machine learning

1
An Introduction to Machine Learning
2
Have you ever wondered?

• How Google classifies your mails as spam/non-spam?

3
Have you ever wondered? How Google translates
to more than 100 languages?
4
Have you ever wondered?

• How they are making Self Driving Cars?

5
Have you ever wondered?

• How Siri, Cortana etc. give you correct replies?

6
Have you ever wondered?

• How products are recommended on the shopping
  sites?

7
How are these all being possible?

• The answer is because of Machine learning

8
Problem statement

• Logic for the problems easily solvable by
  human beings cant be easily implemented because
• Working of Human Brains is not known to us.
• A generalized program covering many of the
  existing patterns in the problem domain can not
  be designed.
• The program will become highly complicated and is
  likely to miss many possible cases if we try to
  implement the logic.
• Many problems are difficult for humans to solve
  also because of their incapability in figuring
  out the patterns.
• we expect machines to solve those
  problems

9

• E.g
• To compute the probability that a credit card
  transaction is fraudulent.

10
Machine learning approach

• Instead of writing a program by hand for each
  specific task ,we collect lots of examples or
  experiences belonging to the problem.
• A machine learning algorithm takes all these
  examples and produces a set of numbers or actions
  that will be able to do the job.
• This set of numbers or actions is then applied on
  to the new examples to produce the correct
  outputs.

11
What is Machine Learning?

• Definition Machine learning is a branch of
  artificial intelligence which aims to create
  intelligent systems which do human like jobs by
  learning from a lot of relevant data.

12
Definition by Tom Mitchell

• A computer program is said to learn from
  experience E with respect to some class of tasks
  T and performance measures P, if its performance
  at tasks in T ,as measured by P, improves with
  experience E.

13
(No Transcript)
14
Types of Machine Learning

• Machine learning algorithm can be classified into
  3 types

15
1.Supervised learning
16
2.Unsupervised learning
17
3.Reinforcement learning
18
Machine Learning Applications

• 1) Image recognition
• 2) Speech recognition
• 3) Medical diagnosis
• 4) Agriculture, Physics
• 5) Email management, Robotics
• 6) Music
• 7) Mathematics
• 8) Natural Language Processing and many more.
•  

19

• Advantages
• 1. Easily identifies trends and patterns.
• 2. No human intervention needed (automation)
• 3. Continuous Improvement
• 4. Handling multi-dimensional and multi-variety
  data
• 5. Wide Applications.
• Disadvantages
• 1. Data Acquisition
• 2. Time and Resources
• 3. Interpretation of Results
• 4. High error-susceptibility.
•  
•  

20
Future scope

• 1. Automatic translation of ideas/briefs/thoughts
• 2. Traffic prediction at the highways/major roads
• 3. Web search and recommendation engines (Search
  engines)
• 4. Medical diagnosis (from past symptoms)
• 5. Spam filtering in emails
• 6. Recognition through images
• 7. Virtual personal assistants (either in the
  office or to the remote students who dont have
  access to education).

21
Conclusions

• Machine Learning Theory is both a
  fundamental theory with many basic and compelling
  foundational questions, and a topic of practical
  importance that helps to advance the state of the
  art in software by providing mathematical
  frameworks for designing new machine learning
  algorithms. It is an exciting time for the field,
  as connections to many other areas are being
  discovered and explored, and as new machine
  learning applications bring new questions to be
  modeled and studied. It is safe to say that the
  potential of Machine Learning and its theory lie
  beyond the frontiers of our imagination. 

22
References

• 1 Dropout a simple way to prevent neural
  network from overfitting, by Hinton, G.E.,
  Krizhevsky, A., Srivastava, N., Sutskever, I.,
  Salakhutdinov, R. (2014). Journal of Machine
  Learning Research, 15, 1929-1958. (cited 2084
  times, HIC 142 , CV 536).
• 2 Deep Residual Learning for Image Recognition,
  by He, K., Ren, S., Sun, J., Zhang, X. (2016).
  CoRR, abs/1512.03385. (cited 1436 times, HIC 137
  , CV 582).
• 3 Batch Normalization Accelerating Deep
  Network Training by Reducing Internal Covariate
  Shift , by Sergey Ioffe, Christian Szegedy (2015)
  ICML. (cited 946 times, HIC 56 , CV 0).
• 4 Large-Scale Video Classification with
  Convolutional Neural Network , by Fei-Fei, L.,
  Karpathy, A., Leung, T., Shetty, S., Sukthankar,
  R., Toderici, G. (2014). IEEE Conference on
  Computer Vision and Pattern Recognition (cited
  865 times, HIC 24 , CV 239).

23

• 11Alpaydin, E. (2004). Introduction to Machine
  Learning. Massachusetts, USA MIT Press.
• 12http//www.intechopen.com/books/new-advances-i
  n-machine-learning/types-of-machine-learning-algor
  ithms
• 13 Carling, A. (1992). Introducing Neural
  Networks. Wilmslow, UK Sigma Press
• 14 Friedberg, R. M. (1958). A learning machine
  Part, 1. IBM Journal, 2-13.
• 15Mitchell, T. M. (2006). The Discipline of
  Machine Learning. Machine Learning Department
  technical report CMU-ML-06-108, Carnegie Mellon
  University.
• 16 Richard S. Sutton, A. G. (1998).
  Reinforcement Learning. MIT Press.
• 17 Ripley, B. (1996). Pattern Recognition and
  Neural Networks. Cambridge University Press.

24

• 18 Tom, M. (1997). Machine Learning. Machine
  Learning, Tom Mitchell, McGraw Hill, 1997 McGraw
  Hill.
• 19 Nilsson, N. J. (1965) Learning machines New
  York McGraw-Hill Popper.
• 20 Rosenblatt, F. (1958) The perceptron a
  probabilistic model for information storage and
  organization in the brain Psychological Review.
• 21 Michalski, R S , Carhoncll, .J G ,
  Mitchcll, T. M. (1983) (Eds) Machine Learning, an
  Artificial Intelligence Approach Palo Alto, CA
  Tioga Press.
• 22 Anderson, J. A. (1983) Acquisition of proof
  skills in geometry.In R. S. Michalski, J. G.
  Carbonell T M Mitchell (Eds ), Machine
  Learnzng, An Artzficaal Intelligence Approach
  Palo Alto,

25
Thanks