Jothi Software Pvt Ltd

#ML Snippets

A "Wading Depth" into Unsupervised Learning techniques - Clustering

Dec 20, 2023

Now that we've covered #supervisedlearning, it's time to move forward to #unsupervisedlearning. We'll be starting off with a basic 101 about clustering, followed by the other methods in our upcoming posts. Clustering is a type of unsupervised learning method in machine learning that involves grouping similar data points together based on their features or characteristics. The goal of clustering is to identify patterns or structures within the data that are not immediately apparent. It is usually used to draw references from datasets consisting of input data without labeled responses. ...Read More

There are several methods of clustering:

1. Density-Based Methods: These methods consider the clusters as the dense region having some similarities and differences from the lower dense region of the space. Example: DBSCAN (Density-Based Spatial Clustering of Applications with Noise), OPTICS (Ordering Points to Identify Clustering Structure), etc.

2. Hierarchical Based Methods: The clusters formed in this method form a tree-type structure based on the hierarchy. Examples: CURE (Clustering Using Representatives), BIRCH (Balanced Iterative Reducing Clustering and using Hierarchies), etc.

3. Partitioning Methods: These methods partition the objects into k clusters and each partition forms one cluster. Example: K-means, CLARANS (Clustering Large Applications based upon Randomized Search), etc.

Uses - Clustering has a wide range of applications, from marketing and customer segmentation to image and speech recognition. It is also used by companies like #amazon in its recommendation system to provide #recommendations based on past search of products.

Here's an example of how K Means clustering is done. We've separated the data into three different colored clusters which all have similar data points in them.

#software #machinelearning #ml #clustering #ml101 #kmeans #recommendersystems ...Read Less

#ML Snippets

A "Wading Depth" into Supervised Learning - Regression

Dec 13, 2023

Aight everybody, let's get straight into it. If you looked into our last post on Classification, you'll know that this post is about "Regression" in Machine Learning. However, if you're new here, howdy and welcome to our page. You can check out our last post here:

https://lnkd.in/gucz4wAC

Now onto Regression:

Regression in machine learning is a statistical method used to model the relationship between a dependent (target) and independent (predictor) variables.It is a supervised learning technique which helps in finding the correlation between variables and enables us to predict the continuous output variable based on one or more predictor variables. It is mainly used for prediction, forecasting, time series modeling, and determining the causal-effect relationship between continuous variables . ...Read More

In Regression, we plot a graph between the variables which best fits the given datapoints. Using this plot, the machine learning model can make predictions about the data and the distance between datapoints and line tells whether a model has captured a strong relationship or not.

Some examples of regression: - Prediction of rain using temperature and other factors - Determining Market trends - Prediction of road accidents due to rash driving.

Types of regression:

So there are two types of regression that we use and they are:

- Simple Regression: Used to predict a continuous dependent variable based on a single independent variable. - Multiple Regression: Used to predict a continuous dependent variable based on multiple independent variables.

#software #machinelearning #ml #classification #ml101 #supervisedlearning

#software #machinelearning #ml #clustering #ml101 #kmeans #recommendersystems ...Read Less

#ML Snippets

A "Wading Depth" into Supervised Learning - Classification

Dec 06, 2023

After quite the break with the festivites (phew!), we're here to give some more insights into Supervised Learning, mainly Classification and Regression.

Regression will be covered in our next post so stay tuned for that. Until then, let's start some learning with Classification. Oh and in case if you're new here or would like a referesher on what we're talking about, check out our previous post on Supervised learning - https://lnkd.in/gEZxyvqA

In supervised machine learning, algorithms can be broadly classified into regression and classification algorithms. Regression algorithms predict the output for continuous values, while classification algorithms predict categorical values. ...Read More

As far as Classification goes, an algorithm is trained on a labeled dataset to predict the class or category of new, unseen data. The main objective is to build a model that can accurately assign a label or category to a new observation based on its features. Post assignment, it should be able to identify the category of new observations on the basis of training data. In short, the program learns from the given dataset or observations and then classifies new observation into a number of classes or groups. Classes can be called as targets/labels or categories.

