Understanding the use of Deep Learning for Generating Captions to Describe Images
Author(s):
Advait Pravin Savant , Sardar Patel Institute of Technology
Keywords:
Machine Learning, AI technology, Convolutional Neural Networks
Abstract:
Machine Learning is that field of Computer Science wherein we create statistical and computational models of systems and tune those models using the data at hand which acts as an experience based on which the system improves its performance at a given task with respect to some performance measure. A large amount of data that is available via computer networks, distributed systems and increase in the computing power of devices have led to a boom in the applications of machine learning today. Deep learning is that subfield of machine learning wherein our focus is on creating representations for the system through artificial neural networks. Deep learning and the use of convolutional neural networks have given us a significant performance gain in Computer Vision tasks and has been successfully used for object tracking, detection etc. Deep learning has also been used for Natural Language Processing problems like machine translation, named entity recognition, parts of speech tagging and has proven to be very useful there. Deep learning applications in Computer Vision and NLP are active areas of research. Another important avenue is the performance of tasks, which require both visual perception and linguistic abilities such as automated caption generation for a given image, which is the focus of this paper. I attempt to demonstrate and explain how deep learning can help us in this task, which is an exemplar of AI technology today.
Other Details:
Manuscript Id | : | IJSTEV6I10001
|
Published in | : | Volume : 6, Issue : 10
|
Publication Date | : | 01/05/2020
|
Page(s) | : | 1-5
|
Download Article