• Monika Mann
• Parmeet Kaur

It presents the concept of image dataset evaluation using deep learning methods. These methods are used for evaluating large databases at a time. It uses the bacteria dataset for evaluation purpose. The scope of this work is defined by several machine learning tasks. The first one is analysed to see how much the unsupervised pre-training technique introduced with the Deep Belief Network (DBN) model improves the training of neural networks. The second is evaluating the efficiency of DBN. The idea behind this greedy layer-wise pre-training algorithm is that each model in the sequence of layers is learning from a different representation of the input. Each model performs a non-linear transformation and produces the input of the next layer. The performance is measured in terms of accuracy value. The proposed mechanism is implemented with MATLAB.

Image Processing, DNN, Boltzmann Machine etc.

"Image Dataset Evaluation by Boltzmann Machine under Deep Neural Networks", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.7, Issue 10, page no.2156-2162, October-2020, Available :http://www.jetir.org/papers/JETIR2010278.pdf

"Image Dataset Evaluation by Boltzmann Machine under Deep Neural Networks", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.7, Issue 10, page no. pp2156-2162, October-2020, Available at : http://www.jetir.org/papers/JETIR2010278.pdf