OPTICAL TRANSMITTING-RECEIVING MODULE WITH NEURAL NETWORK

DETAILED ACTION Notice of Pre-AIA or AIA Status The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA . Status of the Claims Currently, claims 1-10 are pending in the application. Response to Arguments / Amendments Applicant’s arguments have been fully considered, but they are not persuasive, see discussion below. Rejections under 35 U.S.C. § 103: The applicant argued that MATTIA is the not relevant and is non-analogous to the claimed invention and does not satisfy each of the claimed features of independent claim 1. MATTIA and LE fail to satisfy the features recited in independent claim 1. As to the above argument, MATTIA discloses an optical transmitting-receiving module with neural network with an optical control component that weights each delayed copy with an amplitude and a phase having "Both the phase and the amplitude of the optical signal is considered, i.e. the NN treats complex valued quantities ... complex valued weights) (Page 2, Paragraph 2) that are electrically adjusted during a training procedure as "train ... complex valued weights", §2.3 on p. 5 and §3: "Training takes about 6 min on i7-4500U laptop with 8 Gb of RAM", i.e. they are electrically trained), where the optical signal is processed in a complex field, not treating separately its real and imaginary parts (Page 2, Paragraph 2), and MATTIA discloses a coupler which recombines the signals and a non-linear node to which a complex sum is sent at the output of the coupler (coupler is implicit in summing(optically) the signals from the nodes (fig. 2(c), left nodes) to the output node as disclosed in eq. 2, in which A0 and cp 0 are caused by the non-linear output node), having an analog signal: A digital (PRBS) signal is converted by the DAC to an analog signal that is further LP filtered, pre-compensated and propagated through a fiber, and thus remains an analog signal. The "sampling" mentioned in the next paragraph seems to be a continuous sampling, i.e. for each value of t, there are delayed signals for t - 6t, t - 26t,t- 36t ... , t not being limited to any sampling instances, but being continuous (Pages 5-6, Fig. 2 (a)). PNG media_image1.png 554 436 media_image1.png Greyscale In addition to MATTIA , Le teaches a power divider which distributes an input signal to be corrected and sends it in N waveguides with Optical S/P 1110 is an optical sampler which converts a serial optical signal to parallel optical samples that include a set of splitters (jointly forming a power divider) and a set of delay lines (jointly forming the delay component. The input to optical S/P 1110 may be a received optical signal (for recovery of the data carried by the optical signal) or an optical signal for pre-distortion prior to transmission ([0153]) PNG media_image2.png 382 438 media_image2.png Greyscale The applicant argued that MATTIA and LE fail to satisfy the features recited in independent claim 4 that recites, "wherein phase information are set due to the weight imposed on each of the N channels, which act as multiple Mach-Zehnder MZ interferometers on temporally distributed versions of the signal at input." As to the above argument, MATTIA discloses MATTIA discloses multiple Mach-Zehnder MZ interferometers on temporally distributed versions of the signal at input as disclosed in fig. 7 A-B and p. 17, I. 14-19 "The optical neurons employ an integrated planar optic circuit which consists of MMICs [multi-mode interferometric coupler], whose number of inputs and outputs are determined by their function and location in the ONN" and p.17, I. 23-25: "The intermediate section include multiple optical interconnection paths which incorporate the phase shifters 740 embedded on the optical waveguide section". This configuration is implicitly a combination of multiple Mach-Zehnder interferometers). (Mach-Zehnder interferometers are commonly known as alternative neurons for an optical neural network, Therefore, using multiple Mach-Zehnder interferometers for applying weights cannot be considered inventive. The applicant argued that MATTIA and LE fail to satisfy the features recited in independent claim 7 that recites "the electrical component is a photodiode used in a non-linear region", and dependent claim 8 that recites "the non-linear node comprises the sequence of an optical semiconductor amplifier (SOA) and a photodiode close to its region of saturation in case the neural network is a last stage of a communication line" As to the above argument, Le discloses nonlinear optical logic operation is required for decision making in the optical domain ([0145]) and an optical semiconductor amplifier and a photodiode close to its region of saturation in case the neural network is a last stage of a communication line ring the optical logic gate includes two semiconductor optical amplifiers (SOAs) embedded in an integrated interferometer. Further optionally the interferometer is a Mach-Zehnder type interferometer (MZI) with three coupled inputs which are allocated for optical signals ([0143]). Accordingly, Examiner maintains the rejection with regards to above arguments. Claim Rejections - 35 USC § 103 The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action: A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102 