US20210201135A1 - End-to-end learning in communication systems - Google Patents
End-to-end learning in communication systems Download PDFInfo
- Publication number
- US20210201135A1 US20210201135A1 US17/044,607 US201817044607A US2021201135A1 US 20210201135 A1 US20210201135 A1 US 20210201135A1 US 201817044607 A US201817044607 A US 201817044607A US 2021201135 A1 US2021201135 A1 US 2021201135A1
- Authority
- US
- United States
- Prior art keywords
- receiver
- transmitter
- training sequence
- messages
- loss function
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000004891 communication Methods 0.000 title description 13
- 238000012549 training Methods 0.000 claims abstract description 203
- 230000005540 biological transmission Effects 0.000 claims abstract description 93
- 238000000034 method Methods 0.000 claims abstract description 13
- 230000006870 function Effects 0.000 claims description 106
- 238000013528 artificial neural network Methods 0.000 claims description 22
- 238000004590 computer program Methods 0.000 claims description 20
- 239000013598 vector Substances 0.000 description 36
- 238000010586 diagram Methods 0.000 description 13
- 238000012545 processing Methods 0.000 description 8
- 238000013507 mapping Methods 0.000 description 7
- 238000010606 normalization Methods 0.000 description 6
- 230000009471 action Effects 0.000 description 5
- 230000004913 activation Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000013459 approach Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 description 2
- 230000003247 decreasing effect Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G06N3/0454—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B1/00—Details of transmission systems, not covered by a single one of groups H04B3/00 - H04B13/00; Details of transmission systems not characterised by the medium used for transmission
- H04B1/02—Transmitters
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B1/00—Details of transmission systems, not covered by a single one of groups H04B3/00 - H04B13/00; Details of transmission systems not characterised by the medium used for transmission
- H04B1/06—Receivers
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L1/00—Arrangements for detecting or preventing errors in the information received
- H04L1/004—Arrangements for detecting or preventing errors in the information received by using forward error control
- H04L1/0041—Arrangements at the transmitter end
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L1/00—Arrangements for detecting or preventing errors in the information received
- H04L1/004—Arrangements for detecting or preventing errors in the information received by using forward error control
- H04L1/0045—Arrangements at the receiver end
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L25/00—Baseband systems
- H04L25/02—Details ; arrangements for supplying electrical power along data transmission lines
- H04L25/0202—Channel estimation
- H04L25/0204—Channel estimation of multiple channels
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L25/00—Baseband systems
- H04L25/02—Details ; arrangements for supplying electrical power along data transmission lines
- H04L25/0202—Channel estimation
- H04L25/0224—Channel estimation using sounding signals
- H04L25/0226—Channel estimation using sounding signals sounding signals per se
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L25/00—Baseband systems
- H04L25/02—Details ; arrangements for supplying electrical power along data transmission lines
- H04L25/03—Shaping networks in transmitter or receiver, e.g. adaptive shaping networks
- H04L25/03006—Arrangements for removing intersymbol interference
- H04L25/03012—Arrangements for removing intersymbol interference operating in the time domain
- H04L25/03114—Arrangements for removing intersymbol interference operating in the time domain non-adaptive, i.e. not adjustable, manually adjustable, or adjustable only during the reception of special signals
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L25/00—Baseband systems
- H04L25/02—Details ; arrangements for supplying electrical power along data transmission lines
- H04L25/03—Shaping networks in transmitter or receiver, e.g. adaptive shaping networks
- H04L25/03006—Arrangements for removing intersymbol interference
- H04L25/03165—Arrangements for removing intersymbol interference using neural networks
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L25/00—Baseband systems
- H04L25/02—Details ; arrangements for supplying electrical power along data transmission lines
- H04L25/03—Shaping networks in transmitter or receiver, e.g. adaptive shaping networks
- H04L25/03006—Arrangements for removing intersymbol interference
- H04L25/03343—Arrangements at the transmitter end
Definitions
- the present specification relates to learning in communication systems.
- a simple communications system includes a transmitter, a transmission channel, and a receiver.
- the design of such communications systems may involve the separate design and optimisation of each part of the system.
- An alternative approach is to consider the entire communication system as a single system and to seek to optimise the entire system.
- this specification describes an apparatus comprising: means for obtaining or generating a transmitter-training sequence of messages for a transmission system, wherein the transmission system comprises a transmitter, a channel and a receiver, wherein the transmitter includes a transmitter algorithm having at least some trainable weights and the receiver includes a receiver algorithm having at least some trainable weights (the transmitter algorithm may be implemented as a differentiable parametric function and the receiver algorithm may be implemented as a differentiable parametric function); means for transmitting perturbed versions of the transmitter-training sequence of messages over the transmission system (wherein the perturbations may be zero-mean Gaussian perturbations); means for receiving first receiver loss function data at the transmitter, the first receiver loss function data being generated based on a received-training sequence as received at the receiver and knowledge of the transmitter training sequence of messages for the transmission system; and means for training at least some weights of the transmitter algorithm based on the first receiver loss function data and knowledge of the transmitter-training sequence of messages and the perturbed versions of the transmitter-training sequence of messages.
