SlideShare a Scribd company logo
1 of 13
AI Club
AI Club
How Neural Networks
Learn – Part III
The Model
The Network and
Its Weights
w1
1
w1
2w1
3
w1
4
w6
1
w6
2w6
3 w6
4
Real life Neural Networks can have hundreds of
hidden layers and 1000s of neurons per layer, or
more! This means millions or billions of weights!
How do you learn the weights ?
AI Algorithm
Training
DATA
Examples of
happy and
sad
MODE
L
= weights of the
neural
network
AI Algorithm
Prediction
PREDICT
ANSWE
R
“Happy”
• Weights of a neural network are learnt during training
How do you learn the weights?
• Weights of a neural network are learnt during training
• Weights are learnt using a mechanism called stochastic
gradient descent (SGD)
Parameters of a neural network
• Learning rate: The rate at which you will make changes to
your model weights
• For example: if initial weight = 1, should the change to a weight
value be 0.1 or 0.01 or 0.001 resulting in 1.1 or 1.01 or 1.001
Parameters of a neural network
• Learning rate: The rate at which you will make changes to
your model weights
• For example: if initial weight = 1, should the change to a weight
value be 0.1 or 0.01 or 0.001 resulting in 1.1 or 1.01 or 1.001
• Mini-batch size: The number of samples that will be used to
make a change to the weights.
• For example: I will look at 10 sample images to understand how
I should change my model weights.
Parameters of a neural network
• Learning rate: The rate at which you will make changes to your model
weights
• For example: if initial weight = 1, should the change to a weight value be 0.1 or 0.01
or 0.001 resulting in 1.1 or 1.01 or 1.001
• Mini-batch size: The number of samples that will be used to make a
change to the weights.
• For example: I will look at 10 sample images to understand how I should change my
model weights.
• Epochs: Number of times you will go through the entire data to make
changes to the weights.
• For example: If epochs = 5, I have looked at all samples 5 times and made changes
to weights (5*(samples/Mini-batch size)) number of times.
Let us look at these parameters a bit more
• Learning rate: The rate at which you will make changes to
your model weights
• For example: if initial weight = 1, should the change to a weight
value be 0.1 or 0.01 or 0.001 resulting in 1.1 or 1.01 or 1.001
• What happens if it is too high or too low?
Let us look at these parameters a bit more
● Mini-batch size: The number of samples that will be used to
make a change to the weights.
○ For example: I will look at 10 sample images to understand how I
should change my model weights.
• What happens if it is too high or too low?
• Too high - not much benefit, takes a lot longer and cost more
• Too low, may not get good results
Let us look at these parameters a bit more
● Epochs: Number of times you will go through the entire data to
make changes to the weights.
○ For example: If epochs = 5, I have looked at all samples 5 times
and made changes to weights (5*(samples/Mini-batch size))
number of times.
• What happens if it is too high or too low?
• Too high - not much benefit, takes a lot longer and cost more
• Too low, may not get good results
THANK YOU
https://aiclub.world
info@pyxeda.ai

More Related Content

Similar to How neural networks learn part iii

SI Units and Unit Conversion Slides.pptx
SI Units and Unit Conversion Slides.pptxSI Units and Unit Conversion Slides.pptx
SI Units and Unit Conversion Slides.pptxSiharaGallage
 
SI Units and Unit Conversion Slides.pptx
SI Units and Unit Conversion Slides.pptxSI Units and Unit Conversion Slides.pptx
SI Units and Unit Conversion Slides.pptxSiharaGallage
 
Moles, Calculations, Dimensional Analysis!!!
Moles, Calculations, Dimensional Analysis!!!Moles, Calculations, Dimensional Analysis!!!
Moles, Calculations, Dimensional Analysis!!!guest806c70
 
Topic 5 (multiple regression)
Topic 5 (multiple regression)Topic 5 (multiple regression)
Topic 5 (multiple regression)Ryan Herzog
 
Drug calculation tutorial_091407
Drug calculation tutorial_091407Drug calculation tutorial_091407
Drug calculation tutorial_091407olayski
 
CS532L4_Backpropagation.pptx
CS532L4_Backpropagation.pptxCS532L4_Backpropagation.pptx
CS532L4_Backpropagation.pptxMFaisalRiaz5
 
Topic 5 (multiple regression)
Topic 5 (multiple regression)Topic 5 (multiple regression)
Topic 5 (multiple regression)Ryan Herzog
 
Topic 3 (Stats summary)
Topic 3 (Stats summary)Topic 3 (Stats summary)
Topic 3 (Stats summary)Ryan Herzog
 
Writing lab reports
Writing lab reportsWriting lab reports
Writing lab reportsphspsquires
 
Mr Exham's Guide to writing up a Biology Practical Investigation
Mr Exham's Guide to writing up a Biology Practical InvestigationMr Exham's Guide to writing up a Biology Practical Investigation
Mr Exham's Guide to writing up a Biology Practical Investigationmrexham
 
