SlideShare a Scribd company logo
1 of 43
Download to read offline
Machine Learning
A YEAR SPENT IN
ARTIFICIAL INTELLIGENCE
ENOUGH TO MAKE ONE BELIEVE IN GOD” – ALAN PERLIS
Agenda
 Introduction
 Basics
 Types of Machine Learning
 Machine Learning Technologies
 Application
 Vision in next few years
Quick Questionnaire
 How many people have heard about Machine Learning ?
 How many people know about Machine Learning ?
 How many people are using Machine Learning ?
What is Machine Learning ?
 Subfield of Artificial Intelligence.
 First Arthur Samuel gave the concept of Machine Learning, In 1959.
 "Field of study that gives computers the ability to learn without being explicitly programmed“.
 Computer program is said to be learn from Experience (E) with some class of tasks (T) and
performance measure (P) if its performance at tasks in T as measured by P improves with E.
What is Machine Learning ?
 Explores the study and construction of algorithms that can learn from and make
predictions on data.
 Algorithms operate by building a model from example inputs.
 Data driven predictions or decisions.
 Unlike strictly static program instructions as we do.
Artificial Intelligence
 Machine Learning is the branch of the Artificial Intelligence.
 Inserting the learning capabilities just like humans into machines.
 Even the fastest supercomputer is 32 times slower than Human Brain.
 Predictions says that in 2o6o , we are able to form the digital brain like humans.
 NLP (Natural Language Processing ) is also based on the Machine Learning , more the data the
machine has , more its prediction goes to perfect.
 Titanic Disaster could be saved through Machine Learning.
Use of Machine Learning
 Google Search, Google News ,Page Ranking decided by Machine Learning.
 Upload images , automatically detects the face of your friend.
 Spam filter which is used to filter our mails from tones of spam mails.
 Right product for the right customers.
More applications
 Speech and hand-writing recognition
 Autonomous robot control
 Data mining and bioinformatics: motifs, alignment, …
 Playing games
 Fault detection
 Clinical diagnosis
 Credit scoring, fraud detection
 Web mining: search engines
 Market basket analysis
Why Machine Learning
 Human expertise does not exist (navigating on Mars)-
 TARS in Interstellar.
 Humans are unable to explain their expertise (speech recognition).
 Solution changes in time (routing on a computer network).
 Solution needs to be adapted to particular cases (user biometrics).
Terminology / Basic Terms
 Features – The numbers of features and distinct traits that can be used to describe
each item in quantitative manner.
 Samples – Sample is an item to process. It can document, picture, sound, video or
any other file contains data.
 Feature Vector – n dimensional vector that represents some object.
 Training Set – Set of data to discover potentially predictive relationships.
Terminology with Example
Features
Color – Red
Type- Logo
Shape
Features
Color – Light Blue
Type – Logo
Shape
Here sample are –both apples, Feature Vector =[Color, Type, Shape] , Training Set- Taken all at time
Categories
Types of Problems and Tasks
 Depending on the nature of the learning "signal" or "feedback" available to a learning system.
Supervised Learning
Unsupervised Learning
Reinforcement Learning
Example of Supervised Learning
Supervised Learning
 Learning from labelled data, and different set of training examples.
 Input and output is fixed.
 the goal is to learn a general rule that maps inputs to outputs.
 Or find the correlation to between input and output to find the algo which is
general to all the training examples.
 Input data called Vector & Output value called Supervisory signal.
 Presence of Expert or Teacher.
 E.g.- Neural Networks , Decision Trees , Bayesian Classification.
To solve Supervised Learning problem
 Determine the type of training examples.
 Decide what kind of data is to be used as a training set.
 Gather a training set.
 Set of input object and corresponding output is gathered.
 Determine the input feature representation of the learned function.
 The input object is transformed into a feature vector, which contains a number of features
that are descriptive of the object.
To solve Supervised Learning problem
 Determine the structure of the learned function and corresponding learning algorithm.
 Find out the function or algorithm which maps all the training sets.
 Just like bridge how input is connected with output.
 Complete the design.
 Addition of some control parameters & adjusted by optimizing performance.
 Evaluate the accuracy of the learned function.
 Check it is working properly or not, if not redesign again.
Supervised Learning Flow Chart
Raw Data Algorithm
Sample Data Trained
Product
Verification Production
Application
 Bioinformatics
 Database marketing
 Handwriting recognition
 Spam detection
 Pattern Recognition
 Speech Recognition
Unsupervised Learning
 No labels are given to the learning algorithm.
 Find structure in its input with the help of Clustering.
 Discover hidden patterns in data and find the suitable algorithm.
 As input is unlabeled, there is no error or reward signal to evaluate a potential solution. This makes
it different form others.
 Self guided learning algorithm.
 Plays important role in data mining methods to preprocess the data.
 Approaches to Unsupervised Learning – K means, hierarchical clustering, mixture models.
Unsupervised Learning
K- means / Hierarchical
 K means is a method of vector quantization.
