Magnetic reproduction processing device, magnetic recording / reproducing device, and magnetic reproducing method

Abstract

To provide a magnetic reproduction processing device, a magnetic recording / reproducing device, and a magnetic reproducing method capable of suppressing errors.SOLUTION: According to an embodiment, a magnetic reproduction processing device includes a decoder and an error correction decoder. A first signal based on a reproduction signal is input to the decoder. A signal based on a second signal output from the decoder is input to the error correction decoder. The error correction decoder corrects errors of the second signal on the basis of a check matrix. The decoder includes a neural network layer. The neural network layer includes a plurality of computation nodes. A connection relation of the plurality of computation nodes is based on the check matrix.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] An embodiment of the present invention relates to a magnetic reproducing processing device, a magnetic recording and reproducing device, and a magnetic reproducing method. [Background technology]

[0002] For example, fewer errors are desired in magnetic regeneration processing equipment. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] U.S. Pat. No. 10,804,938 Summary of the Invention [Problem to be solved by the invention]

[0004] The embodiments of the present invention provide a magnetic reproducing processing device, a magnetic recording and reproducing device, and a magnetic reproducing method that can suppress errors. [Means for solving the problem]

[0005] According to an embodiment of the present invention, a magnetic reproducing processing device includes a decoder and an error correction decoder. A first signal based on a reproduced signal is input to the decoder. A signal based on a second signal output from the decoder is input to the error correction decoder. The error correction decoder corrects an error in the second signal based on a check matrix. The decoder includes a neural network layer. The neural network layer includes a plurality of calculation nodes. A connection relationship of the plurality of calculation nodes is based on the check matrix. [Brief description of the drawings]

[0006] [Figure 1] FIG. 1 is a schematic diagram illustrating a magnetic reproducing processing device and a magnetic recording and reproducing device according to the first embodiment. [Diagram 2]FIG. 2 is a schematic view illustrating the magnetic regeneration processing device according to the first embodiment. [Diagram 3] FIG. 3 is a schematic view illustrating the magnetic regeneration processing device according to the first embodiment. [Figure 4] FIG. 4 is a schematic view illustrating the magnetic regeneration processing device according to the first embodiment. [Diagram 5] FIG. 5 is a schematic view illustrating the magnetic regeneration processing device according to the first embodiment. [Figure 6] FIG. 6 is a schematic view illustrating the magnetic regeneration processing device according to the first embodiment. [Figure 7] FIG. 7 is a schematic diagram illustrating the magnetic regeneration processing device according to the embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0007] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. The drawings are schematic or conceptual, and the relationship between the thickness and width of each part, the size ratio between parts, etc. are not necessarily the same as in reality. Even when the same part is shown, the dimensions and ratios of each part may be different depending on the drawing. In this specification and each drawing, elements similar to those described above with reference to the previous drawings are given the same reference numerals and detailed descriptions thereof will be omitted as appropriate.

[0008] (First embodiment) FIG. 1 is a schematic diagram illustrating a magnetic reproducing processing device and a magnetic recording and reproducing device according to the first embodiment. 1, a magnetic recording and reproducing device 210 according to the embodiment includes a magnetic reproducing processing device 110 according to the embodiment. The magnetic recording and reproducing device 210 may further include a magnetic recording and reproducing unit 80D.

[0009] The magnetic recording and reproducing unit 80D includes a magnetic recording medium 80. The magnetic recording medium 80 may include, for example, a magnetic disk (HDD: Hard Disk Drive) or the like. The magnetic recording and reproducing unit 80D may include, for example, an SSD (Solid State Drive). The magnetic recording and reproducing unit 80D may include, for example, a recording and reproducing unit 80R. The recording and reproducing unit 80R may include, for example, a magnetic head 80H. The recording and reproducing unit 80R (magnetic head 80H) records information on the magnetic recording medium 80. The recording and reproducing unit 80R (magnetic head 80H) reproduces the information recorded on the magnetic recording medium 80. A reproduction signal Sig-r is obtained from the recording and reproducing unit 80R. The reproduction signal Sig-r may be, for example, a continuous or discontinuous signal in a time series.

