SAVE THE DATE Tapia 2018 Orlando, FL September 19-22, 2018

2017 Tapia Conference

Using Deep Learning and Machine Learning Techniques to Teach Computer to Paint Masterpiece Art

Contributors

Presenter: Gaston Seneza (Philander Smith College)

Abstract

How do we learn? Time changes, concepts stay unchanging. Information outlasts the body. It’s stored in our brains, and passed down from generation to generation. Our brain can synthesize the diverse set of inputs from our five senses, thereby creating a hierarchy of concepts. If we are lucky we can learn a task under direct supervision. While interacting with our environment we can feel our surroundings, see our obstacles and try to predict our next steps. Through the process of trial and error, we can learn anything. What is it that gives our brain this special capability unlike anything else in nature? Everything we’ve ever experienced, felt, all our thoughts, memories, our very sense of self, is produced by the brain. At the molecular level, our brain consists of an estimated 100 billion neurons. Each neuron has three jobs: Receive a set of signals from dendrites. Integrate those signals together to determine whether or not the information should be passed on in the cell body. Pass the information onwards if it passes a certain threshold. This is the intelligence that for long scientists have tried to solve.

Today, with deep learning, advanced machine learning techniques and artificial intelligence, we teach/train machines to do almost anything only humans were capable of doing before. In this project, we explore the use of deep learning and neural networks to train computers to paint similar masterpiece art produced by famous artists. The relationship between human and computer generated masterpieces are to be studied.