SlideShare a Scribd company logo
ERI SUMMER TRAINING
COMPUTERS & SYSTEMS DEPT.
Dr. Randa ElanwarLecture 3
Content
Non linear problems
Learning Methods
Supervised learning
Unsupervised learning
2
ERI Summer training (C&S) Dr. Randa Elanwar
Unsupervised learning
Reinforcement learning
Non linear problems
3
So far we understood that NN can handle problems
with
feature vectors > 2 (i.e. hyper feature space)
multiple classes >= 2multiple classes >= 2
linear problems (linearly separable)
Sometimes, the problem nature or the features
taken in the feature space cannot be solved using
first degree polynomial like this example.
ERI Summer training (C&S) Dr. Randa Elanwar
Non linear problems
Assume a shoes factory is packing the shoes pairs of certain
size on a moving belt, the machine should check that the
pairs are not alike. The factory labels left shoe as "0" and
right shoe as "1".
The factory needs a solution that checks labels and
4
ERI Summer training (C&S) Dr. Randa Elanwar
The factory needs a solution that checks labels and
whenever it find similar pair stops the moving belt to
prevent packing it.
So we want to implement a NN to act as logical XOR
function .. In other words whenever the input is '00' or "11"
the output is '0' and belt stops, otherwise the output is '1'
and belt keeps moving.
Non linear problems
5
XOR problem
No single line can ever separate the samples correctly.
The only way to separate the positive from negative
examples is to draw 2 lines (i.e., we need 2 straight line
equations) or draw a nonlinear region to capture one
type only
ERI Summer training (C&S) Dr. Randa Elanwar
Non linear problems
To implement the nonlinearity we need to insert one or
more extra layer of nodes between the input layer and
the output layer (Hidden layer)
6
ERI Summer training (C&S) Dr. Randa Elanwar
Non linear problems
7
The nonlinearity can help re-shape the straight line
decision boundary into higher order polynomial that can
successfully separates each class samples
ERI Summer training (C&S) Dr. Randa Elanwar
Non linear problems
The higher the polynomial order, the more over fitting we get.
But here we have to answer 2 questions:
8
ERI Summer training (C&S) Dr. Randa Elanwar
Why are the samples interfering in the feature space?
How far should we pursue raising the order of the
decision boundary (adding hidden layers to the network)?
Non linear problems
9
Well! first you will notice that discriminative features
are rare and have a limit.
Real samples usually have similarities that cause
classes interference/overlap within any featureclasses interference/overlap within any feature
space.
Moreover, some features may be dependent on
other features used and not distinct. This
dependency usually allows more interference.
ERI Summer training (C&S) Dr. Randa Elanwar
Non linear problems
Some times the number of features used is insufficient to
distinctly separate the samples in the feature space.
Increasing the number of distinct features help widen
the space between each class samples.
10
ERI Summer training (C&S) Dr. Randa Elanwar
the space between each class samples.
However, increasing the number of features more than
needed introduce noise in the form of irrelevant
features, which doesn't lead to the separation as well
as it leads to the system complexity (remember that the
number of nodes in the NN input layer is equal to the
number of features used).
Non linear problems
11
Using a feed forward network to solve the overlapping
problem will not help, because the delta rule works only If a
set of <input, output> pairs are learnable (representable),
the delta rule will find the necessary weights:
in a finite number of steps
independent of initial weightsindependent of initial weights
In case of interfering samples in the feature space the delta
rue will run in an infinite loop because the error will never
diminish to zero, i.e. the sample pairs are not learnable. The
only solution we need is a hyperbola (non linear decision
boundary).
ERI Summer training (C&S) Dr. Randa Elanwar
Non linear problems
This solution is offered in either of 2 ways:
1. Adding hidden layers (use Multiple Layer Perceptron
MLP NN) to add non linearity to the decision
boundary to some acceptable limit.
12
ERI Summer training (C&S) Dr. Randa Elanwar
2. Make sample transformation by kernels, in other
words, multiply the feature vector of the
patterns/samples by a set of orthogonal functions to
re-locate them in space in a way that can make the
linear solution possible (use Radial Basis Functions RBF
NN)
Non linear problems
13
The learning of MLP and RBF depends on another
method than the delta rule, called the back
propagation algorithm. This algorithms also depends on
minimizing the error function of misclassified patterns. It
has a long derivation that we will not discuss it now,has a long derivation that we will not discuss it now,
may be later.
But to imagine how things work
Back propagation tries to transform training patterns to
make them almost linearly separable and use linear
network
ERI Summer training (C&S) Dr. Randa Elanwar
Non linear problems
In other words, if we need more than 1 straight
line to separate +ve and –ve patterns, we solve
the problem in two phases:
In phase 1: we first represent each straight line with a
14
ERI Summer training (C&S) Dr. Randa Elanwar
In phase 1: we first represent each straight line with a
single perceptron and classify the training patterns
(output)
In phase 2: these outputs are then transformed to new
patterns which are now linearly separable and can be
classified by an additional perceptron giving the final
result.
Learning Methods
15
Learning/Training is The process of modifying
the weights in the connections between network
layers with the objective of achieving the
expected output.
This is achieved through
Supervised learning
Unsupervised learning
Reinforcement learning
ERI Summer training (C&S) Dr. Randa Elanwar
Supervised learning
Each input vector requires a corresponding
target vector. Training pair=[input vector,
target vector]
16
ERI Summer training (C&S) Dr. Randa Elanwar
Supervised learning
17
During learning, produced output is compared
with the desired output
The difference between both output is used to modify
learning weights according to the learning algorithm
Learning cases: pattern recognition problems.
Neural Network models using supervised learning:
ML Perceptron, feed-forward, radial basis
function, support vector machine.
ERI Summer training (C&S) Dr. Randa Elanwar
Unsupervised learning
18
All similar input patterns are grouped together as
clusters. If a matching input pattern is not found a
new cluster is formed
In unsupervised learning there is no error feedback
because targets are not provided
ERI Summer training (C&S) Dr. Randa Elanwar
Unsupervised learning
Network must discover patterns, regularities, features
for the input data over the output. This process is called
self-organizing
Learning cases: Appropriate for clustering task like:
19
ERI Summer training (C&S) Dr. Randa Elanwar
Learning cases: Appropriate for clustering task like:
Find similar groups of documents in the web, content
addressable memory, clustering.
Neural Network models using unsupervised learning:
Kohonen, self organizing maps, Hopfield networks.
Reinforcement learning
Target is provided, but the desired output is absent.
I.e. unlike unsupervised learning, there is a given
feedback but it is in the form of "Good /bad",
"Greater/less", etc. No exact value for the desired
output or the class membership.
20
ERI Summer training (C&S) Dr. Randa Elanwar
output or the class membership.
The net is only provided with guidance to determine
the produced output is acceptable or not.
Reinforcement learning
21
Weights are modified in the units that have errors
ERI Summer training (C&S) Dr. Randa Elanwar
Reinforcement learning
When Reinforcement learning is used?
If less information is available about the target output
values (critic information)
Feedback in this case is only evaluative and not
22
ERI Summer training (C&S) Dr. Randa Elanwar
instructive

More Related Content

Viewers also liked

What is pattern recognition (lecture 6 of 6)
What is pattern recognition (lecture 6 of 6)What is pattern recognition (lecture 6 of 6)
What is pattern recognition (lecture 6 of 6)
Randa Elanwar
 
What is pattern_recognition (lecture 2 of 6)
What is pattern_recognition (lecture 2 of 6)What is pattern_recognition (lecture 2 of 6)
What is pattern_recognition (lecture 2 of 6)
Randa Elanwar
 
Introduction to Neural networks (under graduate course) Lecture 9 of 9
Introduction to Neural networks (under graduate course) Lecture 9 of 9Introduction to Neural networks (under graduate course) Lecture 9 of 9
Introduction to Neural networks (under graduate course) Lecture 9 of 9
Randa Elanwar
 
تعريف بمدونة علماء مصر ومحاور التدريب على الكتابة للمدونين
تعريف بمدونة علماء مصر ومحاور التدريب على الكتابة للمدونينتعريف بمدونة علماء مصر ومحاور التدريب على الكتابة للمدونين
تعريف بمدونة علماء مصر ومحاور التدريب على الكتابة للمدونين
Randa Elanwar
 
Introduction to matlab lecture 3 of 4
Introduction to matlab lecture 3 of 4Introduction to matlab lecture 3 of 4
Introduction to matlab lecture 3 of 4
Randa Elanwar
 
Introduction to Neural networks (under graduate course) Lecture 4 of 9
Introduction to Neural networks (under graduate course) Lecture 4 of 9Introduction to Neural networks (under graduate course) Lecture 4 of 9
Introduction to Neural networks (under graduate course) Lecture 4 of 9
Randa Elanwar
 
Communications for Clean Water
Communications for Clean WaterCommunications for Clean Water
Communications for Clean Water
Choose Clean Water
 
Digital library construction
Digital library constructionDigital library construction
Digital library construction
Randa Elanwar
 
What is pattern recognition (lecture 5 of 6)
What is pattern recognition (lecture 5 of 6)What is pattern recognition (lecture 5 of 6)
What is pattern recognition (lecture 5 of 6)
Randa Elanwar
 
The Mapping Network Lake Mapping
The Mapping Network Lake MappingThe Mapping Network Lake Mapping
The Mapping Network Lake Mapping
The Mapping Network
 
Pattern recognition on human vision
Pattern recognition on human visionPattern recognition on human vision
Pattern recognition on human vision
Giacomo Veneri
 
Icelandic Bathy model
Icelandic Bathy modelIcelandic Bathy model
Icelandic Bathy model
Peio Elissalde
 
Introduction to matlab lecture 2 of 4
Introduction to matlab lecture 2 of 4Introduction to matlab lecture 2 of 4
Introduction to matlab lecture 2 of 4
Randa Elanwar
 
Conowingo Presentation- USGS
Conowingo Presentation- USGSConowingo Presentation- USGS
Conowingo Presentation- USGS
Choose Clean Water
 
Earth science 14.1
Earth science 14.1Earth science 14.1
Earth science 14.1
Tamara
 
Hydro2016
Hydro2016Hydro2016
Introduction to matlab lecture 4 of 4
Introduction to matlab lecture 4 of 4Introduction to matlab lecture 4 of 4
Introduction to matlab lecture 4 of 4
Randa Elanwar
 
Introduction to Neural networks (under graduate course) Lecture 5 of 9
Introduction to Neural networks (under graduate course) Lecture 5 of 9Introduction to Neural networks (under graduate course) Lecture 5 of 9
Introduction to Neural networks (under graduate course) Lecture 5 of 9
Randa Elanwar
 
Do Humans Beat Computers At Pattern Recognition
Do Humans Beat Computers At Pattern RecognitionDo Humans Beat Computers At Pattern Recognition
Do Humans Beat Computers At Pattern Recognition
Bitdefender
 
RuleML2015: Similarity-Based Strict Equality in a Fully Integrated Fuzzy Logi...
RuleML2015: Similarity-Based Strict Equality in a Fully Integrated Fuzzy Logi...RuleML2015: Similarity-Based Strict Equality in a Fully Integrated Fuzzy Logi...
RuleML2015: Similarity-Based Strict Equality in a Fully Integrated Fuzzy Logi...
RuleML
 

Viewers also liked (20)

What is pattern recognition (lecture 6 of 6)
What is pattern recognition (lecture 6 of 6)What is pattern recognition (lecture 6 of 6)
What is pattern recognition (lecture 6 of 6)
 
What is pattern_recognition (lecture 2 of 6)
What is pattern_recognition (lecture 2 of 6)What is pattern_recognition (lecture 2 of 6)
What is pattern_recognition (lecture 2 of 6)
 
Introduction to Neural networks (under graduate course) Lecture 9 of 9
Introduction to Neural networks (under graduate course) Lecture 9 of 9Introduction to Neural networks (under graduate course) Lecture 9 of 9
Introduction to Neural networks (under graduate course) Lecture 9 of 9
 
تعريف بمدونة علماء مصر ومحاور التدريب على الكتابة للمدونين
تعريف بمدونة علماء مصر ومحاور التدريب على الكتابة للمدونينتعريف بمدونة علماء مصر ومحاور التدريب على الكتابة للمدونين
تعريف بمدونة علماء مصر ومحاور التدريب على الكتابة للمدونين
 
Introduction to matlab lecture 3 of 4
Introduction to matlab lecture 3 of 4Introduction to matlab lecture 3 of 4
Introduction to matlab lecture 3 of 4
 
Introduction to Neural networks (under graduate course) Lecture 4 of 9
Introduction to Neural networks (under graduate course) Lecture 4 of 9Introduction to Neural networks (under graduate course) Lecture 4 of 9
Introduction to Neural networks (under graduate course) Lecture 4 of 9
 
Communications for Clean Water
Communications for Clean WaterCommunications for Clean Water
Communications for Clean Water
 
Digital library construction
Digital library constructionDigital library construction
Digital library construction
 
What is pattern recognition (lecture 5 of 6)
What is pattern recognition (lecture 5 of 6)What is pattern recognition (lecture 5 of 6)
What is pattern recognition (lecture 5 of 6)
 
The Mapping Network Lake Mapping
The Mapping Network Lake MappingThe Mapping Network Lake Mapping
The Mapping Network Lake Mapping
 
Pattern recognition on human vision
Pattern recognition on human visionPattern recognition on human vision
Pattern recognition on human vision
 
Icelandic Bathy model
Icelandic Bathy modelIcelandic Bathy model
Icelandic Bathy model
 
Introduction to matlab lecture 2 of 4
Introduction to matlab lecture 2 of 4Introduction to matlab lecture 2 of 4
Introduction to matlab lecture 2 of 4
 