of this title, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made. Claims 1-10 are rejected under 35 U.S.C. 103 as being unpatentable over MATTIA et al. ("A silicon photonics feed-forward neural network for nonlinear distortion mitigation in an optical link", December 2020 (2020-12-10), hereinafter MATTIA) in view of Le et al. (US 20220138549, hereinafter Le). Regarding Claim 1, MATTIA discloses an optical transmitting-receiving module with neural network (Abstract), comprising: an optical control component that weights each delayed copy with an amplitude and a phase (Page 2, Paragraph 2: "Both the phase and the amplitude of the optical signal is considered, i.e. the NN treats complex valued quantities ... complex valued weights) that are electrically adjusted during a training procedure (Page 2, Paragraph 2: "train ... complex valued weights", §2.3 on p. 5 and §3: "Training takes about 6 min on i7-4500U laptop with 8 Gb of RAM", i.e. they are electrically trained), where the optical signal is processed in a complex field, not treating separately its real and imaginary parts (Page 2, Paragraph 2), and a coupler which recombines the signals and a non-linear node to which a complex sum is sent at the output of the coupler (coupler is implicit in summing(optically) the signals from the nodes (fig. 2(c), left nodes) to the output node as disclosed in eq. 2, in which A0 and cp 0 are caused by the non-linear output node), wherein the input signal is a non-pulsed, continuous, analog, pulsed or digital signal (Pages 5-6, Fig. 2 (a), an analog signal: A digital (PRBS) signal is converted by the DAC to an analog signal that is further LP filtered, pre-compensated and propagated through a fiber, and thus remains an analog signal. The "sampling" mentioned in the next paragraph seems to be a continuous sampling, i.e. for each value of t, there are delayed signals for t - 6t, t - 26t,t- 36t ... , t not being limited to any sampling instances, but being continuous). PNG media_image1.png 554 436 media_image1.png Greyscale MATTIA does not explicitly disclose a power divider which distributes an input signal to be corrected and sends it in N waveguides to an optical delay component which imparts time delays to copies of the optical signal. Le teaches a power divider which distributes an input signal to be corrected and sends it in N waveguides to an optical delay component which imparts time delays to copies of the optical signal (0153] Optical S/P 1110 is an optical sampler which converts a serial optical signal to parallel optical samples that include a set of splitters (jointly forming a power divider) and a set of delay lines (jointly forming the delay component. The input to optical S/P 1110 may be a received optical signal (for recovery of the data carried by the optical signal) or an optical signal for pre-distortion prior to transmission) PNG media_image2.png 382 438 media_image2.png Greyscale Therefore, it would have been obvious to one ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of power divider which distributes an input signal to be corrected as taught by Le ([0153]) into the optical transmitting-receiving system of MATTIA in order to provide apparatus processes signals in an optical domain that provides benefit of handling ultra-high data rate signals used during optical transmission in a simple and effective manner and avoids low processing speeds and high resource costs involved in digital signal processing of corresponding electrical signals (Le, [0178]). Regarding Claim 2, MATTIA in view of Le discloses the optical transmitting-receiving module of claim 1, MATTIA in view of Le discloses wherein the optical delay component comprises a coil with a thermal phase shifter and/or a ring resonator and/or an electro-optical modulator since optical delay component comprises a coil with a thermal phase shifter and/or a ring resonator and/or an electro-optical modulator are common means for incurring a time delay and cannot therefore constitute an inventive step. Regarding Claim 3, MATTIA in view of Le discloses the optical transmitting-receiving module of claim 1, MATTIA discloses wherein, in the training procedure, both amplitude ai and phase Φi of the weights wi are trained independently of each other, with the following limits: 0-1 for amplitude ai and 0-2π for phase Φi according to the formula wi=ai, or, alternatively, active elements are used to determine the weights which, being able to act as both attenuator and amplifier, can have amplitude >1 (§2.3 (p. 5, par 4) training weights for phase and amplitude separately; and teaches the limits disclosed for amplitudes and phase. The optional feature of allowing amplitudes is an obvious implementation choice representing a balance between choosing a passive device (as in 01 ), with limitations of conservation of power and an active device containing also optical amplifiers to reach amplitudes> 1). Regarding Claim 4, MATTIA in view of Le discloses the optical transmitting-receiving module of claim 1, MATTIA discloses wherein phase information are set due to the weight imposed on each of the N channels, which act as multiple Mach-Zehnder MZ interferometers on temporally distributed versions of the signal at input (Mach-Zehnder interferometers are commonly