Introduction

Machine learning is programming computers to optimize
a performance criterion using example data or past experience.

We need learning in cases where we cannot directly write a computer program to solve a given problem, but need example data or experience. One case where learning is necessary is when human expertise does not exist, or when humans are unable to explain their expertise.

Consider the recognition of spoken speech-that is, converting the acoustic speech signal to an ASCII text. We can do this talk seemingly without any difficulty, we are unable to explain how we do it. Different people utter the same word differently due to differences in age, gender or accent. In machine learning, the approach is to collect a large collection of sample utterances from different people and learn to map these to words.

Another case is when the problem to be solved changes in time, or depends on the particular environment. We would like to have general purpose systems that can adapt to their circumstances, rather than explicitly writing a different program for each special circumstance.

Consider routing packets over a computer network. The path maximizing the quality of service from a source to destination changes continuously as the network traffic changes. A learning routing program is able to adapt to the best path by monitoring the network traffic.
Another example is an intelligent user interface that can adapt to the biometrics of its user—namely, his or her accent, handwriting, working habits, and so forth.

Applications

Already, there are many successful applications of machine learning in various domains:

• There are commercially available systems for recognizing speech and handwriting
• Retail companies analyze their past sales data to learn their customers’ behavior to improve customer relationship management
• Financial institutions analyze past transactions to predict customer’s credit risks
• Robots learn to optimize their behavior to complete a task using minimum resources
• In bioinformatics, the huge amount of data can only be analyzed and knowledge extracted using computers.

These are only some of the applications that I will discuss throughout this blog.

We can only imagine what future applications can be realized using machine learning:

• Cars that can drive themselves under different road and weather conditions
• Phones that can translate in real time to and from a foreign language
• Autonomous robots that can navigate in a new environment, for example, on the surface of another planet

Current digital image processing possibilities

History

In the past, research in these different communities followed different paths with different emphases.
Machine learning has seen important developments since it first appeared as a theory.

• First, application areas have grown rapidly. Internet related technologies, bioinformatics and computational biology, natural language processing applications, robotics, medical diagnosis, speech and image recognition, biometrics, finance, sometimes under the name pattern recognition, sometimes disguised as data mining
• There have been supporting advances in theory. Especially, the idea of kernel functions and the kernel machines that use them allow a better representation of the problem and the associated convex optimization framework is one step further than multilayer perceptrons with sigmoid hidden units trained using gradient-descent
• Another revelation hugely significant for the field has been in the realization that machine learning experiments need to be designed better. We have gone a long way from using a single test set to methods for cross validation to paired t tests.

Types of problems and tasks

Machine learning tasks are typically classified into three broad categories, depending on the nature of the learning "signal" or "feedback" available to a learning system. These are:

• Supervised learning: The computer is presented with example inputs and their desired outputs, given by a "teacher", and the goal is to learn a general rule that maps inputs to outputs.
• Unsupervised learning: No labels are given to the learning algorithm, leaving it on its own to find structure in its input. Unsupervised learning can be a goal in itself (discovering hidden patterns in data) or a means towards an end (feature learning).
• Reinforcement learning: A computer program interacts with a dynamic environment in which it must perform a certain goal (such as driving a vehicle), without a teacher explicitly telling it whether it has come close to its goal. Another example is learning to play a game by playing against an opponent.

Between supervised and unsupervised learning is semi-supervised learning, where the teacher gives an incomplete training signal: a training set with some (often many) of the target outputs missing.
Transduction is a special case of this principle where the entire set of problem instances is known at learning time, except that part of the targets are missing.

Categorization considering the desired output of a machine-learned system

• In classification, inputs are divided into two or more classes, and the learner must produce a model that assigns unseen inputs to one or more (multi-label classification) of these classes. This is typically tackled in a supervised way. Spam filtering is an example of classification, where the inputs are email (or other) messages and the classes are "spam" and "not spam".
• In regression, also a supervised problem, the outputs are continuous rather than discrete.
• In clustering, a set of inputs is to be divided into groups. Unlike in classification, the groups are not known beforehand, making this typically an unsupervised task.
• Density estimation finds the distribution of inputs in some space.
• Dimensionality reduction simplifies inputs by mapping them into a lower-dimensional space. Topic modeling is a related problem, where a program is given a list of human language documents and is tasked to find out which documents cover similar topics.

Different way of solving problems

It has long been believed, especially by older members of the scientific community, that for machines to be as intelligent as us, that is, for artificial intelligence to be a reality, our current knowledge in general, or computer science in particular, is not sufficient.

People largely are of the opinion that we need a new technology, a new type of material, a new type of computational mechanism or a new programming methodology, and that, until then, we can only “simulate” some aspects of human intelligence and only in a limited way but can never fully attain it.

I believe that we will soon prove them wrong.

First we saw this in chess and go, and now we are seeing it in a whole variety of domains.

Given enough memory and computation power, we can realize tasks with relatively simple algorithms.
The trick here is learning, either learning from example data or learning from trial and error using reinforcement learning.

I believe that this will continue for many domains in artificial intelligence, and the key is learning.
We do not need to come up with new algorithms if machines can learn themselves, assuming that we can provide them with enough data (not necessarily supervised) and computing power.

Summary

This is an introductory post, intended for steemers curious about machine learning,
as well as others working in the industry who are interested in the application of these methods.

Machine learning is certainly an exciting field to study about!

Later posts will contain concepts from areas of computer programming, probability, calculus, and linear algebra. For some cases, I will provide pseudocode of algorithms to make more vivid pictures of what we are talking about.

I enjoyed writing this post.

I hope you will enjoy reading it so I continue reporting about machine learning and its applications in modern industry. I am also grateful to those who provide me any kind of feedback.