A.I.
TECHNIQUES IMPLEMENTATION
Fuzzy logic
Advantages of fuzzy logic
Considerable skill for little investment
Fuzzy logic systems piggy bank on human analysis
Humans encode rules after intelligent analysis of lots of data Verbal rules generated by humans are robust
Simple to create
Not much need for data or ground truth Logic tends to be easy to program
Fuzzy rules are human understandable
Where not to use fuzzy logic
Do not use fuzzy logic if:
Humans do not understand the system Knowledge can not be expressed with verbal rules
A fuzzy logic system is limited
Piece-wise linear approximation to a system Non-linear systems can not be approximated
Many environment applications are non-linear
Neural Networks
Stock Market Prediction Fraud Detection Sales Forecasting Targeted Marketing
Advantages of neural networks
Can approximate any smooth function Can yield true probabilities Not hard to train Fast in operations
Training is slow, but once trained, the network can calculate the output for a set of inputs quite fast
Easy to implement
Just a sum of exponential functions
Disadvantages of neural networks
A black box
The final set of weights yields no insights Magnitude of weights doesnt mean much
Measure of skill needs to be differentiable
for example Can not use Probability of Detection
Training set has to be complete
Unpredictable output on data unlike training Need lots of data Need expert willing to do lot of truthing
Genetic Algorithm
Advantages of genetic algorithms
Near-optimal parameters for given model
Human-understandable rules Best parameters for them
Cost function need not be differentiable
The process of training uses natural selection, not gradient descent
Requires less data than a neural network
Search space is more limited
Disadvantages of genetic algorithms
Highly dependent on class of functions
If poor model is chosen, poor results
Optimization may not help at all
Known model does not always lead to better understanding
Magnitude of weights, etc. may not be meaningful if inputs are correlated Problem may have multiple parametric solutions
Decision tree
Disadvantages Piece-wise linear, so typically less skilled than neural networks Large decision trees are effectively a blackbox Can not do regression, only classification Advantages: Fast to train New advances: bagged, boosted decision trees approach skill of neural networks, but are no longer fast to train
Which AI technique?
Do you have expert knowledge? Create fuzzy logic rules from experts reasoning. Do you already know the model? A power-law relationship? Gaussian? Quadratic? Rules? : use genetic algorithms For classification Neural Networks
Types of data
Observed/primary data Simulated data
Typical data-driven application
Observed data Signal/image processing;sampling Features
normalize/create chromosome/ determine confidences
FzLogic/GenAlg/NN/DecTree f()
Platt method/region-average/threshold
A data-driven application in run-time
Result
APPLICATIONS OF A.I.
Expert systems. Natural Language Processing (NLP).
Speech recognition.
Computer vision.
Robotics.
Automatic Programming.
FUTURE
The day is not far when you will just sit back in your cozy little beds and just command your personal Robot's to entirely do your ruts . He will be a perfect companion for you. Just enjoy the Technology.
FUTURE
But wait, dont be happy. It may end in other way too. Some day there will be a knock to your door. As you open it, you see a large number of Robots marching into your house destroying everything you own and looting you. This is because ever since there is an advantage in the Technology, it attracts anti-social elements. This is true for Robots too. Because now they will have full power to think as human, even as of anti-social elements. So think trice before giving them power of Cognition.
CONCLUSION
In its short existence, AI has increased understanding of the nature of intelligence and provided an impressive array of application in a wide range of areas. It has sharpened understanding of human reasoning, and of the nature of intelligence in general. At the same time, it has revealed the complexity of modeling human reasoning providing new areas and rich challenges for the future.
THANK YOU
PRESENTED BY KARAN NAINA SUMIT
