Thinking Machines Series

This book is an introduction to Robotics, it aims to introduce the reader to the world of robots, how they work and how science strives to transform them from simple electro-mechanical contraptions into intelligent thinking machines. The topics of interest this book covers are as follows: History of Robotics The current state of Robotics in 2017  Cyber Physical Systems The rise of the robot in industry Components of a Robot  Body types, Mechanisms and Sensors Mobility, Motion and Precision Control Automation Operating Systems and Software Kinematics & Trajectory Plans Autonomous and Collaborative Robots Intelligent Robots Bio-robots and Cyborgs Brain Computer Interface Prosthetics and Exoskeletons The Robot's future in society and work This book is an introduction to the engineering science of robotics and as such it sets out to teach the fundamentals of electromechanical robots, starting common actuators, motors, sensors and microcontrollers that we require in designing and constructing simple mechanical robots. In the opening chapters we will learn about the basic elements of mechanical robots, the components that comprise a typical robot and the diverse body shapes which robot designers can adopt to suit their robot's purpose. We learn about precision control of motors and actuators and the mechanisms such as robotic arms that enable robot's to do tasks. We will learn some of the important aspects of physics that we are required to know if we want to design mobile robots; such as Kinematics which is the physics behind controlling the robots movements with regards 2D or 3D coordinates and how to calculate forward and inverse kinematics. We will also learn some of the fundamentals as well as some tricks to cut out a lot of the heavy math traditionally required in kinematics, motion control, torque, velocity and trajectory planning for both mobile vehicles and robotic arms. Building upon what we learned we will consider automating mechanical robots, and be introduced to Microcontrollers, common architectures and their use in robotics. We will consider robotic OS & software, and review several options for hobbyists and industrial use cases. We will learn about how robotic OS work, the constraints and what software languages are best suited for robotic projects. We will also learn about Robotic frameworks for design and production of robots using open source software. Moving along and building on our knowledge we will introduce industrial robots that are designed to collaborate and work safely alongside humans. We will examine why they have come to fill a niche requirement in small medium enterprises. We will also learn how collaborative robots are repurposed and their pros and cons compared to traditional industrial robots. In the later chapters we will introduce the science behind intelligent robots those with an actual intelligent brain. We will also see how inspiration has come from nature and biology in the quest to produce genuinely intelligent autonomous machines. We will also learn that it has often gone beyond just inspiration by using biological brains to interface with robots. This leads us on to Cyborgs and the merging of biology with electronics and robotic technology. We will learn about the diverse research projects underway and some of the amazing discoveries and techniques such as Optogenetics, and Brain Computer Interfaces for mind control and other techniques that have been developed to create cyborg technology. Finally, we will learn about robotic skills in empathy, creativity and developing social skills – the very things that we believed set humans apart. We will also learn how robots are developing human like social intelligence skills which was thought impossible only a few years ago.

