How do exactly machines learn?

Author Topic: How do exactly machines learn?  (Read 2244 times)

Offline motiur.swe

  • Jr. Member
  • **
  • Posts: 72
  • Teamwork Begins By Building Trust.
    • View Profile
How do exactly machines learn?
« on: July 28, 2018, 11:33:10 AM »
The process flow depicted here represents how machine learning works:


There are two popular methods of machine learning named supervised learning and unsupervised learning. It is estimated that about 70 percent of machine learning is supervised learning, while unsupervised learning ranges from 10 – 20 percent. Other methods that are less-often used are semi-supervised and reinforcement learning.

Supervised Learning

This kind of learning is possible when inputs and the outputs are clearly identified, and algorithms are trained using labeled examples. To understand this better, let’s consider the following example: an equipment could have data points labeled F (failed) or R (runs).


The learning algorithm using supervised learning would receive a set of inputs along with the corresponding correct output to find errors. Based on these inputs, it would further modify the model accordingly. This is a form of pattern recognition, as supervised learning happens through methods like classification, regression, prediction, and gradient boosting. Supervised learning uses patterns to predict the values of the label on additional unlabeled data.

Supervised learning is more commonly used in applications where historical data predict future events, such as fraudulent credit card transactions.


Unsupervised Learning

Unsupervised learning, unlike supervised learning, is used with data sets without historical data. An unsupervised learning algorithm explores surpassed data to find the structure. This kind of learning works best for transactional data; for instance, it helps in identifying customer segments and clusters with certain attributes—this is often used in content personalization.


Popular techniques where unsupervised learning is used also include self-organizing maps, nearest neighbor mappig, singular value decomposition, and k-means clustering. Basically, online recommendations, identification of data outliers, and segment text topics are all examples of unsupervised learning.


Semi-Supervised Learning

As the name suggests, semi-supervised learning is a bit of both supervised and unsupervised learning and uses both labeled and unlabeled data for training. In a typical scenario, the algorithm would use a small amount of labeled data with a large amount of unlabeled data.


This type of learning can again be used with methods such as classification, regression, and prediction. Examples of semi-supervised learning would be face and voice recognition techniques.


Reinforcement Learning

This is a bit similar to the traditional type of data analysis; the algorithm discovers through trial and error and decides which action results in greater rewards. Three major components can be identified in reinforcement learning functionality: the agent, the environment, and the actions. The agent is the learner or decision-maker, the environment includes everything that the agent interacts with, and the actions are what the agent can do.


Reinforcement learning occurs when the agent chooses actions that maximize the expected reward over a given time. This is best achieved when the agent has a good policy to follow.


Some Machine Learning Algorithms And Processes

If you’re studying machine learning, you should familiarize yourself with these common machine learning algorithms and processes: neural networks, decision trees, random forests, associations and sequence discovery, gradient boosting and bagging, support vector machines, self-organizing maps, k-means clustering, Bayesian networks, Gaussian mixture models, and more.

Other tools and processes that pair up with the best algorithms to aid in deriving the most value from big data include:

   
  • Comprehensive data quality and management
  • GUIs for building models and process flows
  • Interactive data exploration and visualization of model results
  • Comparisons of different machine learning models to quickly identify the best one
  • Automated ensemble model evaluation to identify the best performers
  • Easy model deployment so you can get repeatable, reliable results quickly
  • Integrated end-to-end platform for the automation of the data-to-decision process


Source: simplilearn
Sheikh Shah Mohammad Motiur Rahman
Lecturer (Senior Scale), Department of Software Engineering
Daffodil International University
+8801718 297606
motiur.swe@diu.edu.bd
http://faculty.daffodilvarsity.edu.bd/profile/swe/motiur.html

Offline iftekhar.swe

  • Full Member
  • ***
  • Posts: 144
  • মানুষ তার স্বপ্নের সমান বড়
    • View Profile
    • DIU_SWE Faculty
Re: How do exactly machines learn?
« Reply #1 on: September 06, 2018, 01:39:45 PM »
This is amazing...
_________________________
MD. IFTEKHAR ALAM EFAT
Sr. Lecturer
Department of Software Engineering, FSIT
Daffodil International Univeristy

Offline motiur.swe

  • Jr. Member
  • **
  • Posts: 72
  • Teamwork Begins By Building Trust.
    • View Profile
Re: How do exactly machines learn?
« Reply #2 on: September 08, 2018, 11:18:19 AM »
Thanks  :)
Sheikh Shah Mohammad Motiur Rahman
Lecturer (Senior Scale), Department of Software Engineering
Daffodil International University
+8801718 297606
motiur.swe@diu.edu.bd
http://faculty.daffodilvarsity.edu.bd/profile/swe/motiur.html

