Linear Block Code Decoding Using Neural
Network
Kiran Maru
Electronics and Communication Engineering
Institute Of Technology, Nirma University
Ahmedabad, Gujarat
15bec061@nirmauni.ac.in
Abstract—In this paper the linear block code
decoder is constructed by neural network. A block
code uses an encoder that accepts a block of message
symbols, and generates a block of code word symbols
at the output. This type is in contrast to a
convolutional code where the encoder accepts a
continuous stream of symbols and similarly generates
a continuous encoded out- put stream.The neural
network will be adapted for a single-bit error. Each
layer of a neural network will simulate a linear block
code decoder stage. The syndrome generator, the error
detection, and the error correction stages of the linear
block code decoder will be simulated by the proposed
neural network.
Index Terms—Linear Block Code, Neural Network,
Syndrome, Error detection, and Error Correction
• INTRODUCTION
Here we have field of neural networks is now
extremely vast and interdisciplinary, drawing interest
from researchers in many different areas such as
engineering (including biomedical engineering), physics,
neurology, psychology, medicine, mathematics,
computer science, chemistry, and economics .Artificial
neural networks provide a neurocomputing approach to
solve complex problems that might otherwise not have a
tractable solution. Applications of neural networks
include (but are not limited to) prediction and
forecasting, associative memory, function
approximation, clustering, data compression, speech
recognition, feature extraction, combinational
optimization, solution of matrix algebra problems, blind
source separation and solution of differential equations.
When a digital message is transmitted over a long
distance, the received message may not be exactly as it
was sent since there may be some interference. In these
situations we should be able to detect and if possible to
correct errors.
Neural networks (NNs) are powerful computational
models that have attracted much attention in many
applications [4]. However, the decoding problem poses a
Subham Jadav
Electronics and Communication Engineering
Institute Of Technology, Nirma University
Ahmedabad, Gujarat
16bec050@nirmauni.ac.in
certain level of difficulty to most of the NN classifiers
because there are a large number of categories to be
classified and the classification requires very high
precision so as to discriminate among patterns of only
one Hamming distance from one to the others .We shall
show, in this paper, that the decoding rules of a number
of LBCs have a close connection with the class of high-
order .
• LINEAR BLOCK CODE DECODER
The binary linear block codes have been defined
over the binary Galois Field GF (2) of two elements {0, 1}
using modulo-2 arithmetic. The linear block code is called
a linear (n, k) code, where “k” is the message length to be
coded and “n” is the length of the message after coding.
The linear block codes are described in terms of their
generator matrix (G), parity check matrix (H), minimum
distance (dmin), and syndrome (S). All the three phases in
the linear block code decoder will be constructed by the
use of neural network. So a neural network with five layers
will be constructed. The first and second layers will
estimate the syndrome vector, the second and third layers
will detect the error, and the third, fourth, and fifth layers
will correct the error, as shown in Fig. 2. The neural
network (plotted in bold lines) is just for delaying the input
in order to be ready for being exclusively ORedwith the
error vector “e”.
This phase is similar to the first block in the linear block
code decoder; which is responsible for generating the
syndrome vector “S”. According to S r. HT, so that the
synaptic weights of this phase must be equal to the
transpose of the parity check matrix “H
• The Random Neural Network (RNN) Model
In the random neural network model [5] signals in the
form of spikes of unit amplitude circulate among the
neurons. Positive signals represent excitation and neg-
active signals represent inhibition. Each neuron's
state is a non-negative its potential, which in-creases
when an excitation signal arrives to it, and decreases
when an inhibition signal arrives. An excitatory spike
is interpreted as a \+1" signal at a receiving neuron,
while an inhibitory spike is interpreted as a \ 1" signal.
A neuron i emitting a spike, whether it is an ex-
citation or an inhibition, will lose potential of one
unit, going from some state whose value is ki to the
state of value ki 1. The state of the n-neuron network
at time t, is represented by the vector of non-negative
integers k(t) = (k1(t); :kn(t)), where ki(t) is the
potential or integer state of neuron I .We will denote
by k and ki arbitrary values of the state vector and of
the i-th neuron's state.
• Genetic Algorithms and Simulated
Annealing
Genetic algorithm (GA) and simulated annealing (SA)
are two kinds of useful stochastic techniques which
can be used to solve optimization problems
efficiently. SA is based on thermodynamics and can
be viewed as an algorithm which generates a sequence
of Markov chains to approach the optimal solutions of
the problem. This sequence of Markov Chains is
controlled by a gradually decreasing temperature of
the system. Theoretically, the probability distribution
of the system configurations generated by SA will
approach to the Boltzmann distribution when the
system has reached equilibrium at a certain fixed
temperature. When the system temperature decreases
gradually to zero. GAs are general purpose
optimization techniques which borrow the spirit of
natural selection from evolution theory. Based on
natural selection, GA tries to inherit the genes with
good fitness from generation to generation. For
eliminating the poor fitting candidates in each
iteration, GA uses the reproduction plan to exhibit
selection pressure, forcing bad ones hard to survive.
In addition, GA applies genetic operations, such as
crossover and mutation, to existing genes for surfing
over the search space. Reproduction plans or genetic
operators may behave in very different ways, but
generally speaking, a typical GA often consists of a
reproduction phase and a manipulation phase.
• Decoding of Linear Block Codes
The general idea of decoding an LBC can be described as
follows. A systematic (n,k) code, in which there are k
information bits and m = n-k parity bits for each codeword,
can be represented by a parity-check matrix H = [hij]m,n, hij
{0,1}. Let A = [a1, a2, … , ak] be an information word. After
A being added with some parities and then transmitted, the
receiving end receives a word V = [v1,v2, … , vn] probably
with some errors in its bits. The received word V is then
multiplied (mudulo2) by the parity-check matrix H to result in
a syndrome vector S = VHT = [s1, s2, … , sm],
The syndrome S provides the information to decode the
codewords V: If S is a zero vector, there would be no errors;
the parity bits vi, i = k+1, k+2, … , n, are discarded and the
information bits are directly accessed, i.e., ai = vi for i = 1, 2,
… , k. If a single error occurs in bit vj, then S matches the jth
column of H and the jth bit vj has to be complemented. For t-
error correcting codes, if S matches the sum (in modulo 2) of
P (P,t) columns of H, then the P bits corresponding to these
constituent p columns of H are in error.
• The Neural Decoders
The conventional decoding rules for cyclic and BCH codes
have no direct transforms resulting in decoding structures
representable by high-order perceptrons. To reduce the
number of terms required, one depends on a robust
optimization method and the method we choose is the
genetic evolution. GAs are more suitable for this structure-
adaptation application than other major optimization methods
such as gradient-based algorithms, enumeration, and
random search due to several reasons. First, the search
space of possible network structures is large, possible
network structures for n binary inputs. Such multimodal
surface would baffle most of the hill-climbing methods.
Another more favorable reason for using GAs is that highly
fit terms are less likely to be destroyed under the genetic
operators and thus often lead to faster convergence,
especially when comparing with the method of SA.
A GA begins with a randomly generated population of
individuals, which are often bit-string encodings of potenitial
solutions to the concerned problem. Each individual is
evaluated to show its fitness. High-fitness individuals receive
a high selection probability for reproduction. Simple selection
rule might use a roulette wheel to select an individual
according to the percentage of its fitness over all population
fitness. A number of genetic operators such as mutation
crossover are applied to the selected individuals to
produce new populations of the next generation
• Training Patterns

