Machine learning seminar ppt

Seminar ppt on M.l

1. IEC College of Engineering & Technology Greater Noida, UP-201308(INDIA) SEMINAR PPT ON MACHINE LEARNING SUBMITED TO:- SUBMITTED BY:- Mr. Kushagra Goel RAHUL DANGWAL . ( 1 6 9 1 1 )

2. INSIGHTS INTRODUCTION . - 3 ALGORITHMS . - 5 supervised learning - 6 unsupervised learning . - 9 Reinforcement Learning . - 1 3 APPLICATIONS . - 1 5 CONCLUSION . - 1 6

3. Definition Machine learning is an application of artificial intelligence (AI) that provides systems the ability to automatically learn . Machine learning focuses on the development of computer programs that can access data and use it learn for themselves . The primary aim is to allow the computers learn automatically without human intervention or assistance and adjust actions accordingly.

4. ML can play a key role in a wide range of critical applications, such as: 1.data mining, 2.natural language processing, 3.image recognition, 4.expert systems. ML provides potential solutions in all these domains and more, and is set to be a pillar of our future civilization.

5. Algorithm by learning Style There are different ways an algorithm can model a problem based on its interaction with the experience or environment or whatever we count to call the input data. Three different styles in machine learning algorithm : 1. Supervised Learning 2.Un supervised Learning 3.Reinforcement Learning

6. SUPERVISED LEARNING Supervised learning is when the model is getting trained on a labelled dataset. A model is prepared through a training process in which it is required to make predictions . Example problems are classification and regression .

7. Linear regression Linear Regression is a machine learning algorithm based on supervised learning . It performs a regression task . Regression models a target prediction value based on independent variables.

8. While training the model we are given : x: input training data ( univariate – one input variable(parameter)) y: labels to data (supervised learning) θ 1 : intercept θ 2 : coefficient of x Once we find the best θ 1 and θ 2 values, we get the best fit line.

9. UNSUPERVISED LEARNING I n u n s u p ervised l earning d ata is not labeled and does not have a known result. A model is prepared by deducing structures present in the input data. Example algorithms include: the Aproi algorithm and k-Means .

10. C lustering Clustering is the task of dividing the population or data points into a number of groups such that data points in the same groups are more similar to other data . Clustering Algorithms : - K-means clustering Algorithm – It is the simplest unsupervised learning algorithm that solves clustering problem. .K-means algorithm partition n observations into k clusters where each observation belongs to the cluster with the nearest mean serving as a prototype of the cluster .

11. Marketing : It can be used to characterize & discover customer segments for marketing purposes. Biology : It can be used for classification among different species of plants and animals. Libraries : It is used in clustering different books on the basis of topics and information. Insurance : It is used to acknowledge the customers, their policies and identifying the frauds. A P P L I CATION S OF C L U S T E R ING

12. REINFORCEMENT LEARNING Reinforcement learning is the training of machine learning models to make a sequence of decisions. The agent learns to achieve a goal in an uncertain, potentially complex environment.

13. Artificial Intelligence vs Machine Learning vs Deep Learning

14. Everyday Examples of Artificial Intelligence and M.L Google’s AI-Powered Predictions (analyze the speed of traffic at any given time). 2 – Ridesharing Apps Like Uber and Lyft . 3 -Commercial Flights Use an AI Autopilot. 4 – Spam Filters. 5 – Smart Email Categorization(the learning behind Gmail b ox ).

15. CONCLUSION These days machine learning techniques are being widely used to solve real-world problems by storing, manipulating, extracting and retrieving data from large sources . Supervised machine learning techniques have been widely adopted however these techniques prove to be very expensive when the systems are implemented over wide range of data.

16. THANKYOU