[0010] The reproduction signal Sig-r obtained by the magnetic recording and reproducing unit 80D (recording and reproducing unit 80R) is supplied to the magnetic reproducing processing device 110. The reproduction signal Sig-r is processed (decoded) by the magnetic reproducing processing device 110. The result of the processing by the magnetic reproducing processing device 110 (decoded) is output from the magnetic reproducing processing device 110 as a decoded signal Sig-c. The decoded signal Sig-c is, for example, a binary signal.

[0011] The magnetic reproducing processing device 110 includes a decoder 71 and an error correction decoder 72. A first signal S1 based on the reproduced signal Sig-r is input to the decoder 71. A signal based on the second signal S2 output from the decoder 71 is input to the error correction decoder 72.

[0012] The error correction decoder 72 is configured to correct errors in the second signal S2 based on the check matrix H. In this example, the check matrix H is a matrix corresponding to 6 bits.

[0013] The decoder 71 includes a neural network layer 71L. The neural network layer 71L includes a plurality of calculation nodes 71N. In this example, the number of the plurality of calculation nodes 71N is six. The number of the plurality of calculation nodes 71N corresponds to the number of a plurality of bits in the parity check matrix H. In this example, the plurality of calculation nodes 71N includes a first node N1, a second node N2, a third node N3, a fourth node N4, a fifth node N5, and a sixth node N6.

[0014] In the embodiment, the connection relationship of the multiple calculation nodes 71N is based on the parity check matrix H. In this example, the first node N1 is connected to the second node N2 and the third node N3. The second node N2 is connected to the first node N1 and the third node N3. The third node N3 is connected to the first node N1, the second node N2, and the fourth node N4. The fourth node N4 is connected to the third node N3, the fifth node N5, and the sixth node N6. The fifth node N5 is connected to the fourth node N4 and the sixth node N6. The sixth node N6 is connected to the fourth node N4 and the fifth node N5.

[0015] In the embodiment, the connection relationship of the multiple calculation nodes 71N is based on the check matrix H used in the error correction decoder 72. This allows a lower BER (Bit Error Rate). According to the embodiment, it is possible to provide a magnetic regeneration processing device that can suppress errors. High-precision decoding is possible.

[0016] In an embodiment, the decoder 71 may be, for example, a graph neural network (GNN). In the GNN, for example, machine learning is performed. In an embodiment, the error correction decoder 72 may include, for example, a low-density parity-check codes (LDPC) decoder. High-precision decoding can be performed.

[0017] In the embodiment, the reproduction signal Sig-r includes waveform information 75W, bit position information 75P, and first likelihood ratio information 75L. The waveform information 75W includes information on the waveforms before and after the bit of interest. For example, the waveform information 75W includes a first waveform of the first bit, a second waveform of the second bit before the first bit, and a third waveform of the third bit after the first bit. The second bit before the first bit may include multiple bits. The third bit after the first bit may include multiple bits. The bit position information 75P includes position information of the first bit. The bit position information 75P includes, for example, information on which bit it is.

[0018] The first likelihood ratio information 75L includes information on the likelihood ratio (first likelihood ratio group α1) for each of the multiple calculation nodes 71N (i.e., multiple bits). The first likelihood ratio group α1 includes the likelihood ratio for each of the multiple bits. The waveform information 75W, the bit position information 75P, and the first likelihood ratio information 75L correspond to the feature amounts for the multiple calculation nodes 71N.

[0019] A first signal S1 based on such a reproduced signal Sig-r is input to a decoder 71. In the decoder 71, the first signal S1 based on the reproduced signal Sig-r is processed by calculation using a plurality of calculation nodes 71N having a connection relationship based on a parity check matrix H. A processing result is output from the decoder 71 as a second signal S2. The second signal S2 includes a likelihood ratio group α2. The likelihood ratio group α2 includes, for example, a likelihood ratio for each of a plurality of bits.

[0020] 1, an output of the error correction decoder 72 may be input to a decoder 71. The decoder 71 is configured to use the output of the error correction decoder 72 to output a second signal S2. For example, iterations are performed. In one example, the number of iterations may correspond to the number of hidden layers included in the decoder 71.

[0021] In one example, the number of features in each of the multiple computation nodes 71N is 7. The number of outputs in each of the multiple computation nodes 71N is 1. In the decoder 71, learning on the following first formula may be performed.

number

[0022] In one example, a fully connected neural network is applied to the MLP in the first formula. The number of input nodes is 7. The number of output nodes is 1. The number of hidden layer nodes is 15. The number of hidden layers is 5.

[0023] In the embodiment, for example, machine learning is performed by local convolution operation. During machine learning, the contribution of error may be changed according to the number of connections in the multiple computation nodes 71N. For example, the number of connections of one of the multiple computation nodes 71N is greater than the number of connections of another of the multiple computation nodes 71N. In this case, during learning (machine learning) of the decoder 71, the contribution of error regarding one of the multiple computation nodes 71N is greater than the contribution of error regarding another of the multiple computation nodes 71N. This enables more efficient learning. A highly accurate decoder 71 can be provided.

[0024] For example, as shown in Fig. 1, the number of connections of the third node N3 is greater than the number of connections of the first node N1. In this case, during learning of the decoder 71, the contribution degree of the error regarding the third node N3 is set to be greater than the contribution degree of the error regarding the first node N1. The contribution degree corresponds to, for example, a coefficient related to weighting.

[0025] FIG. 2 is a schematic view illustrating the magnetic regeneration processing device according to the first embodiment. 2, the magnetic reproducing processing device 111 according to the embodiment further includes a first maximum likelihood decoder 74a. Except for this, the configuration of the magnetic reproducing processing device 111 may be the same as the configuration of the magnetic reproducing processing device 110.

[0026] In the magnetic reproducing processing device 111, a signal based on the reproduced signal Sig-r is input to the first maximum likelihood decoder 74a. The output of the first maximum likelihood decoder 74a is input to the decoder 71 as the first signal S1. In the magnetic reproducing processing device 111, errors are further suppressed. The first maximum likelihood decoder 74a may include, for example, a Viterbi decoder.

[0027] 2, the magnetic reproducing processing device 111 may further include a waveform equalizer 73. A signal based on the reproduced signal Sig-r is input to the waveform equalizer 73. An output of the waveform equalizer 73 may be input to the decoder 71. In this example, the output of the waveform equalizer 73 is input to a first maximum likelihood decoder 74a, and the output of the first maximum likelihood decoder 74a is input to the decoder 71.

[0028] FIG. 3 is a schematic view illustrating the magnetic regeneration processing device according to the first embodiment. 3, the magnetic reproducing processing device 112 according to the embodiment further includes a second maximum likelihood decoder 74b. The configuration of the magnetic reproducing processing device 112 other than this may be the same as the configuration of the magnetic reproducing processing device 110 or the magnetic reproducing processing device 111.

[0029] In the magnetic reproducing processing device 112, the second signal S2 output from the decoder 71 is input to the second maximum likelihood decoder 74b. The output of the second maximum likelihood decoder 74b is input to the error correction decoder 72. In the magnetic reproducing processing device 112, errors are further suppressed. The second maximum likelihood decoder 74b may include, for example, a Viterbi decoder.

[0030] 3, the magnetic reproducing processing device 112 may further include a waveform equalizer 73. A signal based on the reproduced signal Sig-r is input to the waveform equalizer 73. An output of the waveform equalizer 73 is input to the decoder 71.

[0031] FIG. 4 is a schematic view illustrating the magnetic regeneration processing device according to the first embodiment. 4, the magnetic regeneration processing device 120 according to the embodiment includes a decoder 71, an error correction decoder 72, and a memory unit 77M. Except for the memory unit 77M, the configuration of the magnetic regeneration processing device 120 may be the same as the configuration of the magnetic regeneration processing device 110.

[0032] In the magnetic reproducing processing device 120, a first signal S1 based on the reproduced signal Sig-r is input to a decoder 71. A second signal S2 output from the decoder 71 is input to an error correction decoder 72. The memory unit 77M includes a first memory area 77a.

[0033] The error correction decoder 72 is configured to correct errors in the second signal S2 based on a parity check matrix H (see FIG. 1). The decoder 71 includes a neural network layer 71L (see FIG. 1). The neural network layer 71L includes a plurality of calculation nodes 71N (see FIG. 1).

[0034] The first storage area 77a is configured to store information about the connection relationships of the multiple calculation nodes 71N. The connection relationships are based on a check matrix H. The decoder 71 is configured to derive a second signal S2 by performing an operation based on the first signal S1 and the connection relationships stored in the first storage area 77a. The second signal S2 includes, for example, a likelihood ratio group α2. In the magnetic reproducing processing device 120, errors are suppressed.

[0035] In the magnetic reproducing processing device 120, the reproduced signal Sig-r includes waveform information 75W, bit position information 75P, and first likelihood ratio information 75L (first likelihood ratio group α1) (see FIG. 1). The waveform information 75W includes, for example, a first waveform of a first bit, a second waveform of a second bit before the first bit, and a third waveform of a third bit after the first bit. The bit position information 75P includes position information of the first bit.

[0036] 4, the memory unit 77M may further include a second memory area 77b. The second memory area 77b is configured to store information related to the check matrix H. The error correction decoder 72 performs error correction using the information related to the check matrix H stored in the second memory area 77b.

[0037] 4, the storage unit 77M may further include a third storage area 77c. The third storage area 77c is configured to store information about weights in the decoder 71. For example, in learning of the decoder 71, the information about weights stored in the third storage area 77c is applied.

[0038] 4, in the magnetic reproducing processing device 120, the output of the error correction decoder 72 may be input to a decoder 71. The decoder 71 is configured to use the output of the error correction decoder 72 to output a second signal S2.

[0039] FIG. 5 is a schematic view illustrating the magnetic regeneration processing device according to the first embodiment. 5, the magnetic reproducing processing device 121 according to the embodiment further includes a first maximum likelihood decoder 74a. Except for this, the configuration of the magnetic reproducing processing device 121 may be the same as the configuration of the magnetic reproducing processing device 120.

[0040] In the magnetic reproducing processing device 121, a signal based on the reproduced signal Sig-r is input to the first maximum likelihood decoder 74a. The output of the first maximum likelihood decoder 74a is input to the decoder 71 as the first signal S1. In the magnetic reproducing processing device 121, errors are further suppressed. The first maximum likelihood decoder 74a may include, for example, a Viterbi decoder.

[0041] 5, the magnetic reproducing processing device 121 may further include a waveform equalizer 73. A signal based on the reproduced signal Sig-r is input to the waveform equalizer 73. An output of the waveform equalizer 73 may be input to the decoder 71. In this example, the output of the waveform equalizer 73 is input to a first maximum likelihood decoder 74a, and the output of the first maximum likelihood decoder 74a is input to the decoder 71.

[0042] FIG. 6 is a schematic view illustrating the magnetic regeneration processing device according to the first embodiment. 6, the magnetic regeneration processing device 122 according to the embodiment further includes a second maximum likelihood decoder 74b. The configuration of the magnetic regeneration processing device 122 other than this may be the same as the configuration of the magnetic regeneration processing device 120 or the magnetic regeneration processing device 121.

[0043] In the magnetic reproducing processing device 122, the second signal S2 output from the decoder 71 is input to the second maximum likelihood decoder 74b. The output of the second maximum likelihood decoder 74b is input to the error correction decoder 72. In the magnetic reproducing processing device 122, errors are further suppressed. The second maximum likelihood decoder 74b may include, for example, a Viterbi decoder.

[0044] 6, the magnetic reproducing processing device 122 may further include a waveform equalizer 73. A signal based on the reproduced signal Sig-r is input to the waveform equalizer 73. An output of the waveform equalizer 73 is input to the decoder 71.

