Международный журнал роевого интеллекта и эволюционных вычислений

Абстрактный

Significance of Deep learning in Data mining and Machine learning

Shorabi P

Deep learning algorithms use an enormous amount of unsupervised data to automatically extract complex representation. These algorithms are largely motivated by the sector of Artificial Intelligence (AI), which has the overall goal of emulating the human brain’s ability to watch, analyze, learn, and make decisions, especially for extremely complex problems. Work concerning these complex challenges has been a key motivation behind Deep Learning algorithms which strive to emulate the hierarchical learning approach of the human brain. Models supported shallow learning architectures like decision trees, support vector machines, and case-based reasoning may come short when attempting to extract useful information from complex structures and relationships in the input corpus. In contrast, Deep Learning architectures have the potential to generalize in non-local and global ways, generating learning patterns and relationships beyond immediate neighbors within the data. Deep learning is actually a crucial step toward AI. It not only provides complex representations of data which are suitable for AI tasks but also makes the machines independent of human knowledge which is the ultimate goal of AI. It extracts representations directly from unsupervised data without human interference.