The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
DETAILED ACTION
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.
The factual inquiries set forth in Graham v. John Deere Co., 383 U.S. 1, 148 USPQ 459 (1966), that are applied for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1 – 3, 5 – 14, and 16 – 18 are rejected under 35 U.S.C. 103 as being unpatentable over Shen et al (US 2019/0370652 A1).
Regarding claim 1, Shen discloses (Fig. 1A; Abstract; para. 0004 and 0346 – 0364) an apparatus, comprising:
an optical sampler 144 (comprising a modulator array; para. 0359 – 0364), configured to obtain a plurality of parallel optical samples by sampling a continuous optical signal (provided a laser unit 142; para. 0353 and 0357);
an optical neural network 150 (optical matrix multiplication (OMM) unit; para. 0346) associated with the optical sampler 144 (the OMM unit 150 receives modulated/sampled light from it), the optical neural network 150 comprising a plurality of interconnected optical neurons (e.g., an interconnected network of Mach-Zehnder interferometers shown in Figs. 1C and 1D; Figs. 11 and 12; para. 0354 and 0355; para. 0466 and 0519), the optical neural network 150 being configured to optically process the parallel optical samples (from optical sampler 144) and to provide a final output optical signal (to a detection unit 146) resulting from the processing, each optical neuron of the plurality of interconnected optical neurons being configured to input a plurality of optical signals and to output an optical signal comprising a weighted sum of the input plurality of optical signals (“the optical matrix multiplication unit being configured to transform the optical input vector into an optical output vector based on the plurality of weight control signals” at para. 0006; also para. 0350), each weighted sum being established by phase-shifting (by corresponding phase shifters 174, as shown in Fig. 1E; para. 0356) the input plurality of optical signals prior to summing the input plurality of optical signals (“each point in each layer can be considered a neuron that takes input from multiple neurons from the previous layer and adds additional phase and intensity modulation before outputting to the next layer” at para. 0519; “By varying the weight control signals, the phase delays of the first and second phase shifters 174 an 176 of each of the interconnected MZIs 170 can be varied, which reconfigures the optical interference unit 154 of the OMM unit 150 to implement a particular matrix multiplication that is determined by the phase delays set across the entire optical interference unit 154” at para. 0356); and
a phase shift controller 134 (second DAC subunit that provides control electrical signals to the phase sifters of the OMM unit 150, as shown in Fig. 1A; para. 0366 and 0367) associated with the optical neural network 150, the phase shift controller 134 being configured to control the phase-shifting of the input plurality of optical signals, to obtain target weighted sums for the plurality of input optical signals (“To accommodate the different characteristics of the modulator control signals and the weight control signals, in some implementations, the DAC unit 130 may include a first DAC subunit 132, and a second DAC subunit 134. The first DAC subunit 132 may be specifically configured to generate the modulator control signals, and the second DAC subunit 134 may be specifically configured to generate the weight control signals” at para. 0366).
By way of further explanation for the limitation “optical sampler”, it is noted that Shen teaches that the modulator array 144 applies amplitude modulation at high speeds on the continuous optical signal provided by the laser unit 142 (“The light outputs of the laser unit 142 are coupled to the modulator array 144. The modulator array 144 is configured to receive the light inputs from the laser unit 142 and modulate the intensities of the received light inputs based on modulator control signals, which are electrical signals. Examples of modulators include Mach-Zehnder Interferometer (MZI) modulators, ring resonator modulators, and electro-absorption modulators” at para. 0359; “the modulation rate of the modulator array 144 may range, for example, from 5 GHz, 8 GHz, or 10's of GHz to 100's of GHz. In order to sustain the operation of the modulator array 144 at such modulation rate, the integrated circuitry of the controller 110 may be configured to output control signals for the DAC unit 130 at a rate greater than or equal to, for example, 5 GHz, 8 GHz, 10 GHz, 20 GHz, 25 GHz, 50 GHz, or 100 GHz” at para. 0364). The modulator array 144 is controlled by the phase shift controller 132 which provides high-speed sampling/control signals (“For example, the modulation rate of the modulator array 144 may be 25 GHz, and the first DAC subunit 132 may have a per-channel output update rate of 25 giga-samples per second (GSPS) and a resolution of 8 bits or higher” at para. 0366, emphasis added). Hence, Shen at the very least renders obvious that the modulator array 144 functions as an optical sampler.