[0045] The magnetic regeneration processing device according to the embodiment may include a computer. FIG. 7 is a schematic diagram illustrating the magnetic regeneration processing device according to the embodiment. 7, the magnetic regeneration processing device according to the embodiment (for example, the magnetic regeneration processing device 110) may include a processing circuit 76p, a memory circuit 76m, and an interface circuit 76f. The processing circuit 76p is, for example, an electric circuit. The memory circuit 76m may include, for example, at least one of a ROM (Read Only Memory) and a RAM (Random Access Memory). For example, a part of the magnetic recording and regeneration unit 80D may be used as the memory circuit 76m.

[0046] The magnetic regeneration processing device according to the embodiment (e.g., the magnetic regeneration processing device 110) may include a display device 76d and an input device 76i. The display device 76d may include various displays. The input device 76i may include, for example, a device having an operation function (e.g., a keyboard, a mouse, a touch-type input panel, or a voice recognition input device).

[0047] The multiple elements included in the magnetic regeneration processing device according to the embodiment (e.g., the magnetic regeneration processing device 110) can communicate with each other by at least one of wireless and wired methods. The multiple elements included in the magnetic regeneration processing device 110 may be provided in different locations. For example, a general-purpose computer may be used as the magnetic regeneration processing device 110. For example, multiple computers connected to each other may be used as the magnetic regeneration processing device 110. A dedicated circuit may be used as at least a part of the magnetic regeneration processing device 110. For example, multiple circuits connected to each other may be used as the magnetic regeneration processing device 110.

[0048] The embodiment may include a program. The program causes a computer (magnetic reproducing processing device 110) to perform the above-described operations. The embodiment may include a storage medium on which the above-described program is stored.

[0049] The magnetic recording and reproducing device according to the embodiment (magnetic recording and reproducing device 210, see FIG. 1) includes any magnetic reproducing processing device according to the first embodiment and its variations.

[0050] Second embodiment The second embodiment relates to a magnetic reproducing method. The magnetic reproducing method according to the embodiment is a method that uses the magnetic reproducing processing device (for example, 110-112, 120-122) according to the first embodiment and variations thereof. A magnetic reproducing method capable of suppressing errors can be provided.

[0051] The embodiments may include the following technical solutions. (Technical proposal 1) A decoder; an error correction decoder; Equipped with a first signal based on a reproduction signal is input to the decoder; A signal based on a second signal output from the decoder is input to the error correction decoder; The error correction decoder corrects an error in the second signal based on a check matrix; the decoder includes a neural network layer; the neural network layer includes a plurality of computation nodes; A magnetic regeneration processing device, wherein a connection relationship between the plurality of calculation nodes is based on the check matrix.

[0052] (Technical proposal 2) the reproduced signal includes waveform information, bit position information, and first likelihood ratio information; the waveform information includes a first waveform of a first bit, a second waveform of a second bit before the first bit, and a third waveform of a third bit after the first bit; The magnetic reproducing processing device described in technical proposal 1, wherein the bit position information includes the position information of the first bit.

[0053] (Technical proposal 3) The output of the error correction decoder is input to the decoder; The magnetic reproducing processing device described in Technical Solution 1 or 2, wherein the decoder is configured to output the second signal using the output of the error correction decoder.

[0054] (Technical proposal 4) a first maximum likelihood decoder; a signal based on the reproduction signal is input to the first maximum likelihood decoder; The magnetic reproducing processing device according to any one of Technical Solutions 1 to 3, wherein an output of the first maximum likelihood decoder is input to the decoder as the first signal.

[0055] (Technical proposal 5) The magnetic reproducing processing device described in technical proposal 4, wherein the first maximum likelihood decoder includes a Viterbi decoder.

[0056] (Technical proposal 6) a second maximum likelihood decoder; the second signal is input to the second maximum likelihood decoder; The magnetic reproducing processing device according to any one of Technical Solutions 1 to 4, wherein an output of the second maximum likelihood decoder is input to the error correction decoder.

[0057] (Technical proposal 7) The magnetic reproducing processing device according to technical proposal 6, wherein the second maximum likelihood decoder includes a Viterbi decoder.

[0058] (Technical proposal 8) a waveform equalizer; a signal based on the reproduction signal is input to the waveform equalizer; The magnetic reproducing processing device according to any one of Technical Solutions 1 to 7, wherein an output of the waveform equalizer is input to the decoder.