Hamming code are used excluding the all 00s code and
the all 10s code as mentioned before. Thus, we
have n = 7(inputs), N = 14 (patterns), m = 14(outputs)
and I = f1; 2;::: 14g. As an example, the codeword x4 =
( 1; 1; 1; 1; 1; 1; 1) will be associated with the tar- get
output y4 = (1; 1; 1; 0:1; 1; 1; 1; 1; 1; 1; 1; 1; 1; 1) and
hence its class label is c = 4. The training process
iscarried out using the RNNSIM v1.0 package1
(Random Neural Network Simulator) after some slight
modifications to incorporate the general recurrent
training algorithm into the program.
capability of the used code.
In future, we can consider using the RNN model as a
dynamical system in which the codewords are the
constant attractors of the system.
• References
E. R. Berlekamp, R. McEliece,and H.Tilborg, On the inherent
intractability of certain coding problems," IEEE Transaction
on Inf. Theory, vol. 24, No. 3, pp. 384-386, May1978

Blahut, R. E., Theory and Practice of Error Control Codes,

• Simulation Results
The proposed neural decoder was implemented in C
language on Sun Sparc-II workstation. Unless
otherwise stated, a typical parameter setting chooses a
crossover rate 0.9, a mutation rate 0.05, and an iteration
bound IB=10. Population size and maximum generation
are chosen depending on the number of training
patterns.
Addison- Wesley, MA, 1984.
F.M.Ham and I. Kostanic, Principles of Neurocomputing for
Science and Engineering. McGraw-Hill, 2001.
E. Gelenbe, \Learning in the recurrent random neural
network," Neural Computation, vol. 5, no. 1, pp. 154-
164, 1993.

Simulation examples are taken from short-length cyclic

codes. Short-length codes yield reasonable sizes of
training sets and can be extended to useful long codes
by various techniques in the theory of ECCs, such as
product codes and nested codes [1]. They also serve as
good examples to illustrate the effectiveness of the
presented approach.

The first example is the class of (2m-1,2m-1-m) single-

error correcting Hamming code. The simplest nontrivial
Hamming code is the (7,4) code. It contains a total of
128 codewords, in which 16 are legal codewords and
the others are composed by the 7 erroneous codewords
of Hamming distance 1 from each legal ones. The four
bipolar information bits are denoted as x1, x2, x3, x4
and the three parity bits are x5, x6, x7. They are related
as x5= x1x2x4, x6= x1x3x4, and x7= x2x3x4. This
relationship is often described by a parity matrix:

• Conclusions

The linear block code decoder that works on the Galois

fields two (GF (2)), have been solved by the proposed
neural network
The proposed decoder can reduces the error probability
to zero in the range of the error correcting capacity of
the used code.It have been shown through simulation
that the neural based decoder is much better than
the hard decision decoder for decoding codewords
corrupted with errors more than the correction