- the means for training the at least some weights of the transmitter algorithm may make use of a distribution to generate the perturbations applied to the transmitter-training sequence of messages.
- the first loss function data may be related to one or more of block error rate, bit error rate and categorical cross-entropy.
- the apparatus may further comprises means for repeating the training of the at least some weights of the transmitter algorithm until a first condition is reached.
- the first condition may, for example, be a defined number of iterations and/or a defined performance level.
- the means for training may further comprise optimising one or more of a batch size of the transmitter-training sequence of messages, a learning rate, and a distribution of the perturbations applied to the perturbed versions of the transmitter-training sequence of messages.
- the apparatus may further comprise: means for obtaining or generating a receiver-training sequence of messages for transmission over the transmission system; means for transmitting the receiver-training sequence of messages over the transmission system; means for generating or obtaining second receiver loss function data, the second receiver loss function data being generated based on a received-training sequence as received at the receiver and knowledge of the transmitted receiver-training sequence; and means for training at least some weights of the receiver algorithm based on the second receiver loss function data.
- the second loss function may, for example, be related to one or more of block error rate, bit error rate and categorical cross-entropy
- Some forms of the invention may further comprise means for repeating the training of the at least some weights of the receiver algorithm until a second condition is reached.
- the second condition may, for example, be a defined number of iterations and/or a defined performance level.
- Some forms of the invention may further comprise means for repeating both the training of the at least some weights of the transmitter algorithm and repeating the training of the at least some weights of the transmitter algorithm until a third condition is reached.
- At least some weights of the transmit and receive algorithms may be trained using stochastic gradient descent.
- the apparatus may further comprise means for repeating the training of the at least some weights of the transmitter algorithm until a first condition is reached and means for repeating the training of the at least some weights of the receiver algorithm until a second condition is reached.
- the transmitter algorithm may comprise a transmitter neural network and/or the receiver algorithm may comprise a receiver neural network.
- this specification describes an apparatus comprising: means for obtaining or generating a receiver-training sequence of messages for transmission over a transmission system, wherein the transmitter includes a transmitter algorithm (e.g. a transmitter neural network) having at least some trainable weights and the receiver includes a receiver algorithm (e.g.
- a receiver neural network having at least some trainable weights; means for transmitting the receiver-training sequence of messages over the transmission system; means for generating or obtaining second receiver loss function data, the second receiver loss function data being generated based on a receiver-training sequence as received at the receiver and knowledge of the transmitted receiver-training sequence; means for training at least some weights of the receiver algorithm based on the second receiver loss function data; means for obtaining or generating a transmitter-training sequence of messages for the transmission system; means for transmitting perturbed versions of the transmitter-training sequence of messages over the transmission system; means for receiving first receiver loss function data at the transmitter, the first receiver loss function data being generated based on a received-training sequence as received at the receiver and knowledge of the transmitter training sequence of messages for the transmission system; and means for training at least some weights of the transmitter algorithm based on the first receiver loss function data and knowledge of the transmitter-training sequence of messages and the perturbed versions of the transmitter-training sequence of messages.
- the apparatus of the second aspect may further comprise means for repeating the training of the at least some weights of the transmitter algorithm until a first condition is reached and means for repeating the training of the at least some weights of the receiver algorithm until a second condition is reached. Furthermore, the apparatus may further comprise means for repeating both the training of the at least some weights of the transmitter algorithm and repeating the training of the at least some weights of the transmitter algorithm until a third condition is reached.
- the means may comprise: at least one processor; and at least one memory including computer program code, the at least one memory and computer program code configured to, with the at least one processor, cause the performance of the apparatus.
- this specification describes a method comprising: obtaining or generating a transmitter-training sequence of messages for a transmission system, wherein the transmission system comprises a transmitter, a channel and a receiver, wherein the transmitter includes a transmitter algorithm having at least some trainable weights and the receiver includes a receiver algorithm having at least some trainable weights (the transmitter algorithm may be implemented as a differentiable parametric function and the receiver algorithm may be implemented as a differentiable parametric function); transmitting perturbed versions of the transmitter-training sequence of messages over the transmission system; receiving first receiver loss function data at the transmitter, the first receiver loss function data being generated based on a received-training sequence as received at the receiver and knowledge of the transmitter training sequence of messages for the transmission system; and training at least some weights of the transmitter algorithm based on first receiver loss function data and knowledge of the transmitter-training sequence of messages and the perturbed versions of the transmitter-training sequence of messages.
- the method may further comprise: obtaining or generating a receiver-training sequence of messages for transmission over the transmission system; transmitting the receiver-training sequence of messages over the transmission system; generating or obtaining a second receiver loss function data, the second receiver loss function data being generated based on received-training sequence as received at the receiver and knowledge of the transmitted receiver-training sequence; and training at least some weights of the receiver algorithm based on the second receiver loss function data.