Offline Abdus Sattar

  • Sr. Member
  • ****
  • Posts: 483
  • Only the brave teach.
    • View Profile
    • https://sites.google.com/diu.edu.bd/abdussattar/
Re: How do exactly machines learn?
« Reply #3 on: September 08, 2018, 11:45:10 AM »
Good Post.
Abdus Sattar
Assistant Professor
Department of CSE
Daffodil International University(DIU)
Mobile: 01818392800
Email: abdus.cse@diu.edu.bd
Personal Site: https://sites.google.com/diu.edu.bd/abdussattar/
Google Scholar: https://scholar.google.com/citations?user=DL9nSW4AAAAJ&hl=en

Offline afsana.swe

  • Full Member
  • ***
  • Posts: 241
  • Think Positive
    • View Profile
    • DIU profile
Re: How do exactly machines learn?
« Reply #4 on: October 18, 2018, 02:33:39 PM »
I am also interested to learn more. Could you please share some more info please ?
Afsana Begum,
Lecturer (Senior Scale),
Member of Exam Committee and
Convenor of DIU-ISG, Bangladesh,
Software Engineering Department,
Daffodil International University, Dhaka

Offline farzanaSadia

  • Full Member
  • ***
  • Posts: 127
  • Test
    • View Profile
Re: How do exactly machines learn?
« Reply #5 on: October 28, 2018, 07:49:36 PM »
What kind of learning does Facebook use to recognize image?
:)

Offline motiur.swe

  • Jr. Member
  • **
  • Posts: 72
  • Teamwork Begins By Building Trust.
    • View Profile
Re: How do exactly machines learn?
« Reply #6 on: October 29, 2018, 10:02:38 AM »
What kind of learning does Facebook use to recognize image?

Madam,
I exactly don't know about facebook object recognition techniques but if you want to know more about facebook AI the you can check the facebook research group or facebook newsroom to get the exact answer.

https://research.fb.com
https://newsroom.fb.com
Sheikh Shah Mohammad Motiur Rahman
Lecturer (Senior Scale), Department of Software Engineering
Daffodil International University
+8801718 297606
motiur.swe@diu.edu.bd
http://faculty.daffodilvarsity.edu.bd/profile/swe/motiur.html

Offline Fahad Zamal

  • Full Member
  • ***
  • Posts: 115
    • View Profile
Re: How do exactly machines learn?
« Reply #7 on: November 15, 2018, 12:42:06 AM »
Good to know. Very well written article.

Offline akhi

  • Sr. Member
  • ****
  • Posts: 360
  • Life is beautiful
    • View Profile
    • http://faculty.daffodilvarsity.edu.bd/profile/cse/amatul.html
Re: How do exactly machines learn?
« Reply #8 on: November 15, 2018, 12:45:14 AM »
informative
Amatul Bushra Akhi
Employee ID: 710001668
Lecturer
Room No: 704 AB-01
Department of Computer Science and Engineering
Permanent Campus
Daffodil International University

Offline Tapushe Rabaya Toma

  • Full Member
  • ***
  • Posts: 191
    • View Profile
    • University Webpage
Re: How do exactly machines learn?
« Reply #9 on: January 13, 2019, 01:23:49 PM »
Useful Information. Thanks for sharing. I want to work in this field and learn more. Could you please help me?

Offline s.arman

  • Sr. Member
  • ****
  • Posts: 260
  • Test
    • View Profile
Re: How do exactly machines learn?
« Reply #10 on: January 17, 2019, 07:57:53 PM »
good one sir

Offline motiur.swe

  • Jr. Member
  • **
  • Posts: 72
  • Teamwork Begins By Building Trust.
    • View Profile
Re: How do exactly machines learn?
« Reply #11 on: February 25, 2019, 04:57:59 PM »
Useful Information. Thanks for sharing. I want to work in this field and learn more. Could you please help me?

Sure and thanks for interest.
Sheikh Shah Mohammad Motiur Rahman
Lecturer (Senior Scale), Department of Software Engineering
Daffodil International University
+8801718 297606
motiur.swe@diu.edu.bd
http://faculty.daffodilvarsity.edu.bd/profile/swe/motiur.html

Offline motiur.swe

  • Jr. Member
  • **
  • Posts: 72
  • Teamwork Begins By Building Trust.
    • View Profile
Re: How do exactly machines learn?
« Reply #12 on: February 25, 2019, 04:58:36 PM »
Sheikh Shah Mohammad Motiur Rahman
Lecturer (Senior Scale), Department of Software Engineering
Daffodil International University
+8801718 297606
motiur.swe@diu.edu.bd
http://faculty.daffodilvarsity.edu.bd/profile/swe/motiur.html

Offline SSH Shamma

  • Sr. Member
  • ****
  • Posts: 364
    • View Profile
Syeda Sumbul Hossain
Lecturer, SWE
Daffodil International University
Contact No. 01918455555