Title: CS621: Artificial Intelligence Lecture 27: Backpropagation applied to recognition problems; start of logic
1CS621 Artificial IntelligenceLecture 27
Backpropagation applied to recognition problems
start of logic
- Pushpak Bhattacharyya
- Computer Science and Engineering Department
- IIT Bombay
2Backpropagation algorithm
Output layer (m o/p neurons)
.
j
wji
.
i
Hidden layers
.
.
Input layer (n i/p neurons)
- Fully connected feed forward network
- Pure FF network (no jumping of connections over
layers)
3General Backpropagation Rule
- General weight updating rule
- Where
for outermost layer
for hidden layers
4Local Minima
- Due to the Greedy nature of BP, it can get stuck
in local minimum m and will never be able to
reach the global minimum g as the error can only
decrease by weight change.
5Momentum factor
- Introduce momentum factor.
- Accelerates the movement out of the trough.
- Dampens oscillation inside the trough.
- Choosing ß If ß is large, we may jump over
the minimum.
6Symmetry breaking
- If mapping demands different weights, but we
start with the same weights everywhere, then BP
will never converge.
XOR n/w if we s started with identical weight
everywhere, BP will not converge
7Backpropagation Applications
8Feed Forward Network Architecture
Problem defined
O/P layer
Decided by trial error
Hidden layer
Problem defined
I/P layer
9Digit Recognition Problem
- Digit recognition
- 7 segment display
- Segment being on/off defines a digit
2
1
3
7
6
4
5
109O 8O 7O . . . 2O 1O
Full connection
Hidden layer
Full connection
7O 6O 5O . . . 2O
1O Seg-7 Seg-6 Seg-5
Seg-2 Seg-1
11Example - Character Recognition
- Output layer 26 neurons (all capital)
- First output neuron has the responsibility of
detecting all forms of A - Centralized representation of outputs
- In distributed representations, all output
neurons participate in output
12An application in Medical Domain
13Expert System for Skin Diseases Diagnosis
- Bumpiness and scaliness of skin
- Mostly for symptom gathering and for developing
diagnosis skills - Not replacing doctors diagnosis
14Architecture of the FF NN
- 96-20-10
- 96 input neurons, 20 hidden layer neurons, 10
output neurons - Inputs skin disease symptoms and their
parameters - Location, distribution, shape, arrangement,
pattern, number of lesions, presence of an active
norder, amount of scale, elevation of papuls,
color, altered pigmentation, itching, pustules,
lymphadenopathy, palmer thickening, results of
microscopic examination, presence of herald
pathc, result of dermatology test called KOH
15Output
- 10 neurons indicative of the diseases
- psoriasis, pityriasis rubra pilaris, lichen
planus, pityriasis rosea, tinea versicolor,
dermatophytosis, cutaneous T-cell lymphoma,
secondery syphilis, chronic contact dermatitis,
soberrheic dermatitis
16Training data
- Input specs of 10 model diseases from 250
patients - 0.5 is some specific symptom value is not knoiwn
- Trained using standard error backpropagation
algorithm
17Testing
- Previously unused symptom and disease data of 99
patients - Result
- Correct diagnosis achieved for 70 of
papulosquamous group skin diseases - Success rate above 80 for the remaining diseases
except for psoriasis - psoriasis diagnosed correctly only in 30 of the
cases - Psoriasis resembles other diseases within the
papulosquamous group of diseases, and is somewhat
difficult even for specialists to recognise.
18Explanation capability
- Rule based systems reveal the explicit path of
reasoning through the textual statements - Connectionist expert systems reach conclusions
through complex, non linear and simultaneous
interaction of many units - Analysing the effect of a single input or a
single group of inputs would be difficult and
would yield incor6rect results
19Explanation contd.
- The hidden layer re-represents the data
- Outputs of hidden neurons are neither symtoms nor
decisions
20(No Transcript)
21Discussion
- Symptoms and parameters contributing to the
diagnosis found from the n/w - Standard deviation, mean and other tests of
significance used to arrive at the importance of
contributing parameters - The n/w acts as apprentice to the expert
22Exercise
- Find the weakest condition for symmetry breaking.
It is not the case that only when ALL weights are
equal, the network faces the symmetry problem.
23Logic
24Logic and inferencing
Vision
NLP
- Search
- Reasoning
- Learning
- Knowledge
Expert Systems
Robotics
Planning
Obtaining implication of given facts and rules --
Hallmark of intelligence
25- Inferencing through
- Deduction (General to specific)
- Induction (Specific to General)
- Abduction (Conclusion to hypothesis in absence of
any other evidence to contrary)
Deduction Given All men are mortal
(rule) Shakespeare is a man (fact) To
prove Shakespeare is mortal (inference)
Induction Given Shakespeare is mortal
Newton is mortal (Observation) Dijkst
ra is mortal To prove All men are mortal
(Generalization)
26If there is rain, then there will be no
picnic Fact1 There was rain Conclude There was
no picnic
Deduction
Fact2 There was no picnic Conclude There was no
rain (?)
Induction and abduction are fallible forms of
reasoning. Their conclusions are susceptible to
retraction
Two systems of logic 1) Propositional
calculus 2) Predicate calculus
27- Propositions
- Stand for facts/assertions
- Declarative statements
- As opposed to interrogative statements
(questions) or imperative statements (request,
order) - Operators
- gt and form a minimal set (can express other
operations) - - Prove it.
- Tautologies are formulae whose truth value is
always T, whatever the assignment is
28- Model
- In propositional calculus any formula with n
propositions has 2n models (assignments) - - Tautologies evaluate to T in all models.
- Examples
- 1)
- 2)
- e Morgan with AND
29Semantic Tree/Tableau method of proving tautology
Start with the negation of the formula
- a - formula
a-formula
ß-formula
- ß - formula
a-formula
- a - formula
30Example 2
X
(a - formula)
(a - formulae)
a-formula
(ß - formulae)
B
C
B
C
Contradictions in all paths
31A puzzle(Zohar Manna, Mathematical Theory of
Computation, 1974)
- From Propositional Calculus
32Tourist in a country of truth-sayers and liers
- Facts and Rules In a certain country, people
either always speak the truth or always lie. A
tourist T comes to a junction in the country and
finds an inhabitant S of the country standing
there. One of the roads at the junction leads to
the capital of the country and the other does
not. S can be asked only yes/no questions. - Question What single yes/no question can T ask
of S, so that the direction of the capital is
revealed?
33Diagrammatic representation
Capital
S (either always says the truth Or always lies)
T (tourist)
34Deciding the Propositions a very difficult step-
needs human intelligence
- P Left road leads to capital
- Q S always speaks the truth
35Meta Question What question should the tourist
ask
- The form of the question
- Very difficult needs human intelligence
- The tourist should ask
- Is R true?
- The answer is yes if and only if the left road
leads to the capital - The structure of R to be found as a function of P
and Q
36A more mechanical part use of truth table
P Q Ss Answer R
T T Yes T
T F Yes F
F T No F
F F No T
37Get form of R quite mechanical
- From the truth table
- R is of the form (P x-nor Q) or (P Q)
38Get R in English/Hindi/Hebrew
- Natural Language Generation non-trivial
- The question the tourist will ask is
- Is it true that the left road leads to the
capital if and only if you speak the truth? - Exercise A more well known form of this question
asked by the tourist uses the X-OR operator
instead of the X-Nor. What changes do you have to
incorporate to the solution, to get that answer?