- this specification describes a method comprising: obtaining or generating a receiver-training sequence of messages for transmission over a transmission system, wherein the transmitter includes a transmitter algorithm having at least some trainable weights and the receiver includes a receiver algorithm having at least some trainable weights; transmitting the receiver-training sequence of messages over the transmission system; generating or obtaining second receiver loss function data, the second receiver loss function data being generated based on a received-training sequence as received at the receiver and knowledge of the transmitted receiver-training sequence; training at least some weights of the receiver algorithm based on the second loss function; obtaining or generating a transmitter-training sequence of messages for transmission over the transmission system; transmitting perturbed versions of the transmitter-training sequence of messages over the transmission system; receiver first receiver loss function data at the transmitter, the first receiver loss function data being generated based on a received-training sequence as received at the receiver and knowledge of the transmitter training sequence of messages for the transmission system; and training at least some weights of the transmitter algorithm based on the first receiver loss function data and knowledge of the transmitter
- this specification describes an apparatus configured to perform any method as described with reference to the third or fourth aspect.
- this specification describes computer-readable instructions which, when executed by computing apparatus, cause the computing apparatus to perform any method as described with reference to the first aspect.
- this specification describes a computer program comprising instructions stored thereon for performing at least the following: obtaining or generating a transmitter-training sequence of messages for a transmission system, wherein the transmission system comprises a transmitter, a channel and a receiver, wherein the transmitter includes a transmitter algorithm and the receiver includes a receiver algorithm; transmitting perturbed versions of the transmitter-training sequence of messages over the transmission system; receiving first receiver loss function data at the transmitter, the first receiver loss function data being generated based on a received-training sequence as received at the receiver and knowledge of the transmitter training sequence of messages for the transmission system; and training at least some weights of the transmitter algorithm based on first receiver loss function data and knowledge of the transmitter-training sequence of messages and the perturbed versions of the transmitter-training sequence of messages.
- the computer program may further comprise instructions stored thereon for performing at least the following: obtaining or generating a receiver-training sequence of messages for transmission over the transmission system; transmitting the receiver-training sequence of messages over the transmission system; generating or obtaining a second receiver loss function data, the second receiver loss function data being generated based on received-training sequence as received at the receiver and knowledge of the transmitted receiver-training sequence; and training at least some weights of the receiver algorithm based on the second receiver loss function data.
- this specification describes a non-transitory computer-readable medium comprising program instructions stored thereon for performing at least the following: obtaining or generating a transmitter-training sequence of messages for a transmission system, wherein the transmission system comprises a transmitter, a channel and a receiver, wherein the transmitter includes a transmitter algorithm and the receiver includes a receiver algorithm; transmitting perturbed versions of the transmitter-training sequence of messages over the transmission system; receiving first receiver loss function data at the transmitter, the first receiver loss function data being generated based on a received-training sequence as received at the receiver and knowledge of the transmitter training sequence of messages for the transmission system; and training at least some weights of the transmitter algorithm based on first receiver loss function data and knowledge of the transmitter-training sequence of messages and the perturbed versions of the transmitter-training sequence of messages.
- the non-transitory computer-readable medium may further comprise program instructions stored thereon for performing at least the following: obtaining or generating a receiver-training sequence of messages for transmission over the transmission system; transmitting the receiver-training sequence of messages over the transmission system; generating or obtaining a second receiver loss function data, the second receiver loss function data being generated based on received-training sequence as received at the receiver and knowledge of the transmitted receiver-training sequence; and training at least some weights of the receiver algorithm based on the second receiver loss function data.
- this specification describes an apparatus comprising: at least one processor; and at least one memory including computer program code which, when executed by the at least one processor, causes the apparatus to: obtain or generate a transmitter-training sequence of messages for a transmission system, wherein the transmission system comprises a transmitter, a channel and a receiver, wherein the transmitter includes a transmitter algorithm and the receiver includes a receiver algorithm; transmit perturbed versions of the transmitter-training sequence of messages over the transmission system; receive first receiver loss function data at the transmitter, the first receiver loss function data being generated based on a received-training sequence as received at the receiver and knowledge of the transmitter training sequence of messages for the transmission system; and train at least some weights of the transmitter algorithm based on first receiver loss function data and knowledge of the transmitter-training sequence of messages and the perturbed versions of the transmitter-training sequence of messages.
- the computer code may further cause the apparatus to: obtain or generate a receiver-training sequence of messages for transmission over the transmission system; transmit the receiver-training sequence of messages over the transmission system; generate or obtain a second receiver loss function data, the second receiver loss function data being generated based on received-training sequence as received at the receiver and knowledge of the transmitted receiver-training sequence; and train at least some weights of the receiver algorithm based on the second receiver loss function data.