Conowingo Presentation- USGS
Conowingo Presentation- USGSConowingo Presentation- USGS
Conowingo Presentation- USGS
 
Earth science 14.1
Earth science 14.1Earth science 14.1
Earth science 14.1
 
Hydro2016
Hydro2016Hydro2016
Hydro2016
 
Introduction to matlab lecture 4 of 4
Introduction to matlab lecture 4 of 4Introduction to matlab lecture 4 of 4
Introduction to matlab lecture 4 of 4
 
Introduction to Neural networks (under graduate course) Lecture 5 of 9
Introduction to Neural networks (under graduate course) Lecture 5 of 9Introduction to Neural networks (under graduate course) Lecture 5 of 9
Introduction to Neural networks (under graduate course) Lecture 5 of 9
 
Do Humans Beat Computers At Pattern Recognition
Do Humans Beat Computers At Pattern RecognitionDo Humans Beat Computers At Pattern Recognition
Do Humans Beat Computers At Pattern Recognition
 
RuleML2015: Similarity-Based Strict Equality in a Fully Integrated Fuzzy Logi...
RuleML2015: Similarity-Based Strict Equality in a Fully Integrated Fuzzy Logi...RuleML2015: Similarity-Based Strict Equality in a Fully Integrated Fuzzy Logi...
RuleML2015: Similarity-Based Strict Equality in a Fully Integrated Fuzzy Logi...
 

Similar to What is pattern recognition (lecture 3 of 6)

What is pattern recognition (lecture 4 of 6)
What is pattern recognition (lecture 4 of 6)What is pattern recognition (lecture 4 of 6)
What is pattern recognition (lecture 4 of 6)
Randa Elanwar
 
A tour of the top 10 algorithms for machine learning newbies
A tour of the top 10 algorithms for machine learning newbiesA tour of the top 10 algorithms for machine learning newbies
A tour of the top 10 algorithms for machine learning newbies
Vimal Gupta
 
Getting_Started_with_DL_in_Keras.pptx
Getting_Started_with_DL_in_Keras.pptxGetting_Started_with_DL_in_Keras.pptx
Getting_Started_with_DL_in_Keras.pptx
Mohamed Essam
 
Algorithm
AlgorithmAlgorithm
Algorithm
nivlayalat
 
introduction
introductionintroduction
introduction
Mohamed Elsayed
 
Machine learning interview questions and answers
Machine learning interview questions and answersMachine learning interview questions and answers
Machine learning interview questions and answers
kavinilavuG
 
EssentialsOfMachineLearning.pdf
EssentialsOfMachineLearning.pdfEssentialsOfMachineLearning.pdf
EssentialsOfMachineLearning.pdf
Ankita Tiwari
 
Sample_Subjective_Questions_Answers (1).pdf
Sample_Subjective_Questions_Answers (1).pdfSample_Subjective_Questions_Answers (1).pdf
Sample_Subjective_Questions_Answers (1).pdf
AaryanArora10
 
A tutorial on deep learning at icml 2013
A tutorial on deep learning at icml 2013A tutorial on deep learning at icml 2013
A tutorial on deep learning at icml 2013
Philip Zheng
 
Getting started with Machine Learning
Getting started with Machine LearningGetting started with Machine Learning
Getting started with Machine Learning
Gaurav Bhalotia
 
Lect 8 learning types (M.L.).pdf
Lect 8 learning types (M.L.).pdfLect 8 learning types (M.L.).pdf
Lect 8 learning types (M.L.).pdf
HassanElalfy4
 
Iisrt zz mamatha
Iisrt zz mamathaIisrt zz mamatha
Iisrt zz mamatha
IISRT
 
AWS Certified Machine Learning Specialty
AWS Certified Machine Learning Specialty AWS Certified Machine Learning Specialty
AWS Certified Machine Learning Specialty
Adnan Rashid
 
ML_in_QM_JC_02-10-18
ML_in_QM_JC_02-10-18ML_in_QM_JC_02-10-18
ML_in_QM_JC_02-10-18
Suzanne Wallace
 
notes as .ppt
notes as .pptnotes as .ppt
notes as .ppt
butest
 
Algoritmos
AlgoritmosAlgoritmos
Algoritmos
Fab Lab LIMA
 
01 Notes Introduction Analysis of Algorithms Notes
01 Notes Introduction Analysis of Algorithms Notes01 Notes Introduction Analysis of Algorithms Notes
01 Notes Introduction Analysis of Algorithms Notes
Andres Mendez-Vazquez
 
Query Linguistic Intent Detection
Query Linguistic Intent DetectionQuery Linguistic Intent Detection
Query Linguistic Intent Detection
butest
 
Transfer Learning _ Monk AI _ GCOEN.pptx
Transfer Learning _ Monk AI _ GCOEN.pptxTransfer Learning _ Monk AI _ GCOEN.pptx
Transfer Learning _ Monk AI _ GCOEN.pptx
GDSCGCOEN
 
Machine Learning Interview Questions
Machine Learning Interview QuestionsMachine Learning Interview Questions
Machine Learning Interview Questions
Rock Interview
 

Similar to What is pattern recognition (lecture 3 of 6) (20)

What is pattern recognition (lecture 4 of 6)
What is pattern recognition (lecture 4 of 6)What is pattern recognition (lecture 4 of 6)
What is pattern recognition (lecture 4 of 6)
 
A tour of the top 10 algorithms for machine learning newbies
A tour of the top 10 algorithms for machine learning newbiesA tour of the top 10 algorithms for machine learning newbies
A tour of the top 10 algorithms for machine learning newbies
 
Getting_Started_with_DL_in_Keras.pptx
Getting_Started_with_DL_in_Keras.pptxGetting_Started_with_DL_in_Keras.pptx
Getting_Started_with_DL_in_Keras.pptx
 
Algorithm
AlgorithmAlgorithm
Algorithm
 
introduction
introductionintroduction
introduction
 
Machine learning interview questions and answers
Machine learning interview questions and answersMachine learning interview questions and answers
Machine learning interview questions and answers
 
EssentialsOfMachineLearning.pdf
EssentialsOfMachineLearning.pdfEssentialsOfMachineLearning.pdf
EssentialsOfMachineLearning.pdf
 
Sample_Subjective_Questions_Answers (1).pdf
Sample_Subjective_Questions_Answers (1).pdfSample_Subjective_Questions_Answers (1).pdf
Sample_Subjective_Questions_Answers (1).pdf
 
A tutorial on deep learning at icml 2013
A tutorial on deep learning at icml 2013A tutorial on deep learning at icml 2013
A tutorial on deep learning at icml 2013
 
Getting started with Machine Learning
Getting started with Machine LearningGetting started with Machine Learning
Getting started with Machine Learning
 
Lect 8 learning types (M.L.).pdf
Lect 8 learning types (M.L.).pdfLect 8 learning types (M.L.).pdf
Lect 8 learning types (M.L.).pdf
 
