Page 68 - Data Science Algorithms in a Week

52 Olmer Garcia and Cesar Diaz

and so, to ensure that messages related to the transfer of control are given in a
timely and appropriate manner.

The chapter is organized as follows. Section one provides a background about
machine learning and deep learning. Section two expands on the architecture of
autonomous vehicle to identify where and how machine learning algorithms could be
applied. The next section uses a particular case study of machine learning in autonomous
vehicles to illustrate the concepts. Finally, some conclusions and perspectives are
presented.

MACHINE LEARNING AND DEEP LEARNING

This section is an introduction to the main concepts of machine learning and deep
learning.

Machine Learning Concepts

Michalski et al. (1983) stated that a “Learning process includes the acquisition of
new declarative knowledge, the development of motor and cognitive skills through
instruction or practice, the organization of new knowledge into general and effective
representations, the discovery of new facts, and theories through observation and
experimentation.” Kohavi & Provost (1998) published a Glossary of terms for machine
learning and define it as: “The non-trivial process of identifying valid, novel, potentially
useful, and ultimately understandable patterns in data machine learning is most
commonly used to mean the application of induction algorithms, which is one step in the
knowledge discovery process.”
Machine learning is highlighted as the study and computer modeling of learning
processes. The main idea is developed around the following research paths:

 Task-Oriented Studies: Improved performance in a defined set of tasks as the
result of learning systems is the emphasis of this path.
 Cognitive Simulation: This path is related to research and computer simulations
of human learning processes.
 Theoretical Analysis: This path focuses on research of algorithms and learning
methods.