known as alternative neurons for an optical neural network, as disclosed in fig. 7 A-B and p. 17, I. 14-19 "The optical neurons employ an integrated planar optic circuit which consists of MMICs [multi-mode interferometric coupler], whose number of inputs and outputs are determined by their function and location in the ONN" and p.17, I. 23-25: "The intermediate section include multiple optical interconnection paths which incorporate the phase shifters 740 embedded on the optical waveguide section". This configuration is implicitly a combination of multiple Mach-Zehnder interferometers). Therefore, using multiple Mach-Zehnder interferometers for applying weights cannot be considered inventive. Regarding Claim 5, MATTIA in view of Le discloses the optical transmitting-receiving module of claim 1, MATTIA discloses wherein the non-linear node is an optical component or an electrical component (the non-linear node is a micro-ring resonator, see §2.1) Le also discloses an optical logical gate performing a non-linear optical logic operation to discriminate the output of the optical neural network and convert it to a binary signal and the optical logic gate includes two semiconductor optical amplifiers (SOAs) embedded in an integrated interferometer. Further optionally the interferometer is a Mach-Zehnder type interferometer (MZI) with three coupled inputs which are allocated for optical signals ([0143]). The same reason or rational of obviousness motivation applied as used above in claim 1. Regarding Claim 6, MATTIA in view of Le discloses the optical transmitting-receiving module of claim 5, Le discloses wherein the optical component is a semiconductor optical amplifier, a semiconductor optical amplifier with a variable optical attenuator, a Erbium-doped fiber amplifier, a bi-stable ring or micro-ring, a Mach-Zehnder MZ interferometer loaded with micro-ring ([0143], the optical logic gate includes two semiconductor optical amplifiers (SOAs) embedded in an integrated interferometer. Further optionally the interferometer is a Mach-Zehnder type interferometer (MZI) with three coupled inputs which are allocated for optical signals). The same reason or rational of obviousness motivation applied as used above in claim 1. Regarding Claim 7, MATTIA in view of Le discloses the optical transmitting-receiving module of claim 5, Le discloses wherein the electrical component is a photodiode used in a non-linear region ([0145], nonlinear optical logic operation is required for decision making in the optical domain). The same reason or rational of obviousness motivation applied as used above in claim 1. Regarding Claim 8, MATTIA in view of Le discloses the optical transmitting-receiving module of claim 5, Le discloses wherein the non-linear node comprises the sequence of an optical semiconductor amplifier and a photodiode close to its region of saturation in case the neural network is a last stage of a communication line ring ([0143], the optical logic gate includes two semiconductor optical amplifiers (SOAs) embedded in an integrated interferometer. Further optionally the interferometer is a Mach-Zehnder type interferometer (MZI) with three coupled inputs which are allocated for optical signals). The same reason or rational of obviousness motivation applied as used above in claim 1. Regarding Claim 9, MATTIA in view of Le discloses the optical transmitting-receiving module of claim 5, MATTIA in view of Le discloses wherein the non-linear node comprises two branches in a sequence, a first branch comprising a Mach-Zehnder interferometer with a semiconductor optical amplifier and a variable optical attenuator and a second branch with a phase modulator, the first and second branches being part of the same nonlinear node having a single input and a single output, the first and second branches being connected inside the nonlinear node to provide a single output since it appears to be an obvious arrangement of well-known elements the person skilled in the art would make for creating a non-linear node ((see §3.2)) Regarding Claim 10, MATTIA in view of Le discloses the optical transmitting-receiving module of claim 1, MATTIA discloses wherein the optical nodes have activation functions which are tuned during the training phase (p. 4, eq. 1, 2 and the surrounding text that f is the matrix of activation functions selected by the optimiser and that f0, applied to WX, is the activation function of the output node. §2.3, last paragraph indicates the activation functions are trained. §2.1 indicates how different activation functions are selected (using wavelength detuning)). Conclusion THIS ACTION IS MADE FINAL. Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a). A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action. Any inquiry concerning this communication or earlier communications from the examiner should be directed to Samuel D Fereja whose telephone number is (469)295-9243. The examiner can normally be reached 8AM-5PM. Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice. If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, DAVID CZEKAJ can be reached at (571) 272-7327. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300. Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000. /SAMUEL D FEREJA/Primary Examiner, Art Unit 2487