2. INSIGHTS
• Introduction
• Neural Network
• Pattern Recognition
• Examples of Pattern
• Application Examples
• Approaches
• Components of a Pattern Recognition System
3. Contd…
• Bayesian Decision Making
• Recent Advances in Neural Networks
• Conclusion
• Neural Networks in Future
• References
4. INTRODUCTION
• As the name suggests, neural networks are inspired by the
brain.
• “Neural“ is an adjective for neuron, and “network” denotes
a graph like structure.
5. •An artificial neuron is a device
with many inputs and one output.
•The neuron has two modes of
operation;
•the training mode and
•the using mode
Contd…
7. HISTORICAL BACKGROUND
• Neural network simulations appear to be a recent development.
However, this field was established before the advent of
computers, and has survived at least one major setback and
several eras.
• The first artificial neuron was produced in 1943 by the
neurophysiologist Warren McCulloch and the logician Walter
Pits.
8. PATTERN RECOGNITION
•An important application of neural networks is pattern recognition. Pattern
recognition can be implemented by using a feed-forward neural network that
has been trained accordingly.
•During training, the network is trained to associate outputs with input patterns.
•When the network is used, it identifies the input pattern and tries to output the
associated output pattern.
•The power of neural networks comes to life when a pattern that has no output
associated with it, is given as an input.
In this case, the network gives the output that corresponds to a taught input
pattern that is least different from the given pattern.
24. PATTERN RECOGNITION SYSTEM
Sensing
The input to a pattern recognition system is often some kind of a
transducer, such as a camera or a microphone array. The difficulty
of the problem may well depend on the characteristics and
limitations of the transducer- its bandwidth, resolution, sensitivity,
distortion, signal-to-noise ratio, latency, etc
25. Segmentation
• In practice, the fish would often be overlapping, and our system
would have to determine where one fish ends and the next
begins-the individual patterns have to be segmented.
• We need a way to know when we have switched from one
model to another, or to know when we just have background or
no category.
26.
27. Post Processing
A classifier rarely exists in a vacuum. Instead, it is
generally to be used to recommend actions (put this fish
in this bucket, put that fish in that bucket), each action
having an associated cost. The post-processor uses the
output of the classifier to decide on the recommended
action.
31. Contd…
• The Bayesian decision making is a fundamental statistical
approach which allows to design the optimal classifier if
complete statistical model is known.
• Task: to design decision rule q which minimizes Bayesian risk
• R(q) =∑∑p(x, y)W(q(x), y)
• y∈ ∈Y x X
Definition: Obsevations
Hidden states
Decisions
X
Y
D
A loss function
A decision rule
A joint probability
32. RECENT ADVANCES IN NEURAL
NETWORKS
• Interactive Voice Response (IVR) with pattern recognition based on
Neural Networks
• The addition of voice pattern recognition in the authentication
process can potentially further enhance the security level.
• The developed system is fully compliant with landline phone
system. The results are promising based on false accept and false
reject criteria offering quick response time.
• It can potentially play an effective role in the existing authentication
techniques used for identity verification to access secured services
through telephone or similar media.
33. Predicting Student Performance Using Artificial Neural
Network: in the Faculty of Engineering and Information
Technology (2015)
• A number of factors that may possibly influence the performance of
a student were outlined. Such factors as high school score, score of
subject such as Math I, Math II, Electrical Circuit I, and Electronics
I taken during the student freshman year, number of credits passed,
student cumulative grade point average of freshman year, types of
high school attended and gender, among others, were then used as
input variables for the ANN model.
34. IN BUSINESS LEXICON, ARTIFICIAL
INTELLIGENCE(AI) TOUCHED AN UNPRECEDENTED
HIGH
• AI started picking up in 2015 and saw a
remarkable spike from the latter half of 2016,
which continued into 2017. Insights said AI was
mentioned 791 times in just the third quarter of
2017.
• The same report showed how the AI system at the
Icahn School of Medicine at Mt. Sinai, New York,
called Deep Patient, has analyzed electronic
health records from 700,000 patients. Deep
Patient, it said, taught itself to predict risk factors
for 78 different diseases – and doctors now turn to
the system to aid in diagnoses.
35. Contd…
• IBM’s AI-based platform Watson offers over 25 different services including knowledge
validation, voice synthesis, language modeling and visual analysis.
• A recent Infosys report said enterprises are moving beyond the experimentation phase with AI,
and are deploying AI technologies more broadly and realizing benefits across their business.
• The report, Leadership in the Age of AI, surveyed more than 1,000 business and IT leaders
with decision-making power over AI solutions or purchases at large organizations across seven
countries.
• The survey found 73% of respondents agreeing or strongly agreeing that their AI deployments
have already transformed the way they do business, and 90% of C-level executives reporting
measurable benefits from AI within their organization.
37. CONCLUSION
• In its broadest sense pattern recognition is the heart of all scientific
inquiry, including understanding ourselves and the real-world
around us.
• And the developing of pattern recognition is increasing very fast,
the related fields and the application of pattern recognition became
wider and wider.
• In addition, it is an important trend to use pattern recognition on
engineering; we should make efforts on this.
• And pattern recognition scientists should pay attention to new
technique of PR, and enlarge the application areas of PR.
38. IN FUTURE…
• Robots that can see, feel, and predict the world around them
• Improved stock prediction
• Common usage of self-driving cars
• Composition of music
• Handwritten documents to be automatically transformed into
formatted word processing documents
• Trends found in the human genome to aid in the understanding of
the data compiled by the Human Genome Project
• Self-diagnosis of medical problems using neural networks
• And much more!
39. REFERENCES
[1] Snapp R., CS 295: Pattern Recognition, Course Notes, Department of
Computer Science, University of Vermont,
(http://www.cs.uvm.edu/~snapp/teaching/CS295PR/whatispr.html)
[2] Duda, R.O., Hart, P.E., and Stork D.G., (2001). Pattern Classification. (2nd
ed.). New York: Wiley-Interscience Publication.
[3] Gutierrez-Osuna R., Intelligent Sensor Systems, Course Notes,
Department of Computer Science, Wright State University,
(http://research.cs.tamu.edu/prism/lectures/iss/iss_l9.pdf)
[4] Olszewski R. T. (2001) Generalized Feature Extraction for Structural
Pattern Recognition in TimeSeries Data, PhD. Thesis at School of
Computer Science, Carnegie Mellon University, Pittsburgh.