Bayesian networks : Bayesian learning in neural networks and autoencoders
In traditional neural networks, we have fixed weights and biases that determine how input is transformed into an output. In a Bayesian Neural Network (BNN), all weights and biases have a probability distribution attached to them. To classify an image, we do multiple runs (forward passes) of the network, each time with a new set of sampled weights and biases. Instead of a single set of output values, we get multiple sets, one for each of the several runs. The set of output values represents a probability distribution on it. In recent literature, a new algorithm was introduced for learning a probability distribution on the weights and biases of a neural network, called Bayes by Backprop. In this work, the accuracies of conventional neural networks (NN) and BNN on MNIST classification are studied. Evaluation of implementation shows that BNN gives better results than using conventional NN. Additionally, in this work, Bayes by Backprop is modified for Autoencoders and implemented Bayesian AutoEncoder (BAE) by changing configuration and loss function of the existing algorithm.
- M Tech Dissertations 
Showing items related by title, author, creator and subject.
Nallagorla, V. S. R. Krishna (Dhirubhai Ambani Institute of Information and Communication Technology, 2004)Automatic text categorization is a problem of assigning text documents to pre¬-defined categories. This requires extraction of useful features. In most of the applications, text document features are commonly represented ...
Patel, Jayendra (Dhirubhai Ambani Institute of Information and Communication Technology, 2014)In this thesis, we have particularly focussed on the aspects of the hardware implementation of the Bayesian inference framework within the George and Hawkins’ model. This framework is based on Judea Pearl’s belief propagation. ...
Sharma, Abhishek (Dhirubhai Ambani Institute of Information and Communication Technology, 2008)This thesis report basically deals with the scheduling algorithms implemented in our computer systems and about the creation of probabilistic network which predicts the behavior of system. The aim of this thesis is to ...