[0059] (Technical proposal 9) The magnetic reproducing processing device according to any one of Technical Solutions 1 to 8, wherein the second signal includes a group of likelihood ratios.

[0060] (Technical proposal 10) a number of connections of one of the plurality of computing nodes is greater than a number of connections of another of the plurality of computing nodes; A magnetic reproducing processing device described in any one of technical proposals 1 to 9, wherein, during learning of the decoder, the contribution of error for the one of the multiple computation nodes is greater than the contribution of error for the other one of the multiple computation nodes.

[0061] (Technical proposal 11) A decoder; an error correction decoder; A storage unit including a first storage area; Equipped with a first signal based on a reproduction signal is input to the decoder; A signal based on a second signal output from the decoder is input to the error correction decoder; The error correction decoder corrects an error in the second signal based on a check matrix; the decoder includes a neural network layer; the neural network layer includes a plurality of computation nodes; the first storage area is configured to store information regarding a connection relationship between the plurality of computing nodes; the connection relationship is based on the parity check matrix, The decoder is configured to derive the second signal by a calculation based on the first signal and the connection relationship stored in the first storage area.

[0062] (Technical proposal 12) the reproduced signal includes waveform information, bit position information, and first likelihood ratio information; the waveform information includes a first waveform of a first bit, a second waveform of a second bit before the first bit, and a third waveform of a third bit after the first bit; The magnetic regeneration processing device described in technical proposal 11, wherein the bit position information includes the position information of the first bit.

[0063] (Technical proposal 13) The storage unit further includes a second storage area, The magnetic reproducing processing device described in Technical Solution 11 or 12, wherein the second memory area is configured to store information regarding the check matrix.

[0064] (Technical proposal 14) the storage unit further includes a third storage area, The magnetic reproducing processing device according to any one of Technical Solutions 11 to 13, wherein the third storage area is configured to store information relating to weights in the decoder.

[0065] (Technical proposal 15) The output of the error correction decoder is input to the decoder; The magnetic reproducing processing device according to any one of Technical Solutions 11 to 14, wherein the decoder is configured to output the second signal using the output of the error correction decoder.

[0066] (Technical proposal 16) a first maximum likelihood decoder; a signal based on the reproduction signal is input to the first maximum likelihood decoder; The magnetic reproducing processing device according to any one of Technical Solutions 11 to 15, wherein an output of the first maximum likelihood decoder is input to the decoder as the first signal.

[0067] (Technical proposal 17) a second maximum likelihood decoder; the second signal is input to the second maximum likelihood decoder; The magnetic reproducing processing device according to any one of Technical Solutions 11 to 16, wherein an output of the second maximum likelihood decoder is input to the error correction decoder.

[0068] (Technical proposal 18) The magnetic reproducing processing device according to any one of Technical Solutions 1 to 17, wherein the error correction decoder includes a Low-Density Parity-Check Codes (LDPC) decoder.

[0069] (Technical proposal 19) A magnetic regeneration processing device according to any one of technical proposals 1 to 18; a magnetic recording and reproducing unit configured to output the reproduced signal; A magnetic recording and reproducing device comprising:

[0070] (Technical proposal 20) A magnetic regeneration method using the magnetic regeneration processing device described in any one of Technical Schemes 1 to 18.

[0071] According to the embodiments, it is possible to provide a magnetic reproducing processing device, a magnetic recording and reproducing device, and a magnetic reproducing method that can suppress errors.

[0072] The above describes the embodiment of the present invention with reference to examples. However, the present invention is not limited to these examples. For example, the specific configurations of each element, such as a decoder, an error correction decoder, and a storage unit, included in the magnetic reproducing processing device are included in the scope of the present invention as long as a person skilled in the art can implement the present invention in the same way and obtain the same effect by appropriately selecting from the known range.

[0073] Any combination of two or more elements of each example, within the scope of technical feasibility, is also included within the scope of the present invention as long as it includes the gist of the present invention.