Iisrt zz mamatha
Iisrt zz mamathaIisrt zz mamatha
Iisrt zz mamatha
 
AWS Certified Machine Learning Specialty
AWS Certified Machine Learning Specialty AWS Certified Machine Learning Specialty
AWS Certified Machine Learning Specialty
 
ML_in_QM_JC_02-10-18
ML_in_QM_JC_02-10-18ML_in_QM_JC_02-10-18
ML_in_QM_JC_02-10-18
 
notes as .ppt
notes as .pptnotes as .ppt
notes as .ppt
 
Algoritmos
AlgoritmosAlgoritmos
Algoritmos
 
01 Notes Introduction Analysis of Algorithms Notes
01 Notes Introduction Analysis of Algorithms Notes01 Notes Introduction Analysis of Algorithms Notes
01 Notes Introduction Analysis of Algorithms Notes
 
Query Linguistic Intent Detection
Query Linguistic Intent DetectionQuery Linguistic Intent Detection
Query Linguistic Intent Detection
 
Transfer Learning _ Monk AI _ GCOEN.pptx
Transfer Learning _ Monk AI _ GCOEN.pptxTransfer Learning _ Monk AI _ GCOEN.pptx
Transfer Learning _ Monk AI _ GCOEN.pptx
 
Machine Learning Interview Questions
Machine Learning Interview QuestionsMachine Learning Interview Questions
Machine Learning Interview Questions
 

More from Randa Elanwar

الجزء السادس ماذا ستقدم لعميلك ريادة الأعمال خطوة بخطوة
الجزء السادس ماذا ستقدم لعميلك ريادة الأعمال خطوة بخطوةالجزء السادس ماذا ستقدم لعميلك ريادة الأعمال خطوة بخطوة
الجزء السادس ماذا ستقدم لعميلك ريادة الأعمال خطوة بخطوة
Randa Elanwar
 
الجزء الخامس ماذا ستقدم لعميلك ريادة الأعمال خطوة بخطوة
الجزء الخامس ماذا ستقدم لعميلك ريادة الأعمال خطوة بخطوةالجزء الخامس ماذا ستقدم لعميلك ريادة الأعمال خطوة بخطوة
الجزء الخامس ماذا ستقدم لعميلك ريادة الأعمال خطوة بخطوةRanda Elanwar
 
الجزء الرابع ماذا ستقدم لعميلك ريادة الأعمال خطوة بخطوة
الجزء الرابع ماذا ستقدم لعميلك ريادة الأعمال خطوة بخطوةالجزء الرابع ماذا ستقدم لعميلك ريادة الأعمال خطوة بخطوة
الجزء الرابع ماذا ستقدم لعميلك ريادة الأعمال خطوة بخطوة
Randa Elanwar
 
الجزء الثالث ماذا ستقدم لعميلك ريادة الأعمال خطوة بخطوة
الجزء الثالث ماذا ستقدم لعميلك ريادة الأعمال خطوة بخطوةالجزء الثالث ماذا ستقدم لعميلك ريادة الأعمال خطوة بخطوة
الجزء الثالث ماذا ستقدم لعميلك ريادة الأعمال خطوة بخطوةRanda Elanwar
 
الجزء الثاني ماذا ستقدم لعميلك ريادة الأعمال خطوة بخطوة
الجزء الثاني ماذا ستقدم لعميلك ريادة الأعمال خطوة بخطوةالجزء الثاني ماذا ستقدم لعميلك ريادة الأعمال خطوة بخطوة
الجزء الثاني ماذا ستقدم لعميلك ريادة الأعمال خطوة بخطوة
Randa Elanwar
 
الجزء الأول ماذا ستقدم لعميلك ريادة الأعمال خطوة بخطوة
الجزء الأول ماذا ستقدم لعميلك ريادة الأعمال خطوة بخطوةالجزء الأول ماذا ستقدم لعميلك ريادة الأعمال خطوة بخطوة
الجزء الأول ماذا ستقدم لعميلك ريادة الأعمال خطوة بخطوةRanda Elanwar
 
تدريب مدونة علماء مصر على الكتابة الفنية (الترجمة والتلخيص )_Pdf5of5
تدريب مدونة علماء مصر على الكتابة الفنية (الترجمة والتلخيص    )_Pdf5of5تدريب مدونة علماء مصر على الكتابة الفنية (الترجمة والتلخيص    )_Pdf5of5
تدريب مدونة علماء مصر على الكتابة الفنية (الترجمة والتلخيص )_Pdf5of5
Randa Elanwar
 
تدريب مدونة علماء مصر على الكتابة الفنية (القصة القصيرة والخاطرة والأخطاء ال...
تدريب مدونة علماء مصر على الكتابة الفنية (القصة القصيرة والخاطرة  والأخطاء ال...تدريب مدونة علماء مصر على الكتابة الفنية (القصة القصيرة والخاطرة  والأخطاء ال...
تدريب مدونة علماء مصر على الكتابة الفنية (القصة القصيرة والخاطرة والأخطاء ال...
Randa Elanwar
 
تدريب مدونة علماء مصر على الكتابة الفنية (مقالات الموارد )_Pdf3of5
تدريب مدونة علماء مصر على الكتابة الفنية (مقالات الموارد   )_Pdf3of5تدريب مدونة علماء مصر على الكتابة الفنية (مقالات الموارد   )_Pdf3of5
تدريب مدونة علماء مصر على الكتابة الفنية (مقالات الموارد )_Pdf3of5
Randa Elanwar
 
تدريب مدونة علماء مصر على الكتابة الفنية (المقالات الإخبارية )_Pdf2of5
تدريب مدونة علماء مصر على الكتابة الفنية (المقالات الإخبارية  )_Pdf2of5تدريب مدونة علماء مصر على الكتابة الفنية (المقالات الإخبارية  )_Pdf2of5
تدريب مدونة علماء مصر على الكتابة الفنية (المقالات الإخبارية )_Pdf2of5
Randa Elanwar
 
تدريب مدونة علماء مصر على الكتابة الفنية (المقالات المبنية على البحث )_Pdf1of5
تدريب مدونة علماء مصر على الكتابة الفنية (المقالات المبنية على البحث )_Pdf1of5تدريب مدونة علماء مصر على الكتابة الفنية (المقالات المبنية على البحث )_Pdf1of5
تدريب مدونة علماء مصر على الكتابة الفنية (المقالات المبنية على البحث )_Pdf1of5
Randa Elanwar
 
Entrepreneurship_who_is_your_customer_(arabic)_7of7
Entrepreneurship_who_is_your_customer_(arabic)_7of7Entrepreneurship_who_is_your_customer_(arabic)_7of7
Entrepreneurship_who_is_your_customer_(arabic)_7of7
Randa Elanwar
 
Entrepreneurship_who_is_your_customer_(arabic)_5of7
Entrepreneurship_who_is_your_customer_(arabic)_5of7Entrepreneurship_who_is_your_customer_(arabic)_5of7
Entrepreneurship_who_is_your_customer_(arabic)_5of7
Randa Elanwar
 
