Repository logo
  • English
  • ქართული
  • Log In
    New user? Click here to register.Have you forgotten your password?
Repository logo
  • English
  • ქართული
  • Log In
    New user? Click here to register.Have you forgotten your password?
  1. Home
  2. Universities
  3. Ivane Javakhishvili Tbilisi State University
  4. Faculties
  5. Faculty of Exact and Natural Sciences
  6. Dissertations and Master Theses
  7. ღრმა სწავლება
 
  • Details
Options

ღრმა სწავლება

Date Issued
2019
Author(s)
გოგისვანიძე, სალომე  
Advisor(s)
ბესიაშვილი, გელა  
Institution
Ivane Javakhishvili Tbilisi State University  
Faculty
Faculty of Exact and Natural Sciences  
Publisher
Ivane Javakhishvili Tbilisi State University  
URI
https://openscience.ge/handle/1/1591
Abstract
Deep learning is a machine learning technique that teaches computers to do what comes naturally to humans: learn by example. Deep learning is a key technology behind driverless cars, enabling them to recognize a stop sign, or to distinguish a pedestrian from a lamppost. It is the key to voice control in consumer devices like phones, tablets, TVs, and hands-free speakers. Deep learning is getting lots of attention lately and for good reason. It’s achieving results that were not possible before.
In deep learning, a computer model learns to perform classification tasks directly from images, text, or sound. Deep learning models can achieve state-of-the-art accuracy, sometimes exceeding humanlevel performance.
Models are trained by using a large set of labeled data and neural network architectures that contain many layers.
Subjects

ღრმა სწავლება

განსხვავებები მანქანუ...

გრადიენტური დაშვება

კონვოლუციური შრე

უკუპროპაგაციული მოდელ...

Degree Name
Master of Information Technology
Degree Discipline
ინფორმაციული ტექნოლოგიები. Information Technology
Degree Grantor
ივანე ჯავახიშვილის სახელობის თბილისის სახელმწიფო უნივერსიტეტი  
File(s)
Loading...
Thumbnail Image
Name

MA Thesis Gogisvanidze Salome.pdf

Description
ღრმა სწავლება
Size

745.02 KB

Format

Adobe PDF

Checksum

(MD5):a55b143e1e93dc11512da52acc323dc8

Communities & Collections Research Outputs Fundings & Projects People
  • Cookie settings
  • Privacy policy
  • Contact