This book is an introduction to Machine learning for beginners yet it has sufficient depth to interest technical developers. It addresses the subject of Machine Learning algorithms and the training techniques used, which will enable an agent to learn through its own experience gained through interaction with its environment. The book is aimed at students without any prerequisite knowledge of math or statistics, instead it addresses the algorithms, functions and techniques as understandable processes that the layman can comprehend and action. The topics of interest are as follows: How does A.I. differ from Machine Learning Machine Learning in practice Understanding the Machine Learning process Introduction to ML algorithms Function families of algorithms Approaches to Machine Learning Techniques and methods in applied Machine Learning Working with error Planning the Machine Learning process Understanding Linear regression Understanding Decision Trees Understanding Bayesian Networks Understanding Association Rules Understanding Support Vector Machines Understanding Clustering Understanding Neural Networks Intro to Deep Neural Networks (DNN) Types of DNN Understanding Feature Engineering Machine Learning Platforms and Frameworks  Initially we will introduce machine learning and describe it relationship with Artificial Intelligence. As part of the discussion we will learn what Machine Learning is and how it differentiates from A.I. we will learn about some features of Machine Learning and study Machine Learning in practical terms by witnessing it in action. We will see the wide and diverse application of Machine Learning and understand its pervasiveness throughout most modern technologies. Then we will look under the hood at the technology to get an idea of how Machine Learning works rather than just a high-level of what it does. In particular we will be introduced to the three approaches to Machine Learning, supervised, unsupervised and reinforcement learning. We will learn about each method, how it works and why it is used for particular scenarios as well the families of algorithms that are the foundation of Machine Learning and by doing so we will learn some of the basic principles behind algorithms and some of the important inherent constraints. We will discuss the Bias-variance dilemma, the requirement for generalization, and our preference for simple over complex models. In addition we will introduce a commonly used term in Machine Learning, overfitting and we will learn the principle, how it occurs and why it is such an issue. We will also learn how we measure error accurately and suggest some trade-offs that improve performance. Then we come to addressing the harsh practical reality of preparing a Machine Learning model. We will learn how to handle data, through acquisition, cleansing and preparation. We will also learn how to choose an approach, a method and an algorithm that suits our needs. In the course of the book we will study Linear regression, Decision Trees, Bayesian Networks, Association Rules, Support Vector Machines, Clustering and Artificial Neural Networks. We will also learn about Feature Engineering the important task of selecting the appropriate features for the method being deployed. We will learn how to identify appropriate features and the techniques for feature extraction. Finally in the closing Chapter we will learn about the Machine Learning platforms and software languages that have good ML frameworks. We will also learn about other Machine learning resources, tools and techniques that enable even SME’s to actively participate in Machine Learning activities and research.

 This book is an introduction to the fundamentals of Artificial Intelligence its aim is to introduce A.I. through its history, its contemporary role in society and the economy. We then lift the hood to see how A.I. works and how we can create our very own rational A.I. agents The topics of interest are as follows: A.I. today in 2017 A.I role in society A.I. role in employment A.I. role in the economy Algorithms and types of A.I Modern Approaches to A.I What A.I. can do What A.I. can't do – for now Types of A.I. agents Understanding Environments Solving Problems with A.I Planning with A.I Building Rational and Logical Agents Applying A.I. through Bayesian and Decision Networks In early chapters of this book we will learn how AI has reemerged over the last couple of decades due to a rise in complimentary enabler technologies and some surprising successes that have brought A.I. to the mainstream media’s attention. Then we lift the hood to start our investigations into how AI systems work. We will learn that AI is powered by algorithms, which do the underlying heavy lifting but we will also get an understanding regards how the algorithms achieve their goals and we will glimpse the principles on which they are designed to function. For example, we will learn the importance as to whether an algorithm acts humanly or rationally Also we will introduce the concept and learn about AI agents what they are and how they relate to artificial intelligence as a technology. We will consider how we make agents intelligent and by what means. We will then consider and learn about the various types of AI agents and have a look at their individual architecture and learn more about each of their functions and purpose. Hence we will learn how to build reflex-based, model-based, goal-based, and utility-based agents by learning how they work. Finally we will introduce learning agents and a radical view of an alternative architecture based upon natures evolutional model. We will address how to use AI algorithms to solve problems. Hence we will learn how to construct our problem, by ensuring it is well-defined. We will also learn how a search tree works and its infrastructure and how to decompose a search algorithm to its four functional components. We will also learn how to understand the algorithm search performance and results by completeness, optimality, and space and time complexity. Then we will learn about knowledge-based agents, what they are, how they are built and how we imbue them with knowledge. Furthermore we will introduce and learn about Logical agents where we use representations based on logic statements to allow the agent to perform acts of reason. In addition we look at AI's role in Planning and why we require AI as a planning agent. We will see how a planning agent's infrastructure differs from problem solving agents in state, goals and actions. Furthermore we will learn the theory behind Bayesian networks and Conditional Probability Tables and how to build them and calculate probability. We will also learn how to use inference algorithms in Bayesian network. Finally we look at the principles behind rational agents and the 6 constraints known as the Axioms of Utility Theory that any preference model must consider when behaving rationally. Using the knowledge accrued over the previous chapters we will construct a decision network and learn how to use it to derive probabilities of events and calculate maximum expected utility (MEU).