Entrepreneurship_who_is_your_customer_(arabic)_4of7
Entrepreneurship_who_is_your_customer_(arabic)_4of7Entrepreneurship_who_is_your_customer_(arabic)_4of7
Entrepreneurship_who_is_your_customer_(arabic)_4of7
Randa Elanwar
 
Entrepreneurship_who_is_your_customer_(arabic)_2of7
Entrepreneurship_who_is_your_customer_(arabic)_2of7Entrepreneurship_who_is_your_customer_(arabic)_2of7
Entrepreneurship_who_is_your_customer_(arabic)_2of7
Randa Elanwar
 
يوميات طالب بدرجة مشرف (Part 19 of 20)
يوميات طالب بدرجة مشرف (Part 19 of 20)يوميات طالب بدرجة مشرف (Part 19 of 20)
يوميات طالب بدرجة مشرف (Part 19 of 20)
Randa Elanwar
 
يوميات طالب بدرجة مشرف (Part 18 of 20)
يوميات طالب بدرجة مشرف (Part 18 of 20)يوميات طالب بدرجة مشرف (Part 18 of 20)
يوميات طالب بدرجة مشرف (Part 18 of 20)Randa Elanwar
 
يوميات طالب بدرجة مشرف (Part 17 of 20)
يوميات طالب بدرجة مشرف (Part 17 of 20)يوميات طالب بدرجة مشرف (Part 17 of 20)
يوميات طالب بدرجة مشرف (Part 17 of 20)
Randa Elanwar
 
يوميات طالب بدرجة مشرف (Part 16 of 20)
يوميات طالب بدرجة مشرف (Part 16 of 20)يوميات طالب بدرجة مشرف (Part 16 of 20)
يوميات طالب بدرجة مشرف (Part 16 of 20)Randa Elanwar
 
يوميات طالب بدرجة مشرف (Part 15 of 20)
يوميات طالب بدرجة مشرف (Part 15 of 20)يوميات طالب بدرجة مشرف (Part 15 of 20)
يوميات طالب بدرجة مشرف (Part 15 of 20)
Randa Elanwar
 

More from Randa Elanwar (20)

الجزء السادس ماذا ستقدم لعميلك ريادة الأعمال خطوة بخطوة
الجزء السادس ماذا ستقدم لعميلك ريادة الأعمال خطوة بخطوةالجزء السادس ماذا ستقدم لعميلك ريادة الأعمال خطوة بخطوة
الجزء السادس ماذا ستقدم لعميلك ريادة الأعمال خطوة بخطوة
 
الجزء الخامس ماذا ستقدم لعميلك ريادة الأعمال خطوة بخطوة
الجزء الخامس ماذا ستقدم لعميلك ريادة الأعمال خطوة بخطوةالجزء الخامس ماذا ستقدم لعميلك ريادة الأعمال خطوة بخطوة
الجزء الخامس ماذا ستقدم لعميلك ريادة الأعمال خطوة بخطوة
 
الجزء الرابع ماذا ستقدم لعميلك ريادة الأعمال خطوة بخطوة
الجزء الرابع ماذا ستقدم لعميلك ريادة الأعمال خطوة بخطوةالجزء الرابع ماذا ستقدم لعميلك ريادة الأعمال خطوة بخطوة
الجزء الرابع ماذا ستقدم لعميلك ريادة الأعمال خطوة بخطوة
 
الجزء الثالث ماذا ستقدم لعميلك ريادة الأعمال خطوة بخطوة
الجزء الثالث ماذا ستقدم لعميلك ريادة الأعمال خطوة بخطوةالجزء الثالث ماذا ستقدم لعميلك ريادة الأعمال خطوة بخطوة
الجزء الثالث ماذا ستقدم لعميلك ريادة الأعمال خطوة بخطوة
 
الجزء الثاني ماذا ستقدم لعميلك ريادة الأعمال خطوة بخطوة
الجزء الثاني ماذا ستقدم لعميلك ريادة الأعمال خطوة بخطوةالجزء الثاني ماذا ستقدم لعميلك ريادة الأعمال خطوة بخطوة
الجزء الثاني ماذا ستقدم لعميلك ريادة الأعمال خطوة بخطوة
 
الجزء الأول ماذا ستقدم لعميلك ريادة الأعمال خطوة بخطوة
الجزء الأول ماذا ستقدم لعميلك ريادة الأعمال خطوة بخطوةالجزء الأول ماذا ستقدم لعميلك ريادة الأعمال خطوة بخطوة
الجزء الأول ماذا ستقدم لعميلك ريادة الأعمال خطوة بخطوة
 
تدريب مدونة علماء مصر على الكتابة الفنية (الترجمة والتلخيص )_Pdf5of5
تدريب مدونة علماء مصر على الكتابة الفنية (الترجمة والتلخيص    )_Pdf5of5تدريب مدونة علماء مصر على الكتابة الفنية (الترجمة والتلخيص    )_Pdf5of5
تدريب مدونة علماء مصر على الكتابة الفنية (الترجمة والتلخيص )_Pdf5of5
 
تدريب مدونة علماء مصر على الكتابة الفنية (القصة القصيرة والخاطرة والأخطاء ال...
تدريب مدونة علماء مصر على الكتابة الفنية (القصة القصيرة والخاطرة  والأخطاء ال...تدريب مدونة علماء مصر على الكتابة الفنية (القصة القصيرة والخاطرة  والأخطاء ال...
تدريب مدونة علماء مصر على الكتابة الفنية (القصة القصيرة والخاطرة والأخطاء ال...
 
تدريب مدونة علماء مصر على الكتابة الفنية (مقالات الموارد )_Pdf3of5
تدريب مدونة علماء مصر على الكتابة الفنية (مقالات الموارد   )_Pdf3of5تدريب مدونة علماء مصر على الكتابة الفنية (مقالات الموارد   )_Pdf3of5
تدريب مدونة علماء مصر على الكتابة الفنية (مقالات الموارد )_Pdf3of5
 
تدريب مدونة علماء مصر على الكتابة الفنية (المقالات الإخبارية )_Pdf2of5
تدريب مدونة علماء مصر على الكتابة الفنية (المقالات الإخبارية  )_Pdf2of5تدريب مدونة علماء مصر على الكتابة الفنية (المقالات الإخبارية  )_Pdf2of5
تدريب مدونة علماء مصر على الكتابة الفنية (المقالات الإخبارية )_Pdf2of5
 
تدريب مدونة علماء مصر على الكتابة الفنية (المقالات المبنية على البحث )_Pdf1of5
تدريب مدونة علماء مصر على الكتابة الفنية (المقالات المبنية على البحث )_Pdf1of5تدريب مدونة علماء مصر على الكتابة الفنية (المقالات المبنية على البحث )_Pdf1of5
تدريب مدونة علماء مصر على الكتابة الفنية (المقالات المبنية على البحث )_Pdf1of5
 