 Partition of n observation into k cluster, and it belongs to nearest mean
 Popular of clustering analysis in data mining.
 NP Hard Problem.
 Hierarchical clustering builds a hierarchy of clusters.
 Agglomerative (Bottom Up Approach)
 Divisive (Top down Approach)
Applications
Difference Supervised Vs Unsupervised
Reinforcement Learning
 Program interacts with a dynamic environment.
 No explicit instructions.
 Decide its own whether it is near to goal or not.
 “Approximate Dynamic Programming”
 Unlike supervised learning correct input/output pairs are never presented.
 No optimization step is there like supervised learning to tell we have reached up to our goal.
 There is a focus on on-line performance.
 Finds a balance between exploration (of uncharted territory) and exploitation (of current
knowledge)
Basic Reinforcement Learning Model
 Set of environment states S.
 Set of actions A.
 Rules of transitions between states.
 Rules that determine the scalar immediate reward of transition.
 Rules that describe what the agent observes.
Algorithms used for Reinforcement Learning
 Criterion of optimality
 the problem studied is episodic, an episode ending when some terminal state is reached.
 Brute force (2 Step Policies)
 For each possible policy, sample returns while following it.
 Choose the policy with the largest expected return.
 1.Value function estimation 2. Direct policy search
 Value function approaches
 It finds the policy which return maximize but maintaining sets.
 Based on MKP(Markov Decision Parameters)
Applications of Reinforcement Learning
 Game theory
 Control theory
 Operations research
 Information theory
 Simulation-based optimization
 Multi-agent systems
 Swarm intelligence
 Statistics
 Genetic algorithms
Semi-Supervised Learning
 Semi-supervised learning is a class of supervised learning tasks.
 But it uses large amount of unlabelled data with the labelled data.
 Actually it falls between supervised learning and supervised learning.
 Assumptions used in semi-supervised learning.
 Smoothness assumption - Points which are close to each other are more likely to share a label.
 Cluster assumption - The data tend to form discrete clusters, and points in the same cluster are more
likely to share a label
 Manifold assumption - The data lie approximately on a manifold of much lower dimension than the
input space.
How ML used in Hospitals
Machine Learning Methods
based on
output of a machine-learned system
Another Categorization
 Based on “desired output” of a machine-learned system
Classification
Regression
Clustering
Classification
 Predict class from observations.
 Inputs are divided into two or more classes.
 Model assigns unseen inputs to one (or multi-label classification) or more of these classes.
 Spam filtering is an example of classification, where the inputs are email (or other) messages and
the classes are "spam" and "not spam"
Regression
 Relation between mean value of one variable and corresponding value of another
variable.
 Statistical method to find the relation between different variables.
 Predict the output with the training data and observations.
 Popular method – Logistic Regression or binary regression.
 The outputs are continuous rather than discrete.
Clustering
 Grouping a set of objects in such way that objects in the same group are similar to each other.
 Objects are not predefined.
 Grouping in meaningful group.
 Unlike in classification, the groups are not known beforehand, making this typically an
unsupervised task.
 Example – Man’s shoes , woman’s shoes , man’s t-shirt, woman’s t-shirts.
 So they are two category “man & woman” and “t-shirts & shoes”.
Popular Framework / Tools
 Weka
 Carrot2
 Gate
 OpenNLP
 LingPipe
 Mallet – Topic Modelling
 Gensim – Topic Modelling (Python)
 Apache Mahout
 Mlib – Apache Spark
 Scikit learn – Python
Difference
Classification
 Classification means to group the output
into class.
 Classification to predict the type of tumor
i.e. harmful or not using the training data
sets.
 If it is discrete / categorical variable , then
it is classification problem.
Regression
 Regression means to predict the output
value using training data.
 Regression to predict the price of the
house from training data sets.
 If it is real / continuous then it is
regressions problem.
Approaches
Decision Tree Learning
 Predictive model.
 Maps observations about an item to conclusions about the item's target value.
 Used in Statistics and data mining.
 Tree models where the target variable can take a finite set of values are called classification trees.
 Leaves represent class labels & branches represent conjunctions.
 When target variable can take continuous values - regression trees.
 In data mining, a decision tree describes data but not decisions.
 Example – Wikipedia
Artificial Neural Networks
 Inspired by Biological Neural Networks(Central Nervous System of animal).
 Used when there are large number of inputs and generally unknown.
 ANNs are generally presented as systems of interconnected "neurons" which exchange messages
between each other.
 Used to solve computer vision, speech recognition and handwriting recognition.
 Eg. In handwriting recognition
 1. Input neuron activated by the pixels of an input image.
 2. Weighted and transformed by a function, the activations of these neurons are then passed on to
other neurons.
 3. This process is repeated until finally, an output neuron is activated. This determines which character
was read.
Artificial Neural Networks Structure
Any Queries ?
for more information :-
machinecanthink.blogspot.in

