However, in the second phase, state-of-the-art algorithms/architectures were developed for many applications including self-driving cars, healthcare sector, text recognition, earthquake predictions, marketing, finance, and image recognition. During the first phase, several developments like backpropagation, chain rule, Neocognitron, hand written text recognition (LeNET architecture), and resolving the training problem were observed (as shown in Figure 1). This field of research is still evolving its evolution can be divided into two time periods-from 1943–2006 and from 2012–until now. The Deep Learning (DL) approach is a subcategory of Machine Learning (ML), introduced in 1943 when threshold logic was introduced to build a computer model closely resembling the biological pathways of humans.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |