Original article can be found here (source): Artificial Intelligence on Medium
Informal to Formal Knowledge
Inventors have long dreamed of creating machines that think. When programmable computers were first conceived, people wondered whether such machines might become intelligent, over a hundred years before one was built. Today, Artificial Intelligence (AI) is a thriving field with many practical applications and active research topics.
In the early days of artificial intelligence, the field rapidly tackled and solved problems that are intellectually difficult for human beings but relatively straight forward for computers, problems that can be described by a list of formal, mathematical rules. The true challenge to artificial intelligence proved to be solving the tasks that are easy for people to perform but hard for people to describe formally, problems that we solve intuitively, that feel automatic, like recognizing spoken words or faces in images.
A person’s everyday life requires an immense amount of knowledge about the world. Much of this knowledge is subjective and intuitive, and therefore difficult to articulate in a formal way. Computers need to capture this same knowledge in order to behave in an intelligent way. One of the key challenges in artificial intelligence is how to get this informal knowledge into a computer. Several artificial intelligence projects have sought to hardcore knowledge about the world in formal languages. A computer can reason about statements in these formal languages automatically using logical inference rules. This is known as knowledge base approach to artificial intelligence.
The difficulties faced by systems relying on hard-coded knowledge suggest that AI systems need the ability to acquire their own knowledge suggest that AI systems need the ability to acquire their own knowledge, by extracting patterns from raw data. This capability is known as Machine Learning. The introduction of machine learning allowed computers to tackle problems involving knowledge of the real world and make decisions that are subjective. A simple machine learning algorithm called naïve bayes can separate legitimate e-mail from spam e-mail. The performance of these simple machine learning algorithms depends heavily on the representation of the data they are given.
The Data representation is very important in machine learning to create solutions for a complex problem from the knowledge. This representation is extracting the features from the raw data; these features are properties of the data. An AI system doesn’t directly deal the patients, but it can solve the problems by observing the features / symptoms of patient. This representation is a complex process in Machine Learning.
Deep Learning solves this central problem in representation learning by introducing representations that are expressed in terms of other, simpler representations. Deep learning allows the computer to build complex concepts out of simpler concepts. Deep Learning systems allow computers to learn from experience and understand the experience and understand the world in terms of hierarchy of concepts, with each concept defined in terms of its relation to simpler concepts. By gathering knowledge from experience, this approach avoids the need from human operators to formally specify all of the knowledge or representation that the computer needs. The hierarchy of concepts allows the computer to learn complicated concepts by building them out of simpler ones. If we draw a graph showing how these concepts are built on top of each other, the graph is deep, with many layers, for this reason, this approach is called as Deep Learning.