- FIG. 1 is a block diagram of an exemplary end-to-end communication system
- FIG. 2 is a block diagram of an exemplary transmitter used in an exemplary implementation of the system of FIG. 1 ;
- FIG. 3 is a block diagram of an exemplary receiver used in an exemplary implementation of the system of FIG. 1 ;
- FIG. 4 is a flow chart showing an algorithm in accordance with an exemplary embodiment
- FIG. 5 is a flow chart showing an algorithm in accordance with an exemplary embodiment
- FIG. 6 is a block diagram of an exemplary end-to-end communication system in accordance with an example embodiment
- FIG. 7 is a flow chart showing an algorithm in accordance with an exemplary embodiment
- FIG. 8 is a block diagram of an exemplary end-to-end communication system in accordance with an example embodiment
- FIG. 9 is a block diagram of a components of a system in accordance with an exemplary embodiment.
- FIGS. 10 a and 10 b show tangible media, respectively a removable memory unit and a compact disc (CD) storing computer-readable code which when run by a computer perform operations according to embodiments.
- CD compact disc
- FIG. 1 is a block diagram of an exemplary communication system, indicated generally by the reference numeral 1 , in which exemplary embodiments may be implemented.
- the system 1 includes a transmitter 2 , a channel 4 and a receiver 6 . Viewed at a system level, the system 1 converts an input symbol (s) (also called a message) received at the input to the transmitter 2 into an output symbol ( ⁇ ) at the output of the receiver 6 .
- s input symbol
- ⁇ output symbol
- the transmitter 2 includes a module 10 (such as a neural network) for implementing a transmitter algorithm.
- the receiver 6 includes a module 14 (such as a neural network) for implementing a receiver algorithm.
- the modules 10 and 14 are trained in order to optimise the performance of the system as a whole.
- the transmitter algorithm implemented by the module 10 may be implemented as a differentiable parametric function and may include at least some trainable weights (which may be trainable through stochastic gradient descent).
- the receiver algorithm implemented by the module 14 may be implemented as a differentiable parametric function and may include at least some trainable weights (which may be trainable through stochastic gradient descent).
- the transmitter hardware imposes constraints on x, e.g., an energy constraint ⁇ x ⁇ 2 2 ⁇ n, an amplitude constraint
- the channel is described by the conditional probability density function (pdf)p(y
- the receiver Upon reception of y, the receiver produces the estimate ⁇ of the transmitted message s.
- FIG. 2 is a block diagram showing details of an exemplary implementation of the transmitter 2 described above.
- the transmitter 2 includes an embedding module 22 , a dense layer of one or more units 24 (e.g. one or more neural networks), a complex vector generator 26 and a normalization module 28 .
- the modules within the transmitter 2 are provided by way of example and modifications are possible.
- the complex vector generator 26 and the normalization module 28 could be provided in a different order.
- the message index s is fed into the embedding module 22 , embedding: n emb , that transforms s into an n emb -dimensional real-valued vector.
- the embedding module 22 can optionally be followed by several dense neural network (NN) layers 24 with possible different activation functions (such as ReLU, tanh, signmoid, linear etc.).
- NN dense neural network
- a normalization is applied by the normalization module 28 that ensures that power, amplitude or other constraints are met.
- the result of the normalization process is the transmit vector x of the transmitter 2 (where x ⁇ n ).
- the order of the complex vector generation and the normalization could be reversed.
- TX maps an integer from the set to an n-dimensional complex-valued vector.
- FIG. 3 is a block diagram showing details of an exemplary implementation of the receiver 6 described above.
- the receiver 6 includes a real vector generator 32 , one or more layers 34 (e.g. one or more neural networks) and a softmax module 36 .
- the output of the softmax module is a probability vector that is provided to the input of an arg max module 38 .
- the modules within the receiver 6 are provided by way of example and modifications are possible.
- the result is fed into the one or more layers 34 , which layers may have different activation functions such as ReLU, tanh, sigmoid, linear, etc.
- the receiver 6 defines the mapping:
- the receiver 6 maps an n-dimensional complex-valued vector to an M-dimensional probability vector and an integer from the set .
- the example above describes how this may be implemented using a neural network architecture, although other architectures are possible.
- the number of dimensions y can be different from n in case the channel provides a different number of relevant outputs.
- FIG. 4 is a flow chart showing an algorithm, indicated generally by the reference numeral 40 , in accordance with an exemplary embodiment.
- the algorithm 40 starts at operation 42 , where the transmitter 2 and the receiver 6 of the transmission system 1 are initialised. Note that the algorithm 40 acts on the system 1 , which system includes a real channel 4 .
- the receiver 6 is trained. As discussed in detail below, the receiver 6 is trained based on known training data sent by the transmitter 2 using the channel 4 .
- the trainable parameters of the receiver algorithm e.g. the receiver layers 34 , which may be implemented using neural networks
- SGD stochastic gradient descent
- the goal of the optimisation is to improve a chosen performance metric (or reward), such as block error rate (BLER), bit error rate (BER), categorical cross-entropy, etc.
- the transmitter is trained.
- the transmitter 2 sends is a sequence of known messages to the receiver 6 .
