diff --git a/sw/decoders/naive_soft_decision.py b/sw/decoders/naive_soft_decision.py
new file mode 100644
index 0000000..2440b31
--- /dev/null
+++ b/sw/decoders/naive_soft_decision.py
@@ -0,0 +1,54 @@
+import numpy
+import numpy as np
+import itertools
+
+
+class SoftDecisionDecoder:
+    """This class naively implements a soft decision decoder. This decoder calculates
+    the posterior probability for each codeword and then chooses the one with the largest
+    probability.
+    """
+
+    def __init__(self, G: np.array, H: np.array):
+        """Construct a new SotDecisionDecoder object.
+
+        :param G: Generator matrix
+        :param H: Parity check matrix
+        """
+        self._G = G
+        self._H = H
+        self._datawords, self._codewords = self._gen_codewords()
+        self._codewords_bpsk = self._codewords * 2 - 1  # The codewords, but mapped to [-1, 1]^n
+
+    def _gen_codewords(self) -> np.array:
+        """Generate a list of all possible codewords.
+
+        :return: Numpy array of the form [[codeword_1], [codeword_2], ...]
+        """
+        k, n = self._G.shape
+
+        # Generate a list of all possible data words
+        u_lst = [list(i) for i in itertools.product([0, 1], repeat=k)]
+        u_lst = np.array(u_lst)
+
+        # Map each data word onto a codeword
+        c_lst = np.dot(u_lst, self._G) % 2
+
+        return u_lst, c_lst
+
+    def decode(self, y: np.array) -> np.array:
+        """Decode a received signal.
+
+        This function assumes a BPSK-like modulated signal ([-1, 1]^n instead of [0, 1]^n)
+        and an AWGN channel.
+
+        :param y: Vector of received values. (y = x + n, where 'x' is element of [-1, 1]^m
+            and 'n' is noise)
+        :return: Most probably sent symbol
+        """
+        # TODO: Is there a nice numpy way to implement this for loop?
+        correlations = []
+        for c in self._codewords_bpsk:
+            correlations.append(np.dot(y, c))
+
+        return self._datawords[numpy.argmax(correlations)]
diff --git a/sw/decoders/proximal.py b/sw/decoders/proximal.py
index d476ee6..b1f84ae 100644
--- a/sw/decoders/proximal.py
+++ b/sw/decoders/proximal.py
@@ -1,5 +1,4 @@
 import numpy as np
-from tqdm import tqdm
 
 
 class ProximalDecoder:
diff --git a/sw/decoders/utility.py b/sw/decoders/utility.py
index fe53519..81c1055 100644
--- a/sw/decoders/utility.py
+++ b/sw/decoders/utility.py
@@ -44,6 +44,7 @@ def count_bit_errors(d: np.array, d_hat: np.array) -> int:
 
 
 def test_decoder(decoder: typing.Any,
+                 d: np.array,
                  c: np.array,
                  SNRs: typing.Sequence[float] = np.linspace(1, 4, 7),
                  target_bit_errors=100,
@@ -54,6 +55,7 @@ def test_decoder(decoder: typing.Any,
     This function prints its progress to stdout.
 
     :param decoder: Instance of the decoder to be tested
+    :param d: Dataword (element of [0, 1]^n)
     :param c: Codeword whose transmission is to be simulated (element of [0, 1]^n)
     :param SNRs: List of SNRs for which the BER should be calculated
     :param target_bit_errors: Number of bit errors after which to stop the simulation
@@ -79,7 +81,7 @@ def test_decoder(decoder: typing.Any,
             y = add_awgn(x, SNR, signal_amp=np.sqrt(2))
             y_hat = decoder.decode(y)
 
-            total_bit_errors += count_bit_errors(c, y_hat)
+            total_bit_errors += count_bit_errors(d, y_hat)
             total_bits += c.size
 
             if total_bit_errors >= target_bit_errors:
diff --git a/sw/main.py b/sw/main.py
index 8744a76..a88e021 100644
--- a/sw/main.py
+++ b/sw/main.py
@@ -4,6 +4,7 @@ import seaborn as sns
 import pandas as pd
 
 from decoders import proximal
+from decoders import naive_soft_decision
 from decoders import utility
 
 
@@ -21,13 +22,14 @@ def main():
 
     # Test decoder
 
-    d = np.array([0, 1, 1, 1])
+    d = np.array([0, 0, 0, 0])
     c = np.dot(G.transpose(), d) % 2
 
     print(f"Simulating with c = {c}")
 
-    decoder = proximal.ProximalDecoder(H, K=100, gamma=0.01)
-    SNRs, BERs = utility.test_decoder(decoder, c, SNRs=np.linspace(1, 5.5, 7), target_bit_errors=200, N_max=15000)
+    # decoder = proximal.ProximalDecoder(H, K=100, gamma=0.01)
+    decoder = naive_soft_decision.SoftDecisionDecoder(G, H)
+    SNRs, BERs = utility.test_decoder(decoder, d, c, SNRs=np.linspace(1, 7, 9), target_bit_errors=500, N_max=10000)
 
     data = pd.DataFrame({"SNR": SNRs, "BER": BERs})