More Related Content

Similar to machinecanthink-160226155704.pdf

introduction to machine learning
introduction to machine learningintroduction to machine learning
introduction to machine learningJohnson Ubah
 
Machine Learning Basics
Machine Learning BasicsMachine Learning Basics
Machine Learning BasicsSuresh Arora
 
Machine learning-in-details-with-out-python-code
Machine learning-in-details-with-out-python-codeMachine learning-in-details-with-out-python-code
Machine learning-in-details-with-out-python-codeOsama Ghandour Geris
 
Machine learning with ADA Boost
Machine learning with ADA BoostMachine learning with ADA Boost
Machine learning with ADA BoostAman Patel
 
Introduction to Machine Learning
Introduction to Machine LearningIntroduction to Machine Learning
Introduction to Machine LearningSujith Jayaprakash
 
Intro/Overview on Machine Learning Presentation
Intro/Overview on Machine Learning PresentationIntro/Overview on Machine Learning Presentation
Intro/Overview on Machine Learning PresentationAnkit Gupta
 
Machine learning presentation (razi)
Machine learning presentation (razi)Machine learning presentation (razi)
Machine learning presentation (razi)Rizwan Shaukat
 
Machine learning
Machine learningMachine learning
Machine learningAbrar ali
 
Top 40 Data Science Interview Questions and Answers 2022.pdf
Top 40 Data Science Interview Questions and Answers 2022.pdfTop 40 Data Science Interview Questions and Answers 2022.pdf
Top 40 Data Science Interview Questions and Answers 2022.pdfSuraj Kumar
 
Lect 7 intro to M.L..pdf
Lect 7 intro to M.L..pdfLect 7 intro to M.L..pdf
Lect 7 intro to M.L..pdfHassanElalfy4
 
LearningAG.ppt
LearningAG.pptLearningAG.ppt
LearningAG.pptbutest
 
Internship - Python - AI ML.pptx
Internship - Python - AI ML.pptxInternship - Python - AI ML.pptx
Internship - Python - AI ML.pptxHchethankumar
 
Internship - Python - AI ML.pptx
Internship - Python - AI ML.pptxInternship - Python - AI ML.pptx
Internship - Python - AI ML.pptxHchethankumar
 
Machine Learning Landscape
Machine Learning LandscapeMachine Learning Landscape
Machine Learning LandscapeEng Teong Cheah
 
ML crash course
ML crash courseML crash course
ML crash coursemikaelhuss
 
Artificial intyelligence and machine learning introduction.pptx
Artificial intyelligence and machine learning introduction.pptxArtificial intyelligence and machine learning introduction.pptx
Artificial intyelligence and machine learning introduction.pptxChandrakalaV15
 
notes as .ppt
notes as .pptnotes as .ppt
notes as .pptbutest
 

Similar to machinecanthink-160226155704.pdf (20)

introduction to machine learning
introduction to machine learningintroduction to machine learning
introduction to machine learning
 
Machine Learning Basics
Machine Learning BasicsMachine Learning Basics
Machine Learning Basics
 
Machine learning-in-details-with-out-python-code
Machine learning-in-details-with-out-python-codeMachine learning-in-details-with-out-python-code
Machine learning-in-details-with-out-python-code
 
Introduction to machine learning
Introduction to machine learningIntroduction to machine learning
Introduction to machine learning
 
Machine learning with ADA Boost
Machine learning with ADA BoostMachine learning with ADA Boost
Machine learning with ADA Boost
 
Introduction to Machine Learning
Introduction to Machine LearningIntroduction to Machine Learning
Introduction to Machine Learning
 
Intro/Overview on Machine Learning Presentation
Intro/Overview on Machine Learning PresentationIntro/Overview on Machine Learning Presentation
Intro/Overview on Machine Learning Presentation
 
Machine learning presentation (razi)
Machine learning presentation (razi)Machine learning presentation (razi)
Machine learning presentation (razi)
 
Machine learning
Machine learningMachine learning
Machine learning
 
Top 40 Data Science Interview Questions and Answers 2022.pdf
Top 40 Data Science Interview Questions and Answers 2022.pdfTop 40 Data Science Interview Questions and Answers 2022.pdf
Top 40 Data Science Interview Questions and Answers 2022.pdf
 
Lect 7 intro to M.L..pdf
Lect 7 intro to M.L..pdfLect 7 intro to M.L..pdf
Lect 7 intro to M.L..pdf
 
LearningAG.ppt
LearningAG.pptLearningAG.ppt
LearningAG.ppt
 
Machine Learning
Machine LearningMachine Learning
Machine Learning
 
Internship - Python - AI ML.pptx
Internship - Python - AI ML.pptxInternship - Python - AI ML.pptx
Internship - Python - AI ML.pptx
 
Internship - Python - AI ML.pptx
Internship - Python - AI ML.pptxInternship - Python - AI ML.pptx
Internship - Python - AI ML.pptx
 
Machine Learning Landscape
Machine Learning LandscapeMachine Learning Landscape
Machine Learning Landscape
 
ML crash course
ML crash courseML crash course
ML crash course
 
Artificial intyelligence and machine learning introduction.pptx
Artificial intyelligence and machine learning introduction.pptxArtificial intyelligence and machine learning introduction.pptx
Artificial intyelligence and machine learning introduction.pptx
 
ML_lec1.pdf
ML_lec1.pdfML_lec1.pdf
ML_lec1.pdf
 
notes as .ppt
notes as .pptnotes as .ppt
notes as .ppt
 

More from PranavPatil822557

distancelearning-160626204752.pdf
distancelearning-160626204752.pdfdistancelearning-160626204752.pdf
distancelearning-160626204752.pdfPranavPatil822557
 
2020_Distance_Learning_Powerpoint.pdf
2020_Distance_Learning_Powerpoint.pdf2020_Distance_Learning_Powerpoint.pdf
2020_Distance_Learning_Powerpoint.pdfPranavPatil822557
 
Induction Program_Revised Schedule.docx
Induction Program_Revised Schedule.docxInduction Program_Revised Schedule.docx
Induction Program_Revised Schedule.docxPranavPatil822557
 
socialnetworkprivacysecurity-130718062319-phpapp02.pdf
socialnetworkprivacysecurity-130718062319-phpapp02.pdfsocialnetworkprivacysecurity-130718062319-phpapp02.pdf
socialnetworkprivacysecurity-130718062319-phpapp02.pdfPranavPatil822557
 
Machine Learning , Analytics & Cyber Security the Next Level Threat Analytics...
Machine Learning , Analytics & Cyber Security the Next Level Threat Analytics...Machine Learning , Analytics & Cyber Security the Next Level Threat Analytics...
Machine Learning , Analytics & Cyber Security the Next Level Threat Analytics...PranavPatil822557
 

More from PranavPatil822557 (7)

distancelearning-160626204752.pdf
distancelearning-160626204752.pdfdistancelearning-160626204752.pdf
distancelearning-160626204752.pdf
 
2020_Distance_Learning_Powerpoint.pdf
2020_Distance_Learning_Powerpoint.pdf2020_Distance_Learning_Powerpoint.pdf
2020_Distance_Learning_Powerpoint.pdf
 
Linux Command.ppsx
Linux Command.ppsxLinux Command.ppsx
Linux Command.ppsx
 
Induction Program_Revised Schedule.docx
Induction Program_Revised Schedule.docxInduction Program_Revised Schedule.docx
Induction Program_Revised Schedule.docx
 
socialnetworkprivacysecurity-130718062319-phpapp02.pdf
socialnetworkprivacysecurity-130718062319-phpapp02.pdfsocialnetworkprivacysecurity-130718062319-phpapp02.pdf
socialnetworkprivacysecurity-130718062319-phpapp02.pdf
 
final-180430094306.pdf
final-180430094306.pdffinal-180430094306.pdf
final-180430094306.pdf
 
Machine Learning , Analytics & Cyber Security the Next Level Threat Analytics...
Machine Learning , Analytics & Cyber Security the Next Level Threat Analytics...Machine Learning , Analytics & Cyber Security the Next Level Threat Analytics...
Machine Learning , Analytics & Cyber Security the Next Level Threat Analytics...
 

Recently uploaded

Russian⚡ Call Girls In Sector 39 Noida✨8375860717⚡Escorts Service
Russian⚡ Call Girls In Sector 39 Noida✨8375860717⚡Escorts ServiceRussian⚡ Call Girls In Sector 39 Noida✨8375860717⚡Escorts Service
Russian⚡ Call Girls In Sector 39 Noida✨8375860717⚡Escorts Servicedoor45step
 
Benjamin Portfolio Process Work Slideshow
Benjamin Portfolio Process Work SlideshowBenjamin Portfolio Process Work Slideshow
Benjamin Portfolio Process Work Slideshowssuser971f6c
 
Bare And Wild Creation, Curio Shop, Tucumcari NM
Bare And Wild Creation, Curio Shop, Tucumcari NMBare And Wild Creation, Curio Shop, Tucumcari NM
Bare And Wild Creation, Curio Shop, Tucumcari NMroute66connected
 
Akola Call Girls #9907093804 Contact Number Escorts Service Akola
Akola Call Girls #9907093804 Contact Number Escorts Service AkolaAkola Call Girls #9907093804 Contact Number Escorts Service Akola
Akola Call Girls #9907093804 Contact Number Escorts Service Akolasrsj9000
 
FULL ENJOY - 9953040155 Call Girls in Dwarka Mor | Delhi
FULL ENJOY - 9953040155 Call Girls in Dwarka Mor | DelhiFULL ENJOY - 9953040155 Call Girls in Dwarka Mor | Delhi
FULL ENJOY - 9953040155 Call Girls in Dwarka Mor | DelhiMalviyaNagarCallGirl
 
FULL ENJOY - 9953040155 Call Girls in Lajpat Nagar | Delhi
FULL ENJOY - 9953040155 Call Girls in Lajpat Nagar | DelhiFULL ENJOY - 9953040155 Call Girls in Lajpat Nagar | Delhi
FULL ENJOY - 9953040155 Call Girls in Lajpat Nagar | DelhiMalviyaNagarCallGirl
 
FULL ENJOY - 9953040155 Call Girls in Moti Nagar | Delhi
FULL ENJOY - 9953040155 Call Girls in Moti Nagar | DelhiFULL ENJOY - 9953040155 Call Girls in Moti Nagar | Delhi
FULL ENJOY - 9953040155 Call Girls in Moti Nagar | DelhiMalviyaNagarCallGirl
 