- the transmitter signals associated with each message are slightly perturbed, for example by adding random vectors taken from a known distribution.
- the receiver computer the chosen performance metric or reward (such as BLER, BER, categorical cross-entropy, as discussed above) for the received signals and feeds the metric or reward data back to the transmitter. Note that the receiver is not optimised at part of the operation 48 .
- the trainable parameters of the transmitter algorithm are optimised based on stochastic gradient descent (SGD) by estimating the gradient of the metric or reward with respect to its trainable parameters using the knowledge of the transmitted messages and signals, as well as the known distribution of the random perturbations.
- SGD stochastic gradient descent
- the communication system 1 is trained using a two-step process.
- the two steps may, for example, be carried out iteratively until and desired performance level is obtained and/or until a predefined number of iterations have been completed.
- There are a number of alternative mechanisms for implementing the operations 46 , 50 and/or 52 such as stopping when a loss function being used has not decreased for a given number of iterations or stopping when a metric such as block error rate (BLER) has reached a desired level.
- BLER block error rate
- FIG. 5 is a flow chart showing an algorithm, indicated generally by the reference numeral 60 , in accordance with an exemplary embodiment.
- the algorithm 60 provides further detail regarding the receiver training operation 44 of the algorithm 40 described above.
- FIG. 6 is a block diagram of an exemplary end-to-end communication system, indicated generally by the reference numeral 70 , in accordance with an example embodiment.
- the system 70 includes the transmitter 2 , channel 4 and receiver 6 described above with reference to FIG. 1 .
- the system 70 demonstrates aspects of the algorithm 60 .
- the algorithm 60 starts at operation 62 , where the following steps are conducted:
- the channel 4 is used to transmit vectors from the transmitter 2 to the receiver 6 as follows:
- a loss function is generated and stochastic gradient descent used for training the receiver as follows (and as indicated in FIG. 6 ):
- L R,i ⁇ log ([pR,i] s R,i ) is the categorical cross entropy between the input message and the output vector p R,i .
- the batch size N R as well as the learning rate could be optimization parameters of the training operation 44 .
- FIG. 7 is a flow chart showing an algorithm, indicated generally by the reference numeral 80 , in accordance with an exemplary embodiment.
- the algorithm 80 provides further detail regarding the transmitter training operation 48 of the algorithm 40 described above.
- FIG. 8 is a block diagram of an exemplary end-to-end communication system, indicated generally by the reference numeral 90 , in accordance with an example embodiment.
- the system 90 includes the transmitter 2 , channel 4 and receiver 6 described above with reference to FIG. 1 .
- the system also includes a perturbation module 92 between the transmitter 2 and the channel 4 .
- the system 90 demonstrates aspects of the algorithm 80 .
- the algorithm 80 starts at operation 82 , where the following steps are conducted:
- p( ⁇ ) could be the muitivariate complex Gaussian distribution (O, ⁇ 2 I n ) with some small variance ⁇ 2 .
- the perturbation vectors ⁇ i are added to the transmitter output using the perturbation module 92 .
- the channel 4 is used to transmit perturbed vectors as follows:
- a loss function is generated and stochastic gradient descent used for training the transmitter as follows:
- log is ([pTi]s T ,) is the categorical cross entropy between the input message and the output vector p T,i ,
- the loss function L T,i could take other forms and does not necessarily need to be differentiable in contrast to the loss function used for receiver training in Section 1.4.
- the batch-size N T as well as the learning-rate; (and possible other parameters of the chosen SGD variant (e.g., ADAM, RMSProp, Momentum)) are optimization parameters.
- the stop criterion in Step 8 can take multiple forms: stop after a fixed number of training iterations, stop when the loss function L T has not decreased during, a fixed number of iterations, stop when the loss or another associated metric such as the BLER
- the criteria to repeat can be similar.
- the training processes described herein encompass a number of variants.
- the use of reinforcement learning as described herein relies on exploring the policy space (i.e. the space of possible state to action mappings).
- the policy is the mapping implemented by the transmitter
- the state space is the source symbol alphabet
- the action space is n . Exploring can be done in numerous ways, two of the most popular approaches being:
- Gaussian policy in which a perturbation vector ⁇ is drawn from a multivariate zero-mean normal distribution and added to the current policy. This ensures exploration “in the neighbourhood” of the current policy.
- the covariance matrix of the normal distribution from which the perturbation vector ⁇ is drawn in the Gaussian policy, and the ⁇ parameter of the ⁇ -greedy approach, are usually fixed parameters, i.e., not learned during training. These parameters control the “amount of exploration”, as making these parameters smaller reduces the amount of random exploration, and favours actions from the current policy.
- the goal is not communicate messages s ⁇ but rather vectors s ⁇ N which are reconstructed by the receiver.
- s could be a digital image and the goal of the receiver is to reconstruct the vector s ⁇ N as good as possible.
- FIGS. 5 and 6 shown the necessary changes to transmitter and receiver, respectively, to implement this idea.
