This seminar gives an introduction to machine learning use-cases in real life. it talks about use of classification, regression and clustering with the help of use-cases that we see daily. it describes how neural networks and reinforcement learning can be leveraged in creating games
Digital Communication Essentials: DPCM, DM, and ADM .pptx
Machine learning
1.
2. CONTENTS
What is machine learning
Definition of ML
Conventional programming vs Machine
learning
Supervised Learning
Unsupervised Learning
Neural Networks
Reinforcement Learning
Conclusion
References
3.
4. Definition of machine learning
"A computer program is said to learn from experience E with
respect to some class of tasks T and performance measure P if
its performance at tasks in T, as measured by P, improves with
experience E.“
-Tom Mitchell
In more generalized form, Machine learning is the ability to
solve a problem without being explicitly programmed. machine
learning explores the study and construction of algorithms that
can learn from and make predictions on data
6. Types of Machine learning
Machine Learning
Supervised Unsupervised Reinforcement
(classification/
Regression)
( clustering ) Algorithms learn
to react to an
environment
7.
8. Supervised Learning
RegressionClassification
Supervised learning problems can be further grouped into
regression and classification problems.
Classification: A classification problem is when the output
variable is a category, such as “red” or “blue” or “disease” and “no
disease”.
Regression: A regression problem is when the output variable is a
real value, such as “dollars” or “weight”
9.
10. Have you noticed that Facebook has developed an uncanny ability to
recognize your friends in your photographs? In the old days, Facebook
used to make you to tag your friends in photos by clicking on them and
typing in their name. Now as soon as you upload a photo, Facebook tags
everyone for you like magic:
This technology is called face recognition. Face book's algorithms are
able to recognize your friends’ faces after they have been tagged only a
few times. It’s pretty amazing technology—Face book can recognize
faces with 98% accuracy which is pretty much as good as humans can do!
11.
12. But face recognition is really a series of several related problems:
First, look at a picture and find all the faces in it
Second, focus on each face and be able to understand that even
if a face is turned in a weird direction or in bad lighting, it is still
the same person.
Third, be able to pick out unique features of the face that you
can use to tell it apart from other people— like how big the eyes
are, how long the face is, etc.
Finally, compare the unique features of that face to all the
people you already know to determine the person’s name.
13.
14.
15.
16.
17.
18.
19. Face book makes use of our personal
information to understand in which things
we are more interested in and shows relavant
ads to us
Facebook uses a similar but separate ranking
algorithm to determine whether you’re likely
to be interested in a Page or business’ ads.
Facebook limits the number of ads you see,
and therefore wants to maximize the
likelihood that the ones it shows you will
resonate with you or get you to click, since
that’s how it earns more money.
The more Facebook knows about you, the
more relevant the ads will be.
20. Step 1 Step 2
Step 3
Label the new object as Red
star as most of the neighbors
belongs to class red star
21.
22.
23.
24.
25.
26.
27. The steps involved in reinforcement Learning are:
•Do some Action in the real word/environment
•If the result is positive, move to another action
•If result is negative, think upon and try to make it positive or avoid it
28.
29. Machine Learning is becoming an exciting
profession in computer science as well as in
Artificial Intelligence too. Because of IOT,
machines in this world are going to fill with
data. In such cases Machine Learning plays a
crucial role in analyzing data and finding
patterns in the data. Also Machine Learning is
used to give the AI Machines the ability to learn
from the experience.
30. 1. Baldi, P. and Brunak, S. (2002). Bioinformatics: A Machine Learning
Approach. Cambridge, MA: MIT Press.
This book offers a good coverage of machine learning approaches - especially
neural networks and hidden Markov models in bioinformatics.
2. Baldi, P., Frasconi, P., Smyth, P. (2003). Modeling the Internet and the
Web - Probabilistic Methods and Algorithms. New York: Wiley.
A good introduction to machine learning approaches to text mining and
related applications on the web.
3. Bishop, C. M. Neural Networks for Pattern Recognition. New York: Oxford
University Press (1995).
This book offers a good coverage of neural networks
Chakrabarti, S. (2003). Mining the Web, Morgan Kaufmann.
4. Cohen, P.R. (1995) Empirical Methods in Artificial Intelligence.
Cambridge, MA: MIT Press. This is an excellent reference on experiment
design, and hypothesis testing, and related topics that are essential for
empirical machine learning research.
5. Cowell, R.G., Dawid, A.P., Lauritzen, S.L., and Spiegelhalter,D.J. (1999).
Graphical Models and Expert Systems.Berlin: Springer.
This is a very good introduction to probabilistic graphical models