9654467111 Call Girls In Noida Sector 62 Short 1500 Night 6000
9654467111 Call Girls In Noida Sector 62 Short 1500 Night 60009654467111 Call Girls In Noida Sector 62 Short 1500 Night 6000
9654467111 Call Girls In Noida Sector 62 Short 1500 Night 6000Sapana Sha
 
Russian⚡ Call Girls In Sector 104 Noida✨8375860717⚡Escorts Service
Russian⚡ Call Girls In Sector 104 Noida✨8375860717⚡Escorts ServiceRussian⚡ Call Girls In Sector 104 Noida✨8375860717⚡Escorts Service
Russian⚡ Call Girls In Sector 104 Noida✨8375860717⚡Escorts Servicedoor45step
 
Karol Bagh Call Girls : ☎ 8527673949, Low rate Call Girls
Karol Bagh Call Girls : ☎ 8527673949, Low rate Call GirlsKarol Bagh Call Girls : ☎ 8527673949, Low rate Call Girls
Karol Bagh Call Girls : ☎ 8527673949, Low rate Call Girlsashishs7044
 
Burari Call Girls : ☎ 8527673949, Low rate Call Girls
Burari Call Girls : ☎ 8527673949, Low rate Call GirlsBurari Call Girls : ☎ 8527673949, Low rate Call Girls
Burari Call Girls : ☎ 8527673949, Low rate Call Girlsashishs7044
 
SHIVNA SAHITYIKI APRIL JUNE 2024 Magazine
SHIVNA SAHITYIKI APRIL JUNE 2024 MagazineSHIVNA SAHITYIKI APRIL JUNE 2024 Magazine
SHIVNA SAHITYIKI APRIL JUNE 2024 MagazineShivna Prakashan
 
MinSheng Gaofeng Estate commercial storyboard
MinSheng Gaofeng Estate commercial storyboardMinSheng Gaofeng Estate commercial storyboard
MinSheng Gaofeng Estate commercial storyboardjessica288382
 
Pragati Maidan Call Girls : ☎ 8527673949, Low rate Call Girls
Pragati Maidan Call Girls : ☎ 8527673949, Low rate Call GirlsPragati Maidan Call Girls : ☎ 8527673949, Low rate Call Girls
Pragati Maidan Call Girls : ☎ 8527673949, Low rate Call Girlsashishs7044
 
Downtown Call Girls O5O91O128O Pakistani Call Girls in Downtown
Downtown Call Girls O5O91O128O Pakistani Call Girls in DowntownDowntown Call Girls O5O91O128O Pakistani Call Girls in Downtown
Downtown Call Girls O5O91O128O Pakistani Call Girls in Downtowndajasot375
 
Low Rate Call Girls in Laxmi Nagar Delhi Call 9990771857
Low Rate Call Girls in Laxmi Nagar Delhi Call 9990771857Low Rate Call Girls in Laxmi Nagar Delhi Call 9990771857
Low Rate Call Girls in Laxmi Nagar Delhi Call 9990771857delhimodel235
 
Russian Call Girls Delhi NCR 9999965857 Call or WhatsApp Anytime
Russian Call Girls Delhi NCR 9999965857 Call or WhatsApp AnytimeRussian Call Girls Delhi NCR 9999965857 Call or WhatsApp Anytime
Russian Call Girls Delhi NCR 9999965857 Call or WhatsApp AnytimeKomal Khan
 
Call Girl in Bur Dubai O5286O4116 Indian Call Girls in Bur Dubai By VIP Bur D...
Call Girl in Bur Dubai O5286O4116 Indian Call Girls in Bur Dubai By VIP Bur D...Call Girl in Bur Dubai O5286O4116 Indian Call Girls in Bur Dubai By VIP Bur D...
Call Girl in Bur Dubai O5286O4116 Indian Call Girls in Bur Dubai By VIP Bur D...dajasot375
 

Recently uploaded (20)

Russian⚡ Call Girls In Sector 39 Noida✨8375860717⚡Escorts Service
Russian⚡ Call Girls In Sector 39 Noida✨8375860717⚡Escorts ServiceRussian⚡ Call Girls In Sector 39 Noida✨8375860717⚡Escorts Service
Russian⚡ Call Girls In Sector 39 Noida✨8375860717⚡Escorts Service
 
Benjamin Portfolio Process Work Slideshow
Benjamin Portfolio Process Work SlideshowBenjamin Portfolio Process Work Slideshow
Benjamin Portfolio Process Work Slideshow
 
Bare And Wild Creation, Curio Shop, Tucumcari NM
Bare And Wild Creation, Curio Shop, Tucumcari NMBare And Wild Creation, Curio Shop, Tucumcari NM
Bare And Wild Creation, Curio Shop, Tucumcari NM
 
Akola Call Girls #9907093804 Contact Number Escorts Service Akola
Akola Call Girls #9907093804 Contact Number Escorts Service AkolaAkola Call Girls #9907093804 Contact Number Escorts Service Akola
Akola Call Girls #9907093804 Contact Number Escorts Service Akola
 