- MSE mean squared error
- the transmitter sends a data vector s ⁇ N , but the goal of the receiver is to classify the transmitted vector into one out of M classes.
- s could be an image and the receiver's goal is to tell whether s contains a dog or a cat.
- the realization of the transmitter as in FIG. 5 could be used while the receiver is implemented as in FIG. 3 .
- the loss functions for training would then be chosen as in Section 1.3 with the difference that each transmit vector s has an associated label l ⁇ which is used to compute the loss, i.e.,
- FIG. 9 is a schematic diagram of components of one or more of the modules described previously (e.g. the transmitter or receiver neural networks), which hereafter are referred to generically as processing systems 110 .
- a processing system 110 may have a processor 112 , a memory 114 closely coupled to the processor and comprised of a RAM 124 and ROM 122 , and, optionally, hardware keys 120 and a display 128 .
- the processing system no may comprise one or more network interfaces 118 for connection to a network, e.g. a modem which may be wired or wireless.
- the processor 112 is connected to each of the other components in order to control operation thereof.
- the memory 114 may comprise a non-volatile memory, a hard disk drive (HDD) or a solid state drive (SSD).
- the ROM 122 of the memory 114 stores, amongst other things, an operating system 125 and may store software applications 126 .
- the RAM 124 of the memory 114 is used by the processor 112 for the temporary storage of data.
- the operating system 125 may contain code which, when executed by the processor, implements aspects of the algorithms 40 , 60 and 80 .
- the processor 112 may take any suitable form. For instance, it may be a microcontroller, plural microcontrollers, a processor, or plural processors.
- the processing system no may be a standalone computer, a server, a console, or a network thereof.
- the processing system no may also be associated with external software applications. These may be applications stored on a remote server device and may run partly or exclusively on the remote server device. These applications may be termed cloud-hosted applications.
- the processing system no may be in communication with the remote server device in order to utilize the software application stored there.
- FIGS. boa and bob show tangible media, respectively a removable memory unit 165 and a compact disc (CD) 168 , storing computer-readable code which when run by a computer may perform methods according to embodiments described above.
- the removable memory unit 165 may be a memory stick, e.g. a USB memory stick, having internal memory 166 storing the computer-readable code.
- the memory 166 may be accessed by a computer system via a connector 167 .
- the CD 168 may be a CD-ROM or a DVD or similar. Other forms of tangible storage media may be used.
- Embodiments of the present invention may be implemented in software, hardware, application logic or a combination of software, hardware and application logic.
- the software, application logic and/or hardware may reside on memory, or any computer media.
- the application logic, software or an instruction set is maintained on any one of various conventional computer-readable media.
- a “memory” or “computer-readable medium” may be any non-transitory media or means that can contain, store, communicate, propagate or transport the instructions for use by or in connection with an instruction execution system, apparatus, or device, such as a computer.
- references to, where relevant, “computer-readable storage medium”, “computer program product”, “tangibly embodied computer program” etc., or a “processor” or “processing circuitry” etc. should be understood to encompass not only computers having differing architectures such as single/multi-processor architectures and sequencers/parallel architectures, but also specialised circuits such as field programmable gate arrays FPGA, application specify circuits ASIC, signal processing devices and other devices. References to computer program, instructions, code etc.
- programmable processor firmware such as the programmable content of a hardware device as instructions for a processor or configured or configuration settings for a fixed function device, gate array, programmable logic device, etc.
- circuitry refers to all of the following: (a) hardware-only circuit implementations (such as implementations in only analogue and/or digital circuitry) and (b) to combinations of circuits and software (and/or firmware), such as (as applicable): (i) to a combination of processor(s) or (ii) to portions of processor(s)/software (including digital signal processor(s)), software, and memory(ies) that work together to cause an apparatus, such as a server, to perform various functions) and (c) to circuits, such as a microprocessor(s) or a portion of a microprocessor(s), that require software or firmware for operation, even if the software or firmware is not physically present.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- Power Engineering (AREA)
- Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Probability & Statistics with Applications (AREA)
- Mobile Radio Communication Systems (AREA)
- Information Transfer Between Computers (AREA)
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/IB2018/000814 WO2019193377A1 (en) | 2018-04-03 | 2018-04-03 | End-to-end learning in communication systems |
Publications (1)
Publication Number | Publication Date |
---|---|
US20210201135A1 true US20210201135A1 (en) | 2021-07-01 |
Family
ID=63517920
Family Applications (3)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US17/044,607 Pending US20210201135A1 (en) | 2018-04-03 | 2018-04-03 | End-to-end learning in communication systems |
US17/044,584 Pending US20210027161A1 (en) | 2018-04-03 | 2018-06-07 | Learning in communication systems |
US17/044,553 Active US11082264B2 (en) | 2018-04-03 | 2018-06-29 | Learning in communication systems |
Family Applications After (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US17/044,584 Pending US20210027161A1 (en) | 2018-04-03 | 2018-06-07 | Learning in communication systems |
US17/044,553 Active US11082264B2 (en) | 2018-04-03 | 2018-06-29 | Learning in communication systems |
Country Status (4)
Country | Link |
---|---|
US (3) | US20210201135A1 (zh) |
EP (3) | EP3776365A1 (zh) |
CN (3) | CN112236782A (zh) |
WO (3) | WO2019193377A1 (zh) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20220095129A1 (en) * | 2020-09-24 | 2022-03-24 | Rohde & Schwarz Gmbh & Co. Kg | Adaptive coverage optimization in single-frequency networks (sfn) |
Families Citing this family (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11552731B2 (en) | 2018-07-20 | 2023-01-10 | Nokia Technologies Oy | Learning in communication systems by updating of parameters in a receiving algorithm |
US11750436B2 (en) * | 2019-05-30 | 2023-09-05 | Nokia Technologies Oy | Learning in communication systems |
FI20195547A1 (en) | 2019-06-20 | 2020-12-21 | Nokia Technologies Oy | Systems and apparatus for adaptive modulation category |
US11570030B2 (en) * | 2019-10-11 | 2023-01-31 | University Of South Carolina | Method for non-linear distortion immune end-to-end learning with autoencoder—OFDM |
US11128498B2 (en) | 2020-02-25 | 2021-09-21 | Nokia Solutions And Networks Oy | Communication-channel tracking aided by reinforcement learning |
US20210303662A1 (en) * | 2020-03-31 | 2021-09-30 | Irdeto B.V. | Systems, methods, and storage media for creating secured transformed code from input code using a neural network to obscure a transformation function |
CN115668218A (zh) * | 2020-05-22 | 2023-01-31 | 诺基亚技术有限公司 | 通信系统 |
CN113193925B (zh) * | 2021-02-09 | 2023-08-11 | 中国人民解放军战略支援部队信息工程大学 | 一种通信系统的优化处理方法、装置及电子设备 |
CN115186797B (zh) * | 2022-06-06 | 2023-05-30 | 山西大学 | 一种语用通信方法及系统 |
CN117295096B (zh) * | 2023-11-24 | 2024-02-09 | 武汉市豪迈电力自动化技术有限责任公司 | 基于5g短共享的智能电表数据传输方法及系统 |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20070162814A1 (en) * | 2006-01-09 | 2007-07-12 | Broadcom Corporation, A California Corporation | LDPC (low density parity check) code size adjustment by shortening and puncturing |
US20180174050A1 (en) * | 2016-12-15 | 2018-06-21 | Google Inc. | Adaptive Channel Coding Using Machine-Learned Models |
Family Cites Families (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5293453A (en) * | 1990-06-07 | 1994-03-08 | Texas Instruments Incorporated | Error control codeword generating system and method based on a neural network |
JP4154229B2 (ja) * | 2002-12-27 | 2008-09-24 | 富士通株式会社 | 適応アレーアンテナ制御装置 |
GB2398976B (en) * | 2003-02-28 | 2006-03-08 | Samsung Electronics Co Ltd | Neural network decoder |
US7606138B2 (en) * | 2003-09-29 | 2009-10-20 | Her Majesty The Queen In Right Of Canada, As Represented By The Minister Of Industry, Through The Communications Research Centre Canada | Multi-symbol encapsulated OFDM system |
US8331420B2 (en) * | 2008-04-14 | 2012-12-11 | General Dynamics C4 Systems, Inc. | Methods and apparatus for multiple-antenna communication of wireless signals with embedded pilot signals |
JP5308102B2 (ja) * | 2008-09-03 | 2013-10-09 | 日本電信電話株式会社 | 誤り数別識別スコア・事後確率計算方法と、その方法を用いた誤り数重み付き識別学習装置とその方法と、その装置を用いた音声認識装置と、プログラムと記録媒体 |
WO2011150533A1 (en) * | 2010-06-03 | 2011-12-08 | Nokia Siemens Networks Oy | Base station calibration |
US9015093B1 (en) * | 2010-10-26 | 2015-04-21 | Michael Lamport Commons | Intelligent control with hierarchical stacked neural networks |
WO2014205376A1 (en) * | 2013-06-21 | 2014-12-24 | Marvell World Trade Ltd. | Methods and systems for determining indicators used in channel state information (csi) feedback in wireless systems |