Entrepreneurship_who_is_your_customer_(arabic)_7of7
Entrepreneurship_who_is_your_customer_(arabic)_7of7Entrepreneurship_who_is_your_customer_(arabic)_7of7
Entrepreneurship_who_is_your_customer_(arabic)_7of7
 
Entrepreneurship_who_is_your_customer_(arabic)_5of7
Entrepreneurship_who_is_your_customer_(arabic)_5of7Entrepreneurship_who_is_your_customer_(arabic)_5of7
Entrepreneurship_who_is_your_customer_(arabic)_5of7
 
Entrepreneurship_who_is_your_customer_(arabic)_4of7
Entrepreneurship_who_is_your_customer_(arabic)_4of7Entrepreneurship_who_is_your_customer_(arabic)_4of7
Entrepreneurship_who_is_your_customer_(arabic)_4of7
 
Entrepreneurship_who_is_your_customer_(arabic)_2of7
Entrepreneurship_who_is_your_customer_(arabic)_2of7Entrepreneurship_who_is_your_customer_(arabic)_2of7
Entrepreneurship_who_is_your_customer_(arabic)_2of7
 
يوميات طالب بدرجة مشرف (Part 19 of 20)
يوميات طالب بدرجة مشرف (Part 19 of 20)يوميات طالب بدرجة مشرف (Part 19 of 20)
يوميات طالب بدرجة مشرف (Part 19 of 20)
 
يوميات طالب بدرجة مشرف (Part 18 of 20)
يوميات طالب بدرجة مشرف (Part 18 of 20)يوميات طالب بدرجة مشرف (Part 18 of 20)
يوميات طالب بدرجة مشرف (Part 18 of 20)
 
يوميات طالب بدرجة مشرف (Part 17 of 20)
يوميات طالب بدرجة مشرف (Part 17 of 20)يوميات طالب بدرجة مشرف (Part 17 of 20)
يوميات طالب بدرجة مشرف (Part 17 of 20)
 
يوميات طالب بدرجة مشرف (Part 16 of 20)
يوميات طالب بدرجة مشرف (Part 16 of 20)يوميات طالب بدرجة مشرف (Part 16 of 20)
يوميات طالب بدرجة مشرف (Part 16 of 20)
 
يوميات طالب بدرجة مشرف (Part 15 of 20)
يوميات طالب بدرجة مشرف (Part 15 of 20)يوميات طالب بدرجة مشرف (Part 15 of 20)
يوميات طالب بدرجة مشرف (Part 15 of 20)
 

Recently uploaded

Direct Seeded Rice - Climate Smart Agriculture
Direct Seeded Rice - Climate Smart AgricultureDirect Seeded Rice - Climate Smart Agriculture
Direct Seeded Rice - Climate Smart Agriculture
International Food Policy Research Institute- South Asia Office
 
waterlessdyeingtechnolgyusing carbon dioxide chemicalspdf
waterlessdyeingtechnolgyusing carbon dioxide chemicalspdfwaterlessdyeingtechnolgyusing carbon dioxide chemicalspdf
waterlessdyeingtechnolgyusing carbon dioxide chemicalspdf
LengamoLAppostilic
 
molar-distalization in orthodontics-seminar.pptx
molar-distalization in orthodontics-seminar.pptxmolar-distalization in orthodontics-seminar.pptx
molar-distalization in orthodontics-seminar.pptx
Anagha Prasad
 
NuGOweek 2024 Ghent programme overview flyer
NuGOweek 2024 Ghent programme overview flyerNuGOweek 2024 Ghent programme overview flyer
NuGOweek 2024 Ghent programme overview flyer
pablovgd
 
Unlocking the mysteries of reproduction: Exploring fecundity and gonadosomati...
Unlocking the mysteries of reproduction: Exploring fecundity and gonadosomati...Unlocking the mysteries of reproduction: Exploring fecundity and gonadosomati...
Unlocking the mysteries of reproduction: Exploring fecundity and gonadosomati...
AbdullaAlAsif1
 
Basics of crystallography, crystal systems, classes and different forms
Basics of crystallography, crystal systems, classes and different formsBasics of crystallography, crystal systems, classes and different forms
Basics of crystallography, crystal systems, classes and different forms
MaheshaNanjegowda
 
aziz sancar nobel prize winner: from mardin to nobel
aziz sancar nobel prize winner: from mardin to nobelaziz sancar nobel prize winner: from mardin to nobel
aziz sancar nobel prize winner: from mardin to nobel
İsa Badur
 
The debris of the ‘last major merger’ is dynamically young
The debris of the ‘last major merger’ is dynamically youngThe debris of the ‘last major merger’ is dynamically young
The debris of the ‘last major merger’ is dynamically young
Sérgio Sacani
 
Immersive Learning That Works: Research Grounding and Paths Forward
Immersive Learning That Works: Research Grounding and Paths ForwardImmersive Learning That Works: Research Grounding and Paths Forward
Immersive Learning That Works: Research Grounding and Paths Forward
Leonel Morgado
 
Authoring a personal GPT for your research and practice: How we created the Q...
Authoring a personal GPT for your research and practice: How we created the Q...Authoring a personal GPT for your research and practice: How we created the Q...
Authoring a personal GPT for your research and practice: How we created the Q...
Leonel Morgado
 
Micronuclei test.M.sc.zoology.fisheries.
Micronuclei test.M.sc.zoology.fisheries.Micronuclei test.M.sc.zoology.fisheries.
Micronuclei test.M.sc.zoology.fisheries.
Aditi Bajpai
 
Shallowest Oil Discovery of Turkiye.pptx
Shallowest Oil Discovery of Turkiye.pptxShallowest Oil Discovery of Turkiye.pptx
Shallowest Oil Discovery of Turkiye.pptx
Gokturk Mehmet Dilci
 
EWOCS-I: The catalog of X-ray sources in Westerlund 1 from the Extended Weste...
EWOCS-I: The catalog of X-ray sources in Westerlund 1 from the Extended Weste...EWOCS-I: The catalog of X-ray sources in Westerlund 1 from the Extended Weste...
EWOCS-I: The catalog of X-ray sources in Westerlund 1 from the Extended Weste...
Sérgio Sacani
 
SAR of Medicinal Chemistry 1st by dk.pdf
SAR of Medicinal Chemistry 1st by dk.pdfSAR of Medicinal Chemistry 1st by dk.pdf
SAR of Medicinal Chemistry 1st by dk.pdf
KrushnaDarade1
 
在线办理(salfor毕业证书)索尔福德大学毕业证毕业完成信一模一样
在线办理(salfor毕业证书)索尔福德大学毕业证毕业完成信一模一样在线办理(salfor毕业证书)索尔福德大学毕业证毕业完成信一模一样
在线办理(salfor毕业证书)索尔福德大学毕业证毕业完成信一模一样
vluwdy49
 
Topic: SICKLE CELL DISEASE IN CHILDREN-3.pdf
Topic: SICKLE CELL DISEASE IN CHILDREN-3.pdfTopic: SICKLE CELL DISEASE IN CHILDREN-3.pdf
Topic: SICKLE CELL DISEASE IN CHILDREN-3.pdf
TinyAnderson
 