[0074] All magnetic reproducing processing devices, magnetic recording and reproducing devices, and magnetic reproducing methods that can be implemented by a person skilled in the art with appropriate design modifications based on the magnetic reproducing processing devices, magnetic recording and reproducing devices, and magnetic reproducing methods described above as embodiments of the present invention also fall within the scope of the present invention as long as they include the gist of the present invention.

[0075] Within the scope of the concept of the present invention, a person skilled in the art may conceive of various modifications and alterations, and it is understood that these modifications and alterations also fall within the scope of the present invention.

[0076] Although some embodiments of the present invention have been described, these embodiments are presented as examples and are not intended to limit the scope of the invention. These novel embodiments can be implemented in various other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and their modifications are included in the scope and spirit of the invention, and are included in the scope of the invention and its equivalents described in the claims. [Explanation of symbols]

[0077] 71: decoder, 71L: neural network layer, 71N: calculation node, 72: error correction decoder, 73: waveform equalizer, 74a, 74b: first and second maximum likelihood decoders, 75L: first likelihood ratio information, 75P: bit position information, 75W: waveform information, 76d: display device, 76f: interface circuit, 76i: input device, 76m: memory circuit, 76p: processing circuit, 77M: memory unit, 77a-77c: first to third memory areas, 80: magnetic recording medium, 80D: magnetic recording and reproducing unit, 80H: magnetic head, 80R: recording and reproducing unit, 110-112, 120-122: magnetic reproducing processing device, 210: magnetic recording and reproducing device, N1-N6: first to sixth nodes, S1, S2: first and second signals, Sig-c: Decoded signal, Sig-r: Reconstructed signal, α1: First likelihood ratio group, α2: Likelihood ratio group

Claims

1. A decoder; an error correction decoder; Equipped with a first signal based on a reproduction signal is input to the decoder; a signal based on a second signal output from the decoder is input to the error correction decoder; The error correction decoder corrects an error in the second signal based on a check matrix; the decoder includes a neural network layer; the neural network layer includes a plurality of computation nodes; A magnetic regeneration processing device, wherein a connection relationship between the plurality of calculation nodes is based on the check matrix.

2. the reproduced signal includes waveform information, bit position information, and first likelihood ratio information; the waveform information includes a first waveform of a first bit, a second waveform of a second bit before the first bit, and a third waveform of a third bit after the first bit; The magnetic reproducing processing device according to claim 1 , wherein the bit position information includes position information of the first bit.

3. The output of the error correction decoder is input to the decoder; 3. The magnetic reproducing processing device according to claim 1, wherein the decoder is configured to output the second signal using the output of the error correction decoder.

4. A decoder; an error correction decoder; A storage unit including a first storage area; Equipped with a first signal based on a reproduction signal is input to the decoder; a signal based on a second signal output from the decoder is input to the error correction decoder; The error correction decoder corrects an error in the second signal based on a check matrix; the decoder includes a neural network layer; the neural network layer includes a plurality of computation nodes; the first storage area is configured to store information regarding a connection relationship between the plurality of computing nodes; the connection relationship is based on the parity check matrix, The decoder is configured to derive the second signal by a calculation based on the first signal and the connection relationship stored in the first storage area.

5. the reproduced signal includes waveform information, bit position information, and first likelihood ratio information; the waveform information includes a first waveform of a first bit, a second waveform of a second bit before the first bit, and a third waveform of a third bit after the first bit; The magnetic reproducing processing device according to claim 4 , wherein the bit position information includes position information of the first bit.

6. The storage unit further includes a second storage area, The magnetic reproducing processing device according to claim 4 , wherein the second storage area is configured to store information relating to the check matrix.

7. the storage unit further includes a third storage area, The magnetic reproducing processing device according to claim 4 , wherein the third storage area is configured to store information relating to weights in the decoder.

8. The magnetic reproducing processing device according to claim 1 , wherein the error correction decoder includes a Low-Density Parity-Check Codes (LDPC) decoder.

9. The magnetic regeneration processing device according to claim 1 ; a magnetic recording and reproducing unit configured to output the reproduced signal; A magnetic recording and reproducing device comprising:

10. A magnetic regeneration method using the magnetic regeneration processing device according to claim 1.

Images