We have built a Perceptron model on the IRIS dataset using Heaviside Step Activation Function using Single Layer Neural Network. The main problem concerns the identification of IRIS Flower species on the basis of Flower attribute measurements. As the Artificial Neural Networks (ANN) have been successfully applied, the Perceptron learned a decision boundary that was able to classify the flower samples in the Iris training subset perfectly. From the results, graphs and discussion, it is concluded that Single Layer Neural Network is faster in terms of learning speed and gave a good accuracy, i.e., has the best trade-off between speed and accuracy.
We have built a convolutional neural network (CNN) that will be trained on multi-class large dataset and later be able to predict the class of the given image. According to our problem in image feature regarding background materials, we have successfully worked done and precisely illustrated our task, including the learning task and the performance task.