THEMATIC APPERCEPTION TEST(TAT) cognitive abilities, creativity, and critic...
THEMATIC  APPERCEPTION  TEST(TAT) cognitive abilities, creativity, and critic...THEMATIC  APPERCEPTION  TEST(TAT) cognitive abilities, creativity, and critic...
THEMATIC APPERCEPTION TEST(TAT) cognitive abilities, creativity, and critic...
Abdul Wali Khan University Mardan,kP,Pakistan
 
ESR spectroscopy in liquid food and beverages.pptx
ESR spectroscopy in liquid food and beverages.pptxESR spectroscopy in liquid food and beverages.pptx
ESR spectroscopy in liquid food and beverages.pptx
PRIYANKA PATEL
 
Sharlene Leurig - Enabling Onsite Water Use with Net Zero Water
Sharlene Leurig - Enabling Onsite Water Use with Net Zero WaterSharlene Leurig - Enabling Onsite Water Use with Net Zero Water
Sharlene Leurig - Enabling Onsite Water Use with Net Zero Water
Texas Alliance of Groundwater Districts
 
Phenomics assisted breeding in crop improvement
Phenomics assisted breeding in crop improvementPhenomics assisted breeding in crop improvement
Phenomics assisted breeding in crop improvement
IshaGoswami9
 

Recently uploaded (20)

Direct Seeded Rice - Climate Smart Agriculture
Direct Seeded Rice - Climate Smart AgricultureDirect Seeded Rice - Climate Smart Agriculture
Direct Seeded Rice - Climate Smart Agriculture
 
waterlessdyeingtechnolgyusing carbon dioxide chemicalspdf
waterlessdyeingtechnolgyusing carbon dioxide chemicalspdfwaterlessdyeingtechnolgyusing carbon dioxide chemicalspdf
waterlessdyeingtechnolgyusing carbon dioxide chemicalspdf
 
molar-distalization in orthodontics-seminar.pptx
molar-distalization in orthodontics-seminar.pptxmolar-distalization in orthodontics-seminar.pptx
molar-distalization in orthodontics-seminar.pptx
 
NuGOweek 2024 Ghent programme overview flyer
NuGOweek 2024 Ghent programme overview flyerNuGOweek 2024 Ghent programme overview flyer
NuGOweek 2024 Ghent programme overview flyer
 
Unlocking the mysteries of reproduction: Exploring fecundity and gonadosomati...
Unlocking the mysteries of reproduction: Exploring fecundity and gonadosomati...Unlocking the mysteries of reproduction: Exploring fecundity and gonadosomati...
Unlocking the mysteries of reproduction: Exploring fecundity and gonadosomati...
 
Basics of crystallography, crystal systems, classes and different forms
Basics of crystallography, crystal systems, classes and different formsBasics of crystallography, crystal systems, classes and different forms
Basics of crystallography, crystal systems, classes and different forms
 
aziz sancar nobel prize winner: from mardin to nobel
aziz sancar nobel prize winner: from mardin to nobelaziz sancar nobel prize winner: from mardin to nobel
aziz sancar nobel prize winner: from mardin to nobel
 
The debris of the ‘last major merger’ is dynamically young
The debris of the ‘last major merger’ is dynamically youngThe debris of the ‘last major merger’ is dynamically young
The debris of the ‘last major merger’ is dynamically young
 
Immersive Learning That Works: Research Grounding and Paths Forward
Immersive Learning That Works: Research Grounding and Paths ForwardImmersive Learning That Works: Research Grounding and Paths Forward
Immersive Learning That Works: Research Grounding and Paths Forward
 
Authoring a personal GPT for your research and practice: How we created the Q...
Authoring a personal GPT for your research and practice: How we created the Q...Authoring a personal GPT for your research and practice: How we created the Q...
Authoring a personal GPT for your research and practice: How we created the Q...
 
Micronuclei test.M.sc.zoology.fisheries.
Micronuclei test.M.sc.zoology.fisheries.Micronuclei test.M.sc.zoology.fisheries.
Micronuclei test.M.sc.zoology.fisheries.
 
Shallowest Oil Discovery of Turkiye.pptx
Shallowest Oil Discovery of Turkiye.pptxShallowest Oil Discovery of Turkiye.pptx
Shallowest Oil Discovery of Turkiye.pptx
 
EWOCS-I: The catalog of X-ray sources in Westerlund 1 from the Extended Weste...
EWOCS-I: The catalog of X-ray sources in Westerlund 1 from the Extended Weste...EWOCS-I: The catalog of X-ray sources in Westerlund 1 from the Extended Weste...
EWOCS-I: The catalog of X-ray sources in Westerlund 1 from the Extended Weste...
 
SAR of Medicinal Chemistry 1st by dk.pdf
SAR of Medicinal Chemistry 1st by dk.pdfSAR of Medicinal Chemistry 1st by dk.pdf
SAR of Medicinal Chemistry 1st by dk.pdf
 
在线办理(salfor毕业证书)索尔福德大学毕业证毕业完成信一模一样
在线办理(salfor毕业证书)索尔福德大学毕业证毕业完成信一模一样在线办理(salfor毕业证书)索尔福德大学毕业证毕业完成信一模一样
在线办理(salfor毕业证书)索尔福德大学毕业证毕业完成信一模一样
 
Topic: SICKLE CELL DISEASE IN CHILDREN-3.pdf
Topic: SICKLE CELL DISEASE IN CHILDREN-3.pdfTopic: SICKLE CELL DISEASE IN CHILDREN-3.pdf
Topic: SICKLE CELL DISEASE IN CHILDREN-3.pdf
 
THEMATIC APPERCEPTION TEST(TAT) cognitive abilities, creativity, and critic...
THEMATIC  APPERCEPTION  TEST(TAT) cognitive abilities, creativity, and critic...THEMATIC  APPERCEPTION  TEST(TAT) cognitive abilities, creativity, and critic...
THEMATIC APPERCEPTION TEST(TAT) cognitive abilities, creativity, and critic...
 
