Publisher's Synopsis
Machine Learning
Often, machine learning is seen as the missing "human" element in machines; the ability for machines to start to fill the gap between what makes us human and what makes machines; a sense of responsiveness and flexibility in a given environment and a set of circumstances. By and large, the goal of learning is to be able to generalize: to take a set of lived circumstances, and to be able to extrapolate a sense of patterning about what the future holds, and how the person should respond to similar given situations. Machine learning is similar; it is the attempt to program machines so that they can generalize about future possibilities and probabilities based on data sets. In short- machine learning is the quest to get machines to think like humans. This takes a wide variety of forms and is used for a wide variety of purposes.
In the following book, we will explore the history of machine learning, the academic and scientific elements that make up the study, as well as touching on this moral and philosophical space that they occupy.
- What is Machine Learning?
- The History of Machine Learning
- Examples of Machine Learning
- How Does Machine Learning Work?
- Common Approaches and Terms in Machine Learning
- Theoretical Computer Science
- Computational Learning Theory/Association Rule Learning
- Pattern Recognition
- Deep Learning
- Induction Logic Reasoning
- Neural networks
- Expert Systems
- Naive Bayes Systems
- Unsupervised and supervised learning algorithms
- Decision Trees
- Random Decision Forests
- The Moral and Philosophical Implications of Machine Learning