Let's look into this a bit deeper in terms of "dividing the broad concept" but at the surface level. So, there are two types of learners in machine learning classification: lazy and eager learners. Eager learners are machine learning algorithms that first build a model from the training dataset before making any prediction on future datasets. Lazy learners or instance-based learners, on the other hand, do not create any model immediately from the training data.

Classification problems can have two possible outcomes (Binary Classifier) or more than two outcomes (Multi-class Classifier). An algorithm can learn to predict whether a given email is spam or not would be a perfect everyday use case.

#software #machinelearning #ml #classification #ml101 #supervisedlearning ...Read Less

#ML Snippets

A 101 on Unsupervised Learning

Nov 27, 2023

We're back with the 101 that you've been patiently waiting for - Unsupervised Learning. If you haven't checked our previous post on Supervised learning, you can catch up over here - https://lnkd.in/gEZxyvqA

Unsupervised learning is a type of machine learning where models learn patterns exclusively from unlabeled data. Unlike supervised learning, where models are trained using labeled data, unsupervised learning models find hidden patterns and insights from the given data without any supervision.

Here's a few pointers about unsupervised learning that simplifies our 101 for this post:- ...Read More

What it does: Unsupervised learning can't be directly applied to a regression or classification problem because we have our input data but no corresponding output data. The goal of unsupervised learning is to find the underlying structure of the dataset and group that according to similarities to represent that dataset in a compressed format.

Example: Suppose an unsupervised learning algorithm is given an input dataset containing images of different types of cats and dogs, but the algorithm is never trained upon the given dataset, which means it does not have any idea about the features of the dataset. The task of the unsupervised learning algorithm is to identify the image features on their own and it will perform this task by clustering the image dataset into groups according to similarities between images.

Why use it?: Unsupervised learning is helpful for finding useful insights from the data as it works on unlabeled and uncategorized data, making it important for cases where we do not always have input data with the corresponding output. It's much similar to how a human learns to think by their own experiences, which makes it closer to real AI.

Common approaches: Unsupervised learning models are utilized for three main tasks—clustering, association, and dimensionality reduction. Clustering is a data mining technique which groups unlabeled data based on their similarities or differences.

In fancy terms we can sum up unsupervised learning to this one liner- "Unsupervised learning is an attractive option for tasks where labelled data may be scarce, expensive to obtain, or simply unavailable." ...Read Less

#ML Snippets

A 101 on Supervised Learning

Nov 15, 2023

Generally, we classify machine learning into three branches(well majorly two, but the third is still something that requires quite the work). These three branches are:

- Supervised Learning - Unsupervised Learning - Reinforcement Learning

In today’s post, we’ll be covering a basic 101 on Supervised Learning for all the ML newbies out there:

Supervised learning is a paradigm in machine learning where input objects and a desired output value, (a human-labeled supervisory signal) are used to train a model. The training data is processed and it builds a function that maps new data on expected output values, as the data is labeled.

In supervised learning, models are trained using labeled datasets – meaning that each segment of the data is labeled through and through and the model wouldn’t have a hard time comprehending this as all it would require is a bit of pre-processing or what we like to call “tweaking to make it prettier for the model.” To understand this better, we've added a visual below. ...Read More

Once the training process is completed, the model is tested based on test data (a subset of the training set), and then it predicts the output.

Supervised learning is further divided into two types:

1. Classification: A classification problem is when the output variable is a category, such as “Red” or “blue”, “disease” or “no disease”. 2. Regression: A regression problem is when the output variable is a real value, such as “dollars” or “weight”.

However, classifying big data can be challenging, as supervised learning would require a lot of computation time to learn all the labels in a short span, which is where Unsupervised Learning comes in, but more on the 101 for that in our next post so stay tuned. ...Read Less

Exploring the Future: AI and ML insights

Recent posts

A "Wading Depth" into Unsupervised Learning techniques - Clustering

A 101 on Unsupervised Learning

A "Wading Depth" into Supervised Learning - Classification