FULL ENJOY - 9953040155 Call Girls in Dwarka Mor | Delhi
FULL ENJOY - 9953040155 Call Girls in Dwarka Mor | DelhiFULL ENJOY - 9953040155 Call Girls in Dwarka Mor | Delhi
FULL ENJOY - 9953040155 Call Girls in Dwarka Mor | Delhi
 
FULL ENJOY - 9953040155 Call Girls in Lajpat Nagar | Delhi
FULL ENJOY - 9953040155 Call Girls in Lajpat Nagar | DelhiFULL ENJOY - 9953040155 Call Girls in Lajpat Nagar | Delhi
FULL ENJOY - 9953040155 Call Girls in Lajpat Nagar | Delhi
 
Call~Girl in Rajendra Nagar New Delhi 8448380779 Full Enjoy Escort Service
Call~Girl in Rajendra Nagar New Delhi 8448380779 Full Enjoy Escort ServiceCall~Girl in Rajendra Nagar New Delhi 8448380779 Full Enjoy Escort Service
Call~Girl in Rajendra Nagar New Delhi 8448380779 Full Enjoy Escort Service
 
FULL ENJOY - 9953040155 Call Girls in Moti Nagar | Delhi
FULL ENJOY - 9953040155 Call Girls in Moti Nagar | DelhiFULL ENJOY - 9953040155 Call Girls in Moti Nagar | Delhi
FULL ENJOY - 9953040155 Call Girls in Moti Nagar | Delhi
 
9654467111 Call Girls In Noida Sector 62 Short 1500 Night 6000
9654467111 Call Girls In Noida Sector 62 Short 1500 Night 60009654467111 Call Girls In Noida Sector 62 Short 1500 Night 6000
9654467111 Call Girls In Noida Sector 62 Short 1500 Night 6000
 
Russian⚡ Call Girls In Sector 104 Noida✨8375860717⚡Escorts Service
Russian⚡ Call Girls In Sector 104 Noida✨8375860717⚡Escorts ServiceRussian⚡ Call Girls In Sector 104 Noida✨8375860717⚡Escorts Service
Russian⚡ Call Girls In Sector 104 Noida✨8375860717⚡Escorts Service
 
Karol Bagh Call Girls : ☎ 8527673949, Low rate Call Girls
Karol Bagh Call Girls : ☎ 8527673949, Low rate Call GirlsKarol Bagh Call Girls : ☎ 8527673949, Low rate Call Girls
Karol Bagh Call Girls : ☎ 8527673949, Low rate Call Girls
 
Burari Call Girls : ☎ 8527673949, Low rate Call Girls
Burari Call Girls : ☎ 8527673949, Low rate Call GirlsBurari Call Girls : ☎ 8527673949, Low rate Call Girls
Burari Call Girls : ☎ 8527673949, Low rate Call Girls
 
SHIVNA SAHITYIKI APRIL JUNE 2024 Magazine
SHIVNA SAHITYIKI APRIL JUNE 2024 MagazineSHIVNA SAHITYIKI APRIL JUNE 2024 Magazine
SHIVNA SAHITYIKI APRIL JUNE 2024 Magazine
 
Dxb Call Girls # +971529501107 # Call Girls In Dxb Dubai || (UAE)
Dxb Call Girls # +971529501107 # Call Girls In Dxb Dubai || (UAE)Dxb Call Girls # +971529501107 # Call Girls In Dxb Dubai || (UAE)
Dxb Call Girls # +971529501107 # Call Girls In Dxb Dubai || (UAE)
 
MinSheng Gaofeng Estate commercial storyboard
MinSheng Gaofeng Estate commercial storyboardMinSheng Gaofeng Estate commercial storyboard
MinSheng Gaofeng Estate commercial storyboard
 
Pragati Maidan Call Girls : ☎ 8527673949, Low rate Call Girls
Pragati Maidan Call Girls : ☎ 8527673949, Low rate Call GirlsPragati Maidan Call Girls : ☎ 8527673949, Low rate Call Girls
Pragati Maidan Call Girls : ☎ 8527673949, Low rate Call Girls
 
Downtown Call Girls O5O91O128O Pakistani Call Girls in Downtown
Downtown Call Girls O5O91O128O Pakistani Call Girls in DowntownDowntown Call Girls O5O91O128O Pakistani Call Girls in Downtown
Downtown Call Girls O5O91O128O Pakistani Call Girls in Downtown
 
Low Rate Call Girls in Laxmi Nagar Delhi Call 9990771857
Low Rate Call Girls in Laxmi Nagar Delhi Call 9990771857Low Rate Call Girls in Laxmi Nagar Delhi Call 9990771857
Low Rate Call Girls in Laxmi Nagar Delhi Call 9990771857
 
Russian Call Girls Delhi NCR 9999965857 Call or WhatsApp Anytime
Russian Call Girls Delhi NCR 9999965857 Call or WhatsApp AnytimeRussian Call Girls Delhi NCR 9999965857 Call or WhatsApp Anytime
Russian Call Girls Delhi NCR 9999965857 Call or WhatsApp Anytime
 
