Stick to the (An)timetab(o)le! Machine Learning to Learning Machine

To understand Machine Learning (ML), we need to first understand its superset i.e. Artificial Intelligence (AI).

1. Artificial Intelligence (AI) as the names suggest are techniques that seek to enable systems to emulate human behaviour and is the superset of or the umbrella under whihc ML falls under.
2. Machine Learning (ML) is a subset or type of AI techniques that uses statistical methods to learn and improve from experience without being explicitly programmed.
3. Deep Learning (DL) is a subset of ML that uses complex algorithms and deep neural nets to train a model or in simpler words it mimics the functioning of the human brain's own network of neurons.

At its most basic level, ML uses?programmed algorithms that receive and analyse input data to predict output?values within a pre-defined acceptable range. As new data is fed to these algorithms, they?learn and optimise their operations to improve performance, developing ‘intelligence’?over time.

The types of ML algorithms are?supervised, unsupervised and reinforcement.

• Supervised Learning

Here the machine is?taught by example i.e. a data scientist provides the ML algorithm with a?known dataset; also known as training dataset. This includes desired inputs and outputs, and the algorithm must?find a method to determine how to arrive at those inputs and outputs. So, knowing the correct answers to the problem, the algorithm's job is to identify?patterns in data, learn from its observations and makes predictions as accurately as possible. eg: K-Nearest-Neighbor (KNN), Random Forests, Naive Bayes, Decision Trees, Linear Regression

• Unsupervised?Learning

Here, the ML algorithm studies data to?identify patterns as no pre-set instructions have been provided. Instead, the machine determines the correlations and relationships?by analysing available dataset. The?algorithm then tries to organise that data in some way to define its structure; it could be by means of grouping the data into clusters or groups with similar features or arranging it in a?more organised manner. As it assesses and is fed more data, its ability to?make decisions on that data gradually improves and it eventually becomes more refined. eg: Principal Component Analysis (PCA)

• Reinforcement?Learning

Reinforcement learning focuses on?a systematic learning process, where a ML algorithm is provided with a set of actions,?parameters and end values. By defining the rules, the machine learning algorithm then tries to?explore different options and possibilities, monitoring and evaluating each?result to determine which one is optimal. Reinforcement learning teaches the?machine, trial and error. It learns from past experiences and begins to adapt?its approach in response to the situation to achieve the best possible result. eg: Markov Decision process

Choosing the appropriate ML algorithm?depends on several factors, including, but not limited to data size, data quality, data diversity, data accuracy, training time, parameters as well as what answers businesses want to derive from that?data.

Therefore, choosing the right ML algorithm is both a?combination of business need, specification and time?available.