ESR spectroscopy in liquid food and beverages.pptx
ESR spectroscopy in liquid food and beverages.pptxESR spectroscopy in liquid food and beverages.pptx
ESR spectroscopy in liquid food and beverages.pptx
 
Sharlene Leurig - Enabling Onsite Water Use with Net Zero Water
Sharlene Leurig - Enabling Onsite Water Use with Net Zero WaterSharlene Leurig - Enabling Onsite Water Use with Net Zero Water
Sharlene Leurig - Enabling Onsite Water Use with Net Zero Water
 
Phenomics assisted breeding in crop improvement
Phenomics assisted breeding in crop improvementPhenomics assisted breeding in crop improvement
Phenomics assisted breeding in crop improvement
 

What is pattern recognition (lecture 3 of 6)

  • 1. ERI SUMMER TRAINING COMPUTERS & SYSTEMS DEPT. Dr. Randa ElanwarLecture 3
  • 2. Content Non linear problems Learning Methods Supervised learning Unsupervised learning 2 ERI Summer training (C&S) Dr. Randa Elanwar Unsupervised learning Reinforcement learning
  • 3. Non linear problems 3 So far we understood that NN can handle problems with feature vectors > 2 (i.e. hyper feature space) multiple classes >= 2multiple classes >= 2 linear problems (linearly separable) Sometimes, the problem nature or the features taken in the feature space cannot be solved using first degree polynomial like this example. ERI Summer training (C&S) Dr. Randa Elanwar
  • 4. Non linear problems Assume a shoes factory is packing the shoes pairs of certain size on a moving belt, the machine should check that the pairs are not alike. The factory labels left shoe as "0" and right shoe as "1". The factory needs a solution that checks labels and 4 ERI Summer training (C&S) Dr. Randa Elanwar The factory needs a solution that checks labels and whenever it find similar pair stops the moving belt to prevent packing it. So we want to implement a NN to act as logical XOR function .. In other words whenever the input is '00' or "11" the output is '0' and belt stops, otherwise the output is '1' and belt keeps moving.
  • 5. Non linear problems 5 XOR problem No single line can ever separate the samples correctly. The only way to separate the positive from negative examples is to draw 2 lines (i.e., we need 2 straight line equations) or draw a nonlinear region to capture one type only ERI Summer training (C&S) Dr. Randa Elanwar
  • 6. Non linear problems To implement the nonlinearity we need to insert one or more extra layer of nodes between the input layer and the output layer (Hidden layer) 6 ERI Summer training (C&S) Dr. Randa Elanwar
  • 7. Non linear problems 7 The nonlinearity can help re-shape the straight line decision boundary into higher order polynomial that can successfully separates each class samples ERI Summer training (C&S) Dr. Randa Elanwar
  • 8. Non linear problems The higher the polynomial order, the more over fitting we get. But here we have to answer 2 questions: 8 ERI Summer training (C&S) Dr. Randa Elanwar Why are the samples interfering in the feature space? How far should we pursue raising the order of the decision boundary (adding hidden layers to the network)?
  • 9. Non linear problems 9 Well! first you will notice that discriminative features are rare and have a limit. Real samples usually have similarities that cause classes interference/overlap within any featureclasses interference/overlap within any feature space. Moreover, some features may be dependent on other features used and not distinct. This dependency usually allows more interference. ERI Summer training (C&S) Dr. Randa Elanwar
  • 10. Non linear problems Some times the number of features used is insufficient to distinctly separate the samples in the feature space. Increasing the number of distinct features help widen the space between each class samples. 10 ERI Summer training (C&S) Dr. Randa Elanwar the space between each class samples. However, increasing the number of features more than needed introduce noise in the form of irrelevant features, which doesn't lead to the separation as well as it leads to the system complexity (remember that the number of nodes in the NN input layer is equal to the number of features used).
  • 11. Non linear problems 11 Using a feed forward network to solve the overlapping problem will not help, because the delta rule works only If a set of <input, output> pairs are learnable (representable), the delta rule will find the necessary weights: in a finite number of steps independent of initial weightsindependent of initial weights In case of interfering samples in the feature space the delta rue will run in an infinite loop because the error will never diminish to zero, i.e. the sample pairs are not learnable. The only solution we need is a hyperbola (non linear decision boundary). ERI Summer training (C&S) Dr. Randa Elanwar
  • 12. Non linear problems This solution is offered in either of 2 ways: 1. Adding hidden layers (use Multiple Layer Perceptron MLP NN) to add non linearity to the decision boundary to some acceptable limit. 12 ERI Summer training (C&S) Dr. Randa Elanwar 2. Make sample transformation by kernels, in other words, multiply the feature vector of the patterns/samples by a set of orthogonal functions to re-locate them in space in a way that can make the linear solution possible (use Radial Basis Functions RBF NN)
  • 13. Non linear problems 13 The learning of MLP and RBF depends on another method than the delta rule, called the back propagation algorithm. This algorithms also depends on minimizing the error function of misclassified patterns. It has a long derivation that we will not discuss it now,has a long derivation that we will not discuss it now, may be later. But to imagine how things work Back propagation tries to transform training patterns to make them almost linearly separable and use linear network ERI Summer training (C&S) Dr. Randa Elanwar
  • 14. Non linear problems In other words, if we need more than 1 straight line to separate +ve and –ve patterns, we solve the problem in two phases: In phase 1: we first represent each straight line with a 14 ERI Summer training (C&S) Dr. Randa Elanwar In phase 1: we first represent each straight line with a single perceptron and classify the training patterns (output) In phase 2: these outputs are then transformed to new patterns which are now linearly separable and can be classified by an additional perceptron giving the final result.
  • 15. Learning Methods 15 Learning/Training is The process of modifying the weights in the connections between network layers with the objective of achieving the expected output. This is achieved through Supervised learning Unsupervised learning Reinforcement learning ERI Summer training (C&S) Dr. Randa Elanwar
  • 16. Supervised learning Each input vector requires a corresponding target vector. Training pair=[input vector, target vector] 16 ERI Summer training (C&S) Dr. Randa Elanwar
  • 17. Supervised learning 17 During learning, produced output is compared with the desired output The difference between both output is used to modify learning weights according to the learning algorithm Learning cases: pattern recognition problems. Neural Network models using supervised learning: ML Perceptron, feed-forward, radial basis function, support vector machine. ERI Summer training (C&S) Dr. Randa Elanwar
  • 18. Unsupervised learning 18 All similar input patterns are grouped together as clusters. If a matching input pattern is not found a new cluster is formed In unsupervised learning there is no error feedback because targets are not provided ERI Summer training (C&S) Dr. Randa Elanwar
  • 19. Unsupervised learning Network must discover patterns, regularities, features for the input data over the output. This process is called self-organizing Learning cases: Appropriate for clustering task like: 19 ERI Summer training (C&S) Dr. Randa Elanwar Learning cases: Appropriate for clustering task like: Find similar groups of documents in the web, content addressable memory, clustering. Neural Network models using unsupervised learning: Kohonen, self organizing maps, Hopfield networks.
  • 20. Reinforcement learning Target is provided, but the desired output is absent. I.e. unlike unsupervised learning, there is a given feedback but it is in the form of "Good /bad", "Greater/less", etc. No exact value for the desired output or the class membership. 20 ERI Summer training (C&S) Dr. Randa Elanwar output or the class membership. The net is only provided with guidance to determine the produced output is acceptable or not.
  • 21. Reinforcement learning 21 Weights are modified in the units that have errors ERI Summer training (C&S) Dr. Randa Elanwar
  • 22. Reinforcement learning When Reinforcement learning is used? If less information is available about the target output values (critic information) Feedback in this case is only evaluative and not 22 ERI Summer training (C&S) Dr. Randa Elanwar instructive