Call Girl in Bur Dubai O5286O4116 Indian Call Girls in Bur Dubai By VIP Bur D...
Call Girl in Bur Dubai O5286O4116 Indian Call Girls in Bur Dubai By VIP Bur D...Call Girl in Bur Dubai O5286O4116 Indian Call Girls in Bur Dubai By VIP Bur D...
Call Girl in Bur Dubai O5286O4116 Indian Call Girls in Bur Dubai By VIP Bur D...
 

machinecanthink-160226155704.pdf

  • 1. Machine Learning A YEAR SPENT IN ARTIFICIAL INTELLIGENCE ENOUGH TO MAKE ONE BELIEVE IN GOD” – ALAN PERLIS
  • 2. Agenda  Introduction  Basics  Types of Machine Learning  Machine Learning Technologies  Application  Vision in next few years
  • 3. Quick Questionnaire  How many people have heard about Machine Learning ?  How many people know about Machine Learning ?  How many people are using Machine Learning ?
  • 4. What is Machine Learning ?  Subfield of Artificial Intelligence.  First Arthur Samuel gave the concept of Machine Learning, In 1959.  "Field of study that gives computers the ability to learn without being explicitly programmed“.  Computer program is said to be learn from Experience (E) with some class of tasks (T) and performance measure (P) if its performance at tasks in T as measured by P improves with E.
  • 5. What is Machine Learning ?  Explores the study and construction of algorithms that can learn from and make predictions on data.  Algorithms operate by building a model from example inputs.  Data driven predictions or decisions.  Unlike strictly static program instructions as we do.
  • 6.
  • 7. Artificial Intelligence  Machine Learning is the branch of the Artificial Intelligence.  Inserting the learning capabilities just like humans into machines.  Even the fastest supercomputer is 32 times slower than Human Brain.  Predictions says that in 2o6o , we are able to form the digital brain like humans.  NLP (Natural Language Processing ) is also based on the Machine Learning , more the data the machine has , more its prediction goes to perfect.  Titanic Disaster could be saved through Machine Learning.
  • 8. Use of Machine Learning  Google Search, Google News ,Page Ranking decided by Machine Learning.  Upload images , automatically detects the face of your friend.  Spam filter which is used to filter our mails from tones of spam mails.  Right product for the right customers.
  • 9. More applications  Speech and hand-writing recognition  Autonomous robot control  Data mining and bioinformatics: motifs, alignment, …  Playing games  Fault detection  Clinical diagnosis  Credit scoring, fraud detection  Web mining: search engines  Market basket analysis
  • 10. Why Machine Learning  Human expertise does not exist (navigating on Mars)-  TARS in Interstellar.  Humans are unable to explain their expertise (speech recognition).  Solution changes in time (routing on a computer network).  Solution needs to be adapted to particular cases (user biometrics).
  • 11. Terminology / Basic Terms  Features – The numbers of features and distinct traits that can be used to describe each item in quantitative manner.  Samples – Sample is an item to process. It can document, picture, sound, video or any other file contains data.  Feature Vector – n dimensional vector that represents some object.  Training Set – Set of data to discover potentially predictive relationships.
  • 12. Terminology with Example Features Color – Red Type- Logo Shape Features Color – Light Blue Type – Logo Shape Here sample are –both apples, Feature Vector =[Color, Type, Shape] , Training Set- Taken all at time
  • 14. Types of Problems and Tasks  Depending on the nature of the learning "signal" or "feedback" available to a learning system. Supervised Learning Unsupervised Learning Reinforcement Learning
  • 16. Supervised Learning  Learning from labelled data, and different set of training examples.  Input and output is fixed.  the goal is to learn a general rule that maps inputs to outputs.  Or find the correlation to between input and output to find the algo which is general to all the training examples.  Input data called Vector & Output value called Supervisory signal.  Presence of Expert or Teacher.  E.g.- Neural Networks , Decision Trees , Bayesian Classification.
  • 17. To solve Supervised Learning problem  Determine the type of training examples.  Decide what kind of data is to be used as a training set.  Gather a training set.  Set of input object and corresponding output is gathered.  Determine the input feature representation of the learned function.  The input object is transformed into a feature vector, which contains a number of features that are descriptive of the object.
  • 18. To solve Supervised Learning problem  Determine the structure of the learned function and corresponding learning algorithm.  Find out the function or algorithm which maps all the training sets.  Just like bridge how input is connected with output.  Complete the design.  Addition of some control parameters & adjusted by optimizing performance.  Evaluate the accuracy of the learned function.  Check it is working properly or not, if not redesign again.
  • 19. Supervised Learning Flow Chart Raw Data Algorithm Sample Data Trained Product Verification Production
  • 20. Application  Bioinformatics  Database marketing  Handwriting recognition  Spam detection  Pattern Recognition  Speech Recognition
  • 21. Unsupervised Learning  No labels are given to the learning algorithm.  Find structure in its input with the help of Clustering.  Discover hidden patterns in data and find the suitable algorithm.  As input is unlabeled, there is no error or reward signal to evaluate a potential solution. This makes it different form others.  Self guided learning algorithm.  Plays important role in data mining methods to preprocess the data.  Approaches to Unsupervised Learning – K means, hierarchical clustering, mixture models.
