t-1) is the previous transfer function, γ is a decay constant in the range 0≦γ≦1 and η is a variable learning constant that is dependent upon the output r i .

Claim 14

A method of processing information comprising the steps of: a. receiving a plurality of input signals s 1 ,s 2 . . . , s j . . . ,s N , b. producing a plurality of intermediate signals s' i1 , s' i2 , . . . s' ij . . . ,s' iN , each s' ij of which is dependent upon a respective one of said input signals s j and an associated transfer function A ij ; c. producing an output response r i which is dependent upon at least one of said intermediate signals s' ij ; and d. modifying at least one of said transfer functions A ij , when in a learning mode, according to the formula: A.sub.ij (t)=γA.sub.ij (t-1)+δA.sub.ij (t) where δA ij (t) has the form: δA.sub.ij (t)=η(r.sub.i)r.sub.i s.sub.j (t) where A ij (t) is the new (modified) transfer function, A ij (t-1) is the previous transfer function, γ is a decay constant in the range 0≦γ≦1 and η is a variable learning constant that is dependent upon the output r i .

Claim 15

A method of processing information comprising the steps of: a. receiving a plurality of input signals s 1 ,s 2 . . . , s j . . . ,s N , b. producing a plurality of intermediate signals s' i1 , s' i2 , . . . s' ij . . . ,s' iN , each s' ij of which is dependent upon a respective one of said input signals s j and an associated transfer function A ij ; c. producing an output response r i which is dependent upon at least one of said intermediate signals s' ij ; and d. modifying at least one of said transfer functions A ij , when in a learning mode, according to the formula: A.sub.ij (t)=γA.sub.ij (t-1)+δA.sub.ij (t) where δA ij (t) has the form: δA.sub.ij (t)=η(r.sub.i)r.sub.i s.sub.j (t) where A ij (t) is the new (modified) transfer function, A ij (t-1) is the previous transfer function, γ is a decay constant in the range 0≦γ≦1 and η is a variable learning constant that is dependent upon the output r i .

Claim 19

The method defined in any one of claims 13-16 wherein η is larger than zero for r i ≦θ M , where θ M is the modification threshold, and smaller than zero for r i< θ M .