Object Classification with Deep Learning on Theano
Machine Learning is a trend topic that aims to solve problems about future by learning the past. Everyday we generate data about our actions and mostof it is stored in some storages. Evidently, tendency of human actions are the similar for ages. People try to act according to what they have learned until now. We can expand the term by examining the usage on computers. With Machine Learning, we are able to use past data to find out a meaning. Implications have a good chance to give us an insight about the problemsthat we are going to encounter in future. Lots of algorithms were implemented to process the past data to train computers.Considering all actions about the past is not easy for a human but speed of computers can handle this issue. In Object Classification, we do not have a data called "past". It is not an issue about the future. Here we have sample images to train computer. Computer will process the given data and from now on we can expect the computer to predict the label or class of given unlabeled image. We call this problem as "Object Classification." Deep Learning is a widely used area of Machine Learning research, which has been introduced with Artificial Intelligence. Computers were tried to be taught as human brains so Neural Networks are built. They have lots of connected neurons and mostly used ones are Convolutional Neural Networks
and Artificial Neural Networks.
Project Poster:
Project Members:
Doruk Demirci
Project Advisor:
Ali Taylan Cemgil
Project Status:
Project Year:
2017
- Spring