Regarding claim 12, Shen renders obvious all of the recited step limitations of a corresponding method of using the disclosed apparatus (detailed above for claim 1). In particular, Shen considers a method, comprising:
obtaining, by an optical sampler 144 (modulator array controlled by 132; see the explanation above for the mapping of the limitation “optical sampler”) of a photonic signal processor, a plurality of parallel optical samples by sampling a continuous optical signal (from the laser unit 142);
optically processing, by an optical neural network 150 associated with the optical sampler 144, parallel optical samples, to provide a final output optical signal resulting from the processing, wherein the optical neural network comprises a plurality of interconnected optical neurons (Figs. 1C and 1D), each optical neuron inputs a plurality of optical signals and outputs an optical signal comprising a weighted sum of the input plurality of optical signals, the weighted sums being established by phase-shifting the input plurality of optical signals prior to the summing;
controlling, by a phase shifter controller 134 associated with the optical neural network 150, the phase-shifting of the input plurality of optical signals, to obtain target weightings for the input plurality of optical signals;
generating, by a feedback signal generator 146,160,110 (para. 0369 and 0370) associated with the optical neural network 150, at least one of an electrical feedback signal or an optical feedback signal from the final output optical signal;
training, by an electronic gate array associated with the phase shift controller, the optical neural network based on a training scheme (Fig. 14; para. 0114 and 0531 – 0538);
providing a training signal 1406 (as identified in Fig. 14) to the optical sampler; and
determining required phase control signals for phase shifters by applying the training scheme to the at least one of the electrical feedback signal or the optical feedback signal (“the training of the discriminator 1402 is performed electronically, e.g., using transistor based data processors (such as central processing units or general purpose graphic processor units) to calculate the weights for the neural layers of the discriminator 1402. Similarly, the training of the generator 1404 is also performed electronically to calculate the weights for the neural layers of the generator 1404” At para. 0532).
Regarding claims 2 and 17, Shen teaches that the apparatus further comprises:
an optical to electrical data converter 146 (detection unit) associated with (receiving light from) the optical neural network 150, the optical to electrical data converter being configured to convert the final output optical signal into an electrical data signal (“The OMM unit 150 is coupled to the detection unit 146, which is configured to generate N output voltages corresponding to the N optical signals of the optical output vector. For example, the detection unit 146 may include an array of N photodetectors configured to absorb the optical signals and generate photocurrents, and an array of N transimpedance amplifiers configured to convert the photocurrents into the output voltages” at para. 0368).
Regarding claim 3, Shen considers that the optical to electrical data converter can comprise a portion of 150 together with 146,160 which include:
an optical logic gate, configured to extract a data content of the final output optical signal into an optical signal state (XOR and OR gates in Figs. 16 and 17; “The above describes using photonic circuits that include Mach-Zehnder interferometers, directional couplers, planar optical waveguides, and photodetectors to implement logic gates such as AND, OR, and XOR gates … There is no optical nonlinearity in the design of the optical logic gates. The nonlinear response comes from the detection of the signal using photodetectors” at para. 0546); and
an optical to electrical converter 146,160 associated with (receiving light from) the optical logic gate (as detailed in Figs. 16 and 17), configured to convert the optical signal state into an electrical data signal.
Regarding claims 5 and 16, Shen considers (Figs. 11 and 12; para. 0350, 0393, and 0395) that the optical neural network comprises:
an input (leftmost) layer, configured to convey the parallel optical samples from the optical sampler to at least some optical neuron of the plurality of optical neurons in the optical neural network;
at least one internal (hidden) layer of optical neurons, each optical neuron comprised in the at least one internal layer of optical neurons comprising a plurality of optical inputs optically connected via respective first controllable phase shifters to optical outputs of a preceding layer of the optical neural network, and configured to output a sum of phase-shifted optical output signals of the preceding layer; and
at least one output (rightmost) optical neuron, comprising a plurality of optical inputs optically connected via respective second controllable phase shifters to optical outputs of a final layer of the at least one internal layers of optical neurons, and configured to output a sum of phase-shifted optical output signals of the final layer of the at least one internal layer as the final output optical signal.
Regarding claim 6, Shen considers (Figs. 1A – 1E) that the phase shift controller 134 is configured to control the phase-shifting of the input plurality of optical signals by applying respective electrical signals to the first controllable phase shifters 174 and the second controllable phase shifters 176 (para. 0356).
Regarding claim 7, Shen renders obvious Fig. 40; para. 0662) that at least one (output) optical neuron of the plurality of interconnected optical neurons comprises a multi-mode interferometric coupler (MMIC) 4002 in order to have two outputs for homodyne detection by the optical to electrical data converter 4004a,4004b,4006.
Additionally or alternatively, the Examiner takes official notice that Mach-Zehnder interferometers (listed by Shen as a suitable type for the neurons; para. 0355) can be implemented with one output or two output, the latter provided by an MMIC. Such arrangement would be obvious to a person of ordinary skill in the art and a suitable/workable design choice.
Regarding claims 8 and 13, Shen considers that the phase shift controller 134 (comprised in 130) stores a table of electrical signal levels to be applied to phase shifters during operation of the apparatus (“The second DAC control signal may include multiple digital values to be converted by the DAC unit 130 into the first plurality of weight control signals. The multiple digital values are generally in correspondence with the first plurality of neural network weights, and may be related through various mathematical relationships or look-up tables” at para. 0382).
Regarding claims 9 and 14, Shen teaches that the apparatus is trained (para. 0114 and 0531 – 0538) and, hence, renders obvious that electrical signal levels of the table of electrical signal levels can be determined during a training phase of the optical neural network.
