G.H.

RAISONI COLLEGE OF ENGINEERING

(AN AUTONOMOUS INSTITUTE UNDER UGC ACT 1956 & AFFILIATED TO RTM NAGPUR UNIVERSITY)

Machine Learning
INTRODUCTION
Definition: 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.

Areas of Influence for Machine Learning

Statistics: How best to use samples drawn from unknown probability distributions to help decide from which distribution some new sample is drawn? Brain Models: Non-linear elements with weighted inputs (Artificial Neural Networks) have been suggested as simple models of

Why is Machine Learning Important?

Some tasks cannot be defined well, except by
examples (e.g., recognizing people). Relationships and correlations can be hidden within large amounts of data. Machine Learning/Data Mining may be able to find these relationships. Human designers often produce machines that do not work as well as desired in the environments in which they are used.

Face Detection
1. 2. 3. 4.

Image pyramid used to locate faces of different sizes Image lighting compensation Neural Network detects rotation of face candidate Final face candidate de-rotated ready for detection

Successful Applications of Machine Learning

1. Learning to recognize spoken words (Lee, 1989; Waibel, 1989). 2. Learning to drive an autonomous vehicle (Pomerleau, 1989).

5.

biological neurons. Adaptive Control Theory: How to deal with controlling a process having unknown parameters that must be estimated during operation? Psychology: How to model human performance on various learning tasks? Artificial Intelligence: How to write algorithms to acquire the knowledge

Case Study: Artificial Neural Network

Takes N inputs Calculates the weight each input has on final decision Neuron outputs a 1 if the decision is true, 0 if it is false Groups of neurons make up an artificial neural network

6.

Submit image to Neural Network a. Break image into segments b. Each segment is a unique input to the network c. Each segment looks for certain patterns (eyes, mouth, etc) Output is likelihood of a face

Current Uses of ML
DivX Face detection POV-Ray Neural Net learns memory accesses Ancestry.com Uses Optical Character Recognition to digitize newspapers Deep Blue Junior Less powerful than Deep Blue, but smarter because of Neural Networks

3. Learning to classify new humans are able to acquire, at least, as well astronomical structures (Fayyad et al., 1995). 4. as humans? Evolutionary Models: How to model certain

Learning to play world- aspects of biological evolution to improve class backgammon (Tesauro 1992, 1995).
Poster Design & Printing by Genigraphics 800.790.4001

SUBMITTED BY
NISHANT PANDEY MTECH-FIRST SEM ETRX

the performance of computer programs?