Özet:

Deep learning (DL) is a powerful machine learning field that has achieved considerable success in many research areas. Especially in the last decade, the-state-of-the-art studies on many research areas such as computer vision, object recognition, speech recognition, natural language processing were led to the awakening of the artificial intelligence from deep sleep. Nowadays, many researchers are trying to find solutions to many problems in various fields under the light of DL methods. In this study, we present important knowledge to guide about DL models and challenging topics which can be used in DL for researchers. We investigated DL studies which are made in the most popular and challenging fields such as Autonomous Vehicles, Natural Language Processing, Handwritten Character Recognition, Signature Verification, Voice and Video Recognition, Medical İmage Processing, Big Data. Furthermore, we point out the remaining challenges of these research areas these can be solved by DL and discuss the future topics in order to help the researchers. The contribution of this study is that to list the most challenging subjects that can be studied with DL. We believe that researchers will contribute to these issues by achieving successful results through DL algorithms. The goal of this work is to help them make informed decisions about the best DL model that fits the needs and resources of researchers seeking to work with DL.

Anahtar Kelimeler: