Υλοποίηση πολυεπίπεδων perceptrons για διάγνωση καρκίνου του μαστού
View/
Keywords
Μηχανική μάθηση ; Βαθιά μάθηση ; Πολυεπίπεδα perceptrons ; Καρκίνος μαστού ; WDBC ; Ταξινόμηση ; Επαναλήψεις ; Οπισθόδρομη / πρόσθια τροφοδότηση ; KerasAbstract
Artificial Neural Networks, which are the core of Deep Learning, find
application in solving complex problems in a wide range of applications, such as
the medical diagnosis of cancer diseases. Breast cancer is the first
cause of cancer in women. To improve the long-term survival rate for
patients, the key factors are early detection and accurate diagnosis
for the existence of malignancy. Creating reliable diagnostic systems with
Computer help and Deep Learning is important medical help
so that the diagnosis is faster and easier, and even without
Theoretical and artificial background is required for Artificial Neural Networks.
The purpose of this dissertation is the implementation of Multilevel
Perceptrons using the Python programming language and the library
Keras for the diagnosis of breast cancer, based on the Wisconsin dataset
(Wisconsin Breast Cancer Diagnostic -WBCD) available in the Engineering repository
UCI Learning.