“There and back again”
One code to rule them all.
Chapter 2 — Artificial Intelligence, Machine Learning and Deep Learning
Artificial Intelligence: sometimes called “machine intelligence”, is “intelligence” demonstrated by machines, in contrast to the natural intelligence displayed by humans. The term “artificial intelligence” is often used to describe computers that mimic “cognitive” human functions, such as “learning” and “problem solving”.
So, whenever a machine completes tasks based on a set of stipulated rules that solve problems, such an “intelligent” behavior is what is called artificial intelligence.
AI can be categorized as either weak or strong:
Weak AI, aka narrow AI, is an AI system that is designed and trained for a particular task. AI machines can perform specific tasks very well, sometimes better than humans — though they are limited in scope. Virtual personal assistants, such as Alexa or Cortana, are a form of weak AI.
Strong AI, aka artificial general intelligence, is an AI system with generalized human cognitive abilities. When presented with an unfamiliar task, a strong AI system is able to find a solution without human intervention.
The main goals of AI research include reasoning, knowledge representation, planning, learning, natural language processing (NLP), perception and the ability to move and manipulate objects.
Machine Learning: is the scientific study of algorithms that computer systems use to perform a specific task without using explicit instructions or without being programmed for this task, relying on patterns and inference instead. It is seen as a subset of Artificial Intelligence.
The intention of ML is to enable machines to learn by themselves using the provided data (train data) and make accurate predictions.
The name machine learning was coined in 1959 by Arthur Samuel.
Tom M. Mitchell provided a widely quoted, more formal definition of the algorithms studied in the machine learning field:
“A computer program is said to learn from experience E with respect to some class of tasks T and performance measure P if its performance at tasks in T, as measured by P, improves with experience E.”
Deep Learning: is part of Machine Learning methods based on artificial neural networks (ANN).
Learning can be supervised, semi-supervised, unsupervised or by reinforcement.
- Supervised Learning: is the machine learning task of learning a function that maps an input to an output based on example input-output pairs. The machine learns explicitly using the labeled train data.
- Semi-supervised Learning: is a class of machine learning tasks and techniques that also make use of unlabeled data for training — typically a small amount of labeled datawith a large amount of unlabeled data.
- Unsupervised Learning: the machine understands the data, identifying patterns and structures. The training data is unlabeled. The evaluation is qualitative or indirect.
- Reinforcement Learning: Systems are trained by receiving virtual “rewards” or “punishments”, essentially learning by trial and error.
Deep Learning architectures such as deep neural networks, deep belief networks, recurrent neural networks (RNN) and convolutional neural networks (CNN) have been applied to fields including computer vision, speech recognition, natural language processing (NLP), audio recognition, social network filtering, medical image analysis, where they have produced results comparable to and in some cases superior to human experts.