WO2016078722A1 (en) * | 2014-11-20 | 2016-05-26 | Huawei Technologies Co., Ltd. | Methods and nodes in a wireless communication network |
CN106295678B (zh) * | 2016-07-27 | 2020-03-06 | 北京旷视科技有限公司 | 神经网络训练与构建方法和装置以及目标检测方法和装置 |
US10546230B2 (en) * | 2016-08-12 | 2020-01-28 | International Business Machines Corporation | Generating labeled data by sequence-to-sequence modeling with added perturbations to encoded information |
CN107241320A (zh) * | 2017-05-26 | 2017-10-10 | 微梦创科网络科技(中国)有限公司 | 一种基于图像的人机鉴别方法及鉴别系统 |
-
2018
- 2018-04-03 WO PCT/IB2018/000814 patent/WO2019193377A1/en unknown
- 2018-04-03 EP EP18765704.4A patent/EP3776365A1/en active Pending
- 2018-04-03 US US17/044,607 patent/US20210201135A1/en active Pending
- 2018-04-03 CN CN201880094274.8A patent/CN112236782A/zh active Pending
- 2018-06-07 CN CN201880093531.6A patent/CN112166568B/zh active Active
- 2018-06-07 EP EP18730331.8A patent/EP3776940A1/en active Pending
- 2018-06-07 WO PCT/EP2018/065006 patent/WO2019192740A1/en unknown
- 2018-06-07 US US17/044,584 patent/US20210027161A1/en active Pending
- 2018-06-29 US US17/044,553 patent/US11082264B2/en active Active
- 2018-06-29 WO PCT/IB2018/001029 patent/WO2019193380A1/en unknown
- 2018-06-29 EP EP18774108.7A patent/EP3776941A1/en active Pending
- 2018-06-29 CN CN201880093390.8A patent/CN112166567B/zh active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20070162814A1 (en) * | 2006-01-09 | 2007-07-12 | Broadcom Corporation, A California Corporation | LDPC (low density parity check) code size adjustment by shortening and puncturing |
US20180174050A1 (en) * | 2016-12-15 | 2018-06-21 | Google Inc. | Adaptive Channel Coding Using Machine-Learned Models |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20220095129A1 (en) * | 2020-09-24 | 2022-03-24 | Rohde & Schwarz Gmbh & Co. Kg | Adaptive coverage optimization in single-frequency networks (sfn) |
Also Published As
Publication number | Publication date |
---|---|
US11082264B2 (en) | 2021-08-03 |
EP3776940A1 (en) | 2021-02-17 |
WO2019193377A1 (en) | 2019-10-10 |
WO2019193380A1 (en) | 2019-10-10 |
CN112236782A (zh) | 2021-01-15 |
EP3776941A1 (en) | 2021-02-17 |
CN112166568A (zh) | 2021-01-01 |
CN112166568B (zh) | 2023-10-20 |
WO2019192740A1 (en) | 2019-10-10 |
US20210027161A1 (en) | 2021-01-28 |
CN112166567A (zh) | 2021-01-01 |
CN112166567B (zh) | 2023-04-18 |
US20210099327A1 (en) | 2021-04-01 |
EP3776365A1 (en) | 2021-02-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20210201135A1 (en) | End-to-end learning in communication systems | |
US11556799B2 (en) | Channel modelling in a data transmission system | |
US11514252B2 (en) | Discriminative caption generation | |
US20210374529A1 (en) | End-to-end learning in communication systems | |
US11797864B2 (en) | Systems and methods for conditional generative models | |
US11750436B2 (en) | Learning in communication systems | |
US20230394245A1 (en) | Adversarial Bootstrapping for Multi-Turn Dialogue Model Training | |
US11804860B2 (en) | End-to-end learning in communication systems | |
US11736899B2 (en) | Training in communication systems | |
CN116431597A (zh) | 用于训练数据分类模型的方法、电子设备和计算机程序产品 | |
US11552731B2 (en) | Learning in communication systems by updating of parameters in a receiving algorithm | |
US20220209888A1 (en) | Iterative Detection in a Communication System | |
US20220083870A1 (en) | Training in Communication Systems | |
US20230246887A1 (en) | Training in Communication Systems | |
US20240105166A1 (en) | Self-supervised learning method based on permutation invariant cross entropy and electronic device thereof | |
US20220263596A1 (en) | Transmitter Algorithm | |
CN115565023A (zh) | 用于图像处理的方法、装置、电子设备和介质 | |
CN115237856A (zh) | 文件标注的方法、设备和计算机程序产品 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AS | Assignment |
Owner name: NOKIA TECHNOLOGIES OY, FINLAND Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:HOYDIS, JAKOB;AOUDIA, FAYCAL AIT;REEL/FRAME:054051/0790 Effective date: 20190117 |
|
AS | Assignment |
Owner name: NOKIA TECHNOLOGIES OY, FINLAND Free format text: CORRECTIVE ASSIGNMENT TO CORRECT THE SECOND INVENTOR'S NAME PREVIOUSLY RECORDED ON REEL 054051 FRAME 0790. ASSIGNOR(S) HEREBY CONFIRMS THE AIT AOUDIA, FAYCAL;ASSIGNORS:HOYDIS, JAKOB;AIT AOUDIA, FAYCAL;REEL/FRAME:054273/0807 Effective date: 20190117 |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: APPLICATION DISPATCHED FROM PREEXAM, NOT YET DOCKETED |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: DOCKETED NEW CASE - READY FOR EXAMINATION |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: NON FINAL ACTION MAILED |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: RESPONSE TO NON-FINAL OFFICE ACTION ENTERED AND FORWARDED TO EXAMINER |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: FINAL REJECTION MAILED |