# Implementation of Artificial Neural Network for NAND Logic Gate with 2-bit Binary Input

Artificial Neural Network (ANN) is a computational model based on the biological neural networks of animal brains. ANN is modeled with three types of layers: an input layer, hidden layers (one or more), and an output layer. Each layer comprises nodes (like biological neurons) are called Artificial Neurons. All nodes are connected with weighted edges (like synapses in biological brains) between two layers. Initially, with the forward propagation function, the output is predicted. Then through backpropagation, the weight and bias to the nodes are updated to minimizing the error in prediction to attain the convergence of cost function in determining the final output.
NAND logical function truth table for 2-bit binary variables, i.e, the input vector and the corresponding output –

Approach:
Step1: Import the required Python libraries
Step2: Define Activation Function : Sigmoid Function
Step3: Initialize neural network parameters (weights, bias)
and define model hyperparameters (number of iterations, learning rate)
Step4: Forward Propagation
Step5: Backward Propagation
Step6: Update weight and bias parameters
Step7: Train the learning model
Step8: Plot Loss value vs Epoch
Step9: Test the model performance

Python Implementation:

## Python3

 `# import Python Libraries` `import` `numpy as np` `from` `matplotlib ``import` `pyplot as plt`   `# Sigmoid Function` `def` `sigmoid(z):` `    ``return` `1` `/` `(``1` `+` `np.exp(``-``z))`   `# Initialization of the neural network parameters` `# Initialized all the weights in the range of between 0 and 1` `# Bias values are initialized to 0` `def` `initializeParameters(inputFeatures, neuronsInHiddenLayers, outputFeatures):` `    ``W1 ``=` `np.random.randn(neuronsInHiddenLayers, inputFeatures)` `    ``W2 ``=` `np.random.randn(outputFeatures, neuronsInHiddenLayers)` `    ``b1 ``=` `np.zeros((neuronsInHiddenLayers, ``1``))` `    ``b2 ``=` `np.zeros((outputFeatures, ``1``))` `    `  `    ``parameters ``=` `{"W1" : W1, "b1": b1,` `                  ``"W2" : W2, "b2": b2}` `    ``return` `parameters`   `# Forward Propagation` `def` `forwardPropagation(X, Y, parameters):` `    ``m ``=` `X.shape[``1``]` `    ``W1 ``=` `parameters["W1"]` `    ``W2 ``=` `parameters["W2"]` `    ``b1 ``=` `parameters["b1"]` `    ``b2 ``=` `parameters["b2"]`   `    ``Z1 ``=` `np.dot(W1, X) ``+` `b1` `    ``A1 ``=` `sigmoid(Z1)` `    ``Z2 ``=` `np.dot(W2, A1) ``+` `b2` `    ``A2 ``=` `sigmoid(Z2)`   `    ``cache ``=` `(Z1, A1, W1, b1, Z2, A2, W2, b2)` `    ``logprobs ``=` `np.multiply(np.log(A2), Y) ``+` `np.multiply(np.log(``1` `-` `A2), (``1` `-` `Y))` `    ``cost ``=` `-``np.``sum``(logprobs) ``/` `m` `    ``return` `cost, cache, A2`   `# Backward Propagation` `def` `backwardPropagation(X, Y, cache):` `    ``m ``=` `X.shape[``1``]` `    ``(Z1, A1, W1, b1, Z2, A2, W2, b2) ``=` `cache` `    `  `    ``dZ2 ``=` `A2 ``-` `Y` `    ``dW2 ``=` `np.dot(dZ2, A1.T) ``/` `m` `    ``db2 ``=` `np.``sum``(dZ2, axis ``=` `1``, keepdims ``=` `True``)` `    `  `    ``dA1 ``=` `np.dot(W2.T, dZ2)` `    ``dZ1 ``=` `np.multiply(dA1, A1 ``*` `(``1``-` `A1))` `    ``dW1 ``=` `np.dot(dZ1, X.T) ``/` `m` `    ``db1 ``=` `np.``sum``(dZ1, axis ``=` `1``, keepdims ``=` `True``) ``/` `m` `    `  `    ``gradients ``=` `{"dZ2": dZ2, "dW2": dW2, "db2": db2,` `                 ``"dZ1": dZ1, "dW1": dW1, "db1": db1}` `    ``return` `gradients`   `# Updating the weights based on the negative gradients` `def` `updateParameters(parameters, gradients, learningRate):` `    ``parameters["W1"] ``=` `parameters["W1"] ``-` `learningRate ``*` `gradients["dW1"]` `    ``parameters["W2"] ``=` `parameters["W2"] ``-` `learningRate ``*` `gradients["dW2"]` `    ``parameters["b1"] ``=` `parameters["b1"] ``-` `learningRate ``*` `gradients["db1"]` `    ``parameters["b2"] ``=` `parameters["b2"] ``-` `learningRate ``*` `gradients["db2"]` `    ``return` `parameters`   `# Model to learn the NAND truth table ` `X ``=` `np.array([[``0``, ``0``, ``1``, ``1``], [``0``, ``1``, ``0``, ``1``]]) ``# NAND input` `Y ``=` `np.array([[``1``, ``1``, ``1``, ``0``]]) ``# NAND output`   `# Define model parameters` `neuronsInHiddenLayers ``=` `2` `# number of hidden layer neurons (2)` `inputFeatures ``=` `X.shape[``0``] ``# number of input features (2)` `outputFeatures ``=` `Y.shape[``0``] ``# number of output features (1)` `parameters ``=` `initializeParameters(inputFeatures, neuronsInHiddenLayers, outputFeatures)` `epoch ``=` `100000` `learningRate ``=` `0.01` `losses ``=` `np.zeros((epoch, ``1``))`   `for` `i ``in` `range``(epoch):` `    ``losses[i, ``0``], cache, A2 ``=` `forwardPropagation(X, Y, parameters)` `    ``gradients ``=` `backwardPropagation(X, Y, cache)` `    ``parameters ``=` `updateParameters(parameters, gradients, learningRate)`   `# Evaluating the performance` `plt.figure()` `plt.plot(losses)` `plt.xlabel("EPOCHS")` `plt.ylabel("Loss value")` `plt.show()`   `# Testing` `X ``=` `np.array([[``1``, ``1``, ``0``, ``0``], [``0``, ``1``, ``0``, ``1``]]) ``# NAND input` `cost, _, A2 ``=` `forwardPropagation(X, Y, parameters)` `prediction ``=` `(A2 > ``0.5``) ``*` `1.0` `# print(A2)` `print``(prediction)`

Output:

` `

`[[ 1.  0.  1.  1.]]`

Here, the model predicted output for each of the test inputs are exactly matched with the NAND logic gate conventional output () according to the truth table and the cost function is also continuously converging.
Hence, it signifies that the Artificial Neural Network for the NAND logic gate is correctly implemented.

Whether you're preparing for your first job interview or aiming to upskill in this ever-evolving tech landscape, GeeksforGeeks Courses are your key to success. We provide top-quality content at affordable prices, all geared towards accelerating your growth in a time-bound manner. Join the millions we've already empowered, and we're here to do the same for you. Don't miss out - check it out now!

Previous
Next