Additionally or alternatively, the Examiner takes official notice that neural networks comprising a look-up tables storing information about control signals, the information obtained during a training phase of the neural networks, are well known in the art. Such arrangement would be obvious to a person of ordinary skill in the art in order to store electrical signal levels and quickly retrieve them without having to retrain the network.
Regarding claim 10, Shen teaches (Figs. 1A, 16, 17, and 40) that the apparatus further comprises:
a feedback signal generator 160 configured to generate at least one of an electrical feedback signal or an optical feedback signal from the final output optical signal; and
an electronic gate array (comprising 110 and gate array 4006 in Fig. 40; para. 0662) configured to train the optical neural network (para. 0114 and 0531 – 0538) based on the at least one of the electrical feedback signal or the optical feedback signal.
Regarding claims 11 and 18, the Examiner takes official notice that connectorized fiber-optic links are well known in the art of optical networks. It would be obvious to a person of ordinary skill in the art that at least some of the optical connections (e.g., from the OMM 150 to the detection unit 146) in the apparatus of Sheng can be established by connectorized fiber-optic links as low-loss lines interconnecting different parts. In such arraignment, the apparatus further comprises: an optical connector (plug and/or receptacle) configured to couple the final output optical signal to an optical transmission medium (optical fiber).
Claims 4 and 15 are rejected under 35 U.S.C. 103 as being unpatentable over Shen in view of Hamilton et al (US 5,010,346), and further in view of Hosoi (US 6,400,490 B1).
Regarding claims 4 and 15, Shen does not detail (i) a suitable/workable layout/topology of the optical sampler 144 and (ii) structural particulars of its sampling elements (modulators). However, Hamilton and Hosoi provide features (i) and (ii), respectively, as detailed below.
As for feature (i), Shen teaches that the optical sampler 144 receives a parallel array of optical inputs from the laser unit 142, samples/modulates them, and provides a parallel array of sampled/modulator output to the OMM 150. Hamilton discloses (Fig. 2; 8:13 – 9:38) optical sampler wherein an optical input from a single laser source 12 is split into a parallel array of sampled/modulated outputs 116a-116m, wherein the optical sampler comprises a plurality of sampling elements/modulators 108a-108m connected in series by optical delay lines 116 (optical fibers).
It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention that the optical sample 144 in Sheng can be implemented as a plurality of sampling elements connected in series by optical delay lines and as illustrated by Hamilton. Such arrangement provides a parallel array of sampled/modulated outputs using only one optical source by using a serially disposed splitters. In fact, Sheng states the use of an optical splitter (“the laser unit 142 includes a single laser source and an optical power splitter. The single laser source is configured to generate laser light. The optical power splitter is configured to split the light generated by the laser source into N light outputs of substantially equal intensities and phase. By splitting a single laser output into multiple outputs, optical coherence of the multiple light outputs may be achieved” at para. 0385). The use of delay lines can (pre)compensate for a phase disbalanced/difference in the following parts of the apparatus.
As for feature (ii), Shen considers (Fig. 39; para. 0399) that each of sampling element/modulator of the plurality of sampling elements (in modulator array 144) can be formed by an electro-optic Mach-Zehnder modulator 3900 with a multi-mode interference coupler 3902b. While Shen does not teach alternative design versions, Hosoi discloses (Fig. 13; 12:45 – 13:54) an electro-optic Mach-Zehnder modulator comprising:
an optical splitter 1x2 configured to split an optical signal (int 12a) into a first (to 12b) component signal and a second (to 12c) component signal;
a first (upper) phase modulator (+ f/2) and a second (lower) phase modulator (- f/2) associated with the optical splitter, the first (upper) phase modulator being configured to phase modulate the first component signal to obtain a phase-modulated first component signal (+ f/2 in the waveguide branch 12b), and the second (lower) phase modulator being configured to modulate the second component signal to obtain a phase-modulated second component signal (- f/2 in the waveguide branch 12c); and
a multi-mode interferometric coupler 23 associated with the first phase modulator and the second phase modulator, the multi-mode interferometric coupler 23 being configured to couple the phase-modulated first component signal (+ f/2) and the phase-modulated second component signal (- f/2); and wherein the first (upper) phase modulator and the second (lower) phase modulator are configured to switch a continuous optical signal to a first output 12d or to a second output 12e, depending on a voltage applied to the electrodes 14 (Figs. 7, 11A – 11C, and 14).
It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention that each sampling element/modulator in Sheng can be modified according to a design choice illustrated by Hosoi in order to provide both modulation and switching functions and to switch the continuous optical signal to a first output of the corresponding sampling element during sampling intervals (with an applied voltage) of the corresponding sampling element and to a second output of the corresponding sampling element between the sampling intervals (no voltage applied) of the corresponding sampling element.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
US 11,017,309 B2
US 2019/0319634 A1
US 10,763,974 B2
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ROBERT TAVLYKAEV whose telephone number is (571)270-5634. The examiner can normally be reached 10:00 am - 6:00 pm, Monday - Friday.
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, William Kraig can be reached on (571)272-8660. 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.
/ROBERT TAVLYKAEV/Primary Examiner, Art Unit 2896