  • 23. K- means / Hierarchical  K means is a method of vector quantization.  Partition of n observation into k cluster, and it belongs to nearest mean  Popular of clustering analysis in data mining.  NP Hard Problem.  Hierarchical clustering builds a hierarchy of clusters.  Agglomerative (Bottom Up Approach)  Divisive (Top down Approach)
  • 25. Difference Supervised Vs Unsupervised
  • 26. Reinforcement Learning  Program interacts with a dynamic environment.  No explicit instructions.  Decide its own whether it is near to goal or not.  “Approximate Dynamic Programming”  Unlike supervised learning correct input/output pairs are never presented.  No optimization step is there like supervised learning to tell we have reached up to our goal.  There is a focus on on-line performance.  Finds a balance between exploration (of uncharted territory) and exploitation (of current knowledge)
  • 27. Basic Reinforcement Learning Model  Set of environment states S.  Set of actions A.  Rules of transitions between states.  Rules that determine the scalar immediate reward of transition.  Rules that describe what the agent observes.
  • 28. Algorithms used for Reinforcement Learning  Criterion of optimality  the problem studied is episodic, an episode ending when some terminal state is reached.  Brute force (2 Step Policies)  For each possible policy, sample returns while following it.  Choose the policy with the largest expected return.  1.Value function estimation 2. Direct policy search  Value function approaches  It finds the policy which return maximize but maintaining sets.  Based on MKP(Markov Decision Parameters)
  • 29. Applications of Reinforcement Learning  Game theory  Control theory  Operations research  Information theory  Simulation-based optimization  Multi-agent systems  Swarm intelligence  Statistics  Genetic algorithms
  • 30. Semi-Supervised Learning  Semi-supervised learning is a class of supervised learning tasks.  But it uses large amount of unlabelled data with the labelled data.  Actually it falls between supervised learning and supervised learning.  Assumptions used in semi-supervised learning.  Smoothness assumption - Points which are close to each other are more likely to share a label.  Cluster assumption - The data tend to form discrete clusters, and points in the same cluster are more likely to share a label  Manifold assumption - The data lie approximately on a manifold of much lower dimension than the input space.
  • 31. How ML used in Hospitals
  • 32. Machine Learning Methods based on output of a machine-learned system
  • 33. Another Categorization  Based on “desired output” of a machine-learned system Classification Regression Clustering
  • 34. Classification  Predict class from observations.  Inputs are divided into two or more classes.  Model assigns unseen inputs to one (or multi-label classification) or more of these classes.  Spam filtering is an example of classification, where the inputs are email (or other) messages and the classes are "spam" and "not spam"
  • 35. Regression  Relation between mean value of one variable and corresponding value of another variable.  Statistical method to find the relation between different variables.  Predict the output with the training data and observations.  Popular method – Logistic Regression or binary regression.  The outputs are continuous rather than discrete.
  • 36. Clustering  Grouping a set of objects in such way that objects in the same group are similar to each other.  Objects are not predefined.  Grouping in meaningful group.  Unlike in classification, the groups are not known beforehand, making this typically an unsupervised task.  Example – Man’s shoes , woman’s shoes , man’s t-shirt, woman’s t-shirts.  So they are two category “man & woman” and “t-shirts & shoes”.
  • 37. Popular Framework / Tools  Weka  Carrot2  Gate  OpenNLP  LingPipe  Mallet – Topic Modelling  Gensim – Topic Modelling (Python)  Apache Mahout  Mlib – Apache Spark  Scikit learn – Python
  • 38. Difference Classification  Classification means to group the output into class.  Classification to predict the type of tumor i.e. harmful or not using the training data sets.  If it is discrete / categorical variable , then it is classification problem. Regression  Regression means to predict the output value using training data.  Regression to predict the price of the house from training data sets.  If it is real / continuous then it is regressions problem.
  • 40. Decision Tree Learning  Predictive model.  Maps observations about an item to conclusions about the item's target value.  Used in Statistics and data mining.  Tree models where the target variable can take a finite set of values are called classification trees.  Leaves represent class labels & branches represent conjunctions.  When target variable can take continuous values - regression trees.  In data mining, a decision tree describes data but not decisions.  Example – Wikipedia
  • 41. Artificial Neural Networks  Inspired by Biological Neural Networks(Central Nervous System of animal).  Used when there are large number of inputs and generally unknown.  ANNs are generally presented as systems of interconnected "neurons" which exchange messages between each other.  Used to solve computer vision, speech recognition and handwriting recognition.  Eg. In handwriting recognition  1. Input neuron activated by the pixels of an input image.  2. Weighted and transformed by a function, the activations of these neurons are then passed on to other neurons.  3. This process is repeated until finally, an output neuron is activated. This determines which character was read.
  • 43. Any Queries ? for more information :- machinecanthink.blogspot.in