Introduction to Machine Learning(Personal Intuition)

Need For Machine Learning

Ever since the technical revolution, we’ve been generating an immeasurable amount of data. As per research, we generate around 2.5 quintillion bytes of data every single day! It is estimated that by 2021, 1.7MB of data will be created every second for every person on earth.

With the availability of so much data, it is finally possible to build predictive models that can study and analyze complex data to find useful insights and deliver more accurate results.

Top Tier companies such as Netflix and Amazon build such Machine Learning models by using tons of data in order to identify profitable opportunities and avoid unwanted risks.

Here’s a list of reasons why Machine Learning is so important:

• Increase in Data Generation: Due to excessive production of data, we need a method that can be used to structure, analyze and draw useful insights from data. This is where Machine Learning comes in. It uses data to solve problems and find solutions to the most complex tasks faced by organizations.
• Improve Decision Making: By making use of various algorithms, Machine Learning can be used to make better business decisions. For example, Machine Learning is used to forecast sales, predict downfalls in the stock market, identify risks and anomalies, etc.

Machine Learning is a system of automated data processing algorithms that help to make decision making more natural and enhance performance based on the results. The “learning” implies that the algorithm can glean new information and insights without being explicitly programmed. There are several models of machine learning:

• Supervised ML (the outputs are labeled, and the inputs are mapped to corresponding outputs)
• Unsupervised ML (the inputs are unlabeled, and the algorithms have to find patterns)
• Reinforcement ML (similar to supervised ML, but in this case, instead of a labeled output, there are rewards and the algorithm’s goal is to maximize rewards)

Artificial intelligence (AI) is a part of Computer Science that focuses on systems that can solve problems and perform tasks that require human (or human-like) intelligence. What does machine learning do in this process? It learns, just like a human(like) brain, acquiring new information.

Concept of learning in ML

We have a task T, performance measure P, experience E.

We say a system is learning when while performing task T, the performance measure P improving as it goes through more experiences E.

Case in point: Task = To make better route decisions

• Performance = Less travel time
• Experience = Traveling through different routes and time

If the system is learning it should start making decisions about selecting routes as it experiences more routes and time associated.

Depending on various features learning can go in either direction.

What are the Challenges?

• To create systems which perform with accuracy and precision of human intelligence and can leverage machine’s innate architecture to accelerate and keep up with big data (Scales of terabytes or petabytes of data)
• To allow for faster and better decision making through machines wherever possible
• To convert large amounts of raw data into useful analytics
• To help forecast the future trends and correct our estimates based on the analytic output

Terminology

• Population : The population is any specific collection of objects of interest.
• Sample : Sample is any subset of the population.
• Measurement : A measurement is a number or attribute computed for each member of a population or of a sample.
• Parameter: Parameter or feature is a numerical value that summarizes some aspects of the whole population.
• Inference: Any key knowledge about the data sample or population as a whole from its attributes and properties

Supervised Vs Unsupervised Learning

• The procedures in supervised learning are well comprehensible due to their structure. It is possible to contrast different methods, to parameterize and thereby find a solution that is optimal for the application .
• The interpretation of the data is easier due to the given traceability than with unsupervised learning methods.
• The disadvantage, however, is often a very high manual effort in the preparation of the data.
• It require lot of man hours to prepare fully formatted data to work with supervised learning.
• The advantages of unsupervised learning are the partially fully automated creation of models.
• These can produce a very good prognosis about new data or even create new content.
• The model learns with each new record and at the same time refines its calculations and classifications. Manual intervention is no longer necessary.
• The biggest disadvantages are there is no control over what model learns. It can start to cluster wrong type as one group
• It can give bad results amiss the output labels and can lead to lot of misclassifications.

The map of the machine learning world