Task 1 : Our main task is to implement Multilayer Perceptron Neural Network and evaluate its performance in classifying handwritten digits. Task 2 : Compare performance of above network VS Deep Neural Network and Convolution Neural Network on celebrity face dataset using Tensoreflow library.
Aim:
- How Neural Networks works and use Feed Forward, Back Propogation to implement Neural Network. Role of regularization in bias-variance trade off.
- How to use TensorFlow library to deploy deep neural networks and understand how having multiple hidden layers can improve the performance of the neural network. 3.How to use TensorFlow library to deploy convolutional neural networks and understand the benefit of convoltuional neural network compared to fully connected neural network.