Azure AI

AI 900 – 2 – The depths of machine learning

Content type Blog Post

Author Kamal Radhakrishnaiah

Publication Date 16 Jan, 2026

Reading Time Less than 1 minute

Contents

Introduction

We started our jou
ey getting a hang of the basics related to AI, Responsible AI and Machine lea
ing. You hear the buzz words Large Language Models (LLM’s) all the time? Lets explore how they came into existance in this blog!

Type of Machine Lea
ing

There are 2 types of machine lea
ing based on the training data included to train the algorithm.

Supervised Machine Lea
ing: In this type of machine lea
ing the training data includes both the feature values and known label values. They are used to train models by determining a relationshop between features and labels in the past observations so that unknown labels can be predicted for features in future cases. There are 2 types of supervised machine lea
ing: Regression (label predicted by the model is a numeric value and Classification (label predicated is a categorization or class, which intu
has binary classifcation which predicts one of the two possible outcomes and multiclass classification which predicts multiple possible values)
Unsupervised Machine Lea
ing: This type of machine lea
ing involves training models using data that consists only of feature values without any known lables. There is 1 type of unsupervised machine lea
ing called Clustering which identifies similarities between observations based on their features and groups them into discrete clusters

Some examples of different types of machine lea
ing below:

Number of ice creams sold on a given day based on temperature, rainfall and wind speed = Regression (supervised machine lea
ing)
Patients at risk for diabetes based on blood glucose level = Binary classification (supervised machine lea
ing)
Identify the species of penguines based on flipper length = Multiclass classification (supervised machine lea
ing)
Group the flowers based on the number of leaves and petals = Clustering (unsupervised machine lea
ing)

Deep Lea
ing

Deep lea
ing is an advanced form of machine lea
ing that tries to emulate the way human brian lea
s. It creates an artificial neural network that stimulates electrochemical activity in biological neurons using mathematical functions. Models produced by deep lea
ing are called deep neural networks

Transformers

Transformer models are trained with large volumes of text enabling them to represent the semantic relationships between words and use those relationships to determine probable sequences of text that makes sense.

Large Language Models are based on Transformer architecture which uses and extends some techniques that have been proven successful in modelling vocabularies to support Natural Language Processing tasks and specifically generating language.

The Transformer architecture consists of 5 components:

Training text of large volumes that is used to train the model
Encoder that breaks the text tokens which are sequenced using attention
Embeddings which is a collection of vectors (multi valued numeric arrays) in which each element of the vector represents a sematic attribute of the token
Decoder generates an appropriate output by creating a new sequence of tokens using the embeddings created by the encoder.
Attention technique to predict an appropriate completion of the sentence by analyzing the input tokens and semantic attrinutes embedded in the embeddings.