Teaching Machines to Understand What They See (11:30 - 13:30)
Humans rely a lot on their visual perception to understand the world. Can machines do the same? In this talk we will briefly go over the basics of machine learning with biologically inspired neural networks. We will then discuss the details of convolutional neural networks and how to use them to understand images.
Part I - Background
• What is Learning and How Machines Learn?
• A Brief Introduction to Neural Networks
Part II - Understanding Images
• How Our Visual System Works
• Convolutional Neural Networks
Part III - Building a ConvNet From Scratch
• How to Build a CNN for Object Recognition with Python in Keras
Semih Yağcıoğlu is a PhD student in Computer Science at Hacettepe University Computer Vision Lab and a Software Engineer at STM. He is interested in Machine Learning and work at the intersection of language and vision.
Industrial Data Science Use Cases with Real Life Examples from Turkey
(13:30 - 14:30)
• IBM Data Science Experience and Watson ML Demos
Umut ŞATIR GÜRBÜZ has been working on Predictive Analytics area for 14 years as trainer, consultant and pre-sales. She joined IBM in 2010 and her current role is Data Scientist for Middle East and Africa. In the past, she implemented predictive analytics projects for various sectors including finance, telecommunication, insurance, private pension, retail, pharmacy, automotive, trainer in different areas including; predictive modeling, profile detection with classification methods, customer segmentation, marketing optimization, forecasting with time series models, association detection analysis, market basket analysis, data manipulation methods.