Introduction To Deep Computer Vision

The field of artificial intelligence has been evolving at an unprecedented rate in the past few years. So many important contributions have been due to the incredible work of a number of post-graduate students from the University of Montreal, University of Toronto, Stanford University, UC Berkeley, MIT and a number of research focused institutions. However, in recent years, a lot of undergraduate students and professionals from other fields of engineering and computer science have been contributing incredibly to the advancement of artificial intelligence. We believe, AI will advance more rapidly if more people are able to quickly get up to speed with recent advances. This can only happen when there are sufficient entry level books designed to address the needs of aspiring AI scientists who may not have a very solid background in the fields of applied mathematics and statistics. The motivation for this treatise is our own experience while transitioning from Application developers to deep learning professionals. We both were very excited to get into the field of Artificial Intelligence but we faced a number of problems, first, many of the books available treated only old-time machine learning algorithms, which were not applicable to the modern tasks facing machine learning practitioners. The other books that addressed modern deep learning approaches, included practical that used low-level deep learning libraries. In this book, we present modern techniques in computer vision and we used a very high level python library for all practical. We hope the reader will find this an easier path towards becoming AI researchers and engineers.


© John Olafenwa 2018