[CVPR2022, LongVersion] Online Continual Learning on a Contaminated Data Stre...
[CVPR2022, LongVersion] Online Continual Learning on a Contaminated Data Stre...[CVPR2022, LongVersion] Online Continual Learning on a Contaminated Data Stre...
[CVPR2022, LongVersion] Online Continual Learning on a Contaminated Data Stre...Jihwan Bang
 
Mixed Effects Models - Post-Hoc Comparisons
Mixed Effects Models - Post-Hoc ComparisonsMixed Effects Models - Post-Hoc Comparisons
Mixed Effects Models - Post-Hoc ComparisonsScott Fraundorf
 
COORDINATE ALGEBRA Unit One Power point
COORDINATE ALGEBRA Unit One Power pointCOORDINATE ALGEBRA Unit One Power point
COORDINATE ALGEBRA Unit One Power pointAmanda Manning
 
Experimental Design Scientific Method and GraphingREVISED.ppt
Experimental Design Scientific Method and GraphingREVISED.pptExperimental Design Scientific Method and GraphingREVISED.ppt
Experimental Design Scientific Method and GraphingREVISED.pptMathandScienced
 

Similar to How neural networks learn part iii (20)

SI Units and Unit Conversion Slides.pptx
SI Units and Unit Conversion Slides.pptxSI Units and Unit Conversion Slides.pptx
SI Units and Unit Conversion Slides.pptx
 
SI Units and Unit Conversion Slides.pptx
SI Units and Unit Conversion Slides.pptxSI Units and Unit Conversion Slides.pptx
SI Units and Unit Conversion Slides.pptx
 
Measurement
MeasurementMeasurement
Measurement
 
Moles, Calculations, Dimensional Analysis!!!
Moles, Calculations, Dimensional Analysis!!!Moles, Calculations, Dimensional Analysis!!!
Moles, Calculations, Dimensional Analysis!!!
 
Topic 5 (multiple regression)
Topic 5 (multiple regression)Topic 5 (multiple regression)
Topic 5 (multiple regression)
 
Drug calculation tutorial_091407
Drug calculation tutorial_091407Drug calculation tutorial_091407
Drug calculation tutorial_091407
 
CS532L4_Backpropagation.pptx
CS532L4_Backpropagation.pptxCS532L4_Backpropagation.pptx
CS532L4_Backpropagation.pptx
 
Topic 5 (multiple regression)
Topic 5 (multiple regression)Topic 5 (multiple regression)
Topic 5 (multiple regression)
 
Topic 3 (Stats summary)
Topic 3 (Stats summary)Topic 3 (Stats summary)
Topic 3 (Stats summary)
 
Mole conversions
Mole conversionsMole conversions
Mole conversions
 
Writing lab reports
Writing lab reportsWriting lab reports
Writing lab reports
 
Mr Exham's Guide to writing up a Biology Practical Investigation
Mr Exham's Guide to writing up a Biology Practical InvestigationMr Exham's Guide to writing up a Biology Practical Investigation
Mr Exham's Guide to writing up a Biology Practical Investigation
 
[CVPR2022, LongVersion] Online Continual Learning on a Contaminated Data Stre...
[CVPR2022, LongVersion] Online Continual Learning on a Contaminated Data Stre...[CVPR2022, LongVersion] Online Continual Learning on a Contaminated Data Stre...
[CVPR2022, LongVersion] Online Continual Learning on a Contaminated Data Stre...
 
PowerPointCh2_Sections2.5.pdf
PowerPointCh2_Sections2.5.pdfPowerPointCh2_Sections2.5.pdf
PowerPointCh2_Sections2.5.pdf
 
Validity andreliability
Validity andreliabilityValidity andreliability
Validity andreliability
 
Mixed Effects Models - Post-Hoc Comparisons
Mixed Effects Models - Post-Hoc ComparisonsMixed Effects Models - Post-Hoc Comparisons
Mixed Effects Models - Post-Hoc Comparisons
 
Measurements
MeasurementsMeasurements
Measurements
 
COORDINATE ALGEBRA Unit One Power point
COORDINATE ALGEBRA Unit One Power pointCOORDINATE ALGEBRA Unit One Power point
COORDINATE ALGEBRA Unit One Power point
 
Maths Behind Models.pptx
Maths Behind Models.pptxMaths Behind Models.pptx
Maths Behind Models.pptx
 
Experimental Design Scientific Method and GraphingREVISED.ppt
Experimental Design Scientific Method and GraphingREVISED.pptExperimental Design Scientific Method and GraphingREVISED.ppt
Experimental Design Scientific Method and GraphingREVISED.ppt
 

More from aiclub_slides

Linear regression middleschool
Linear regression middleschoolLinear regression middleschool
Linear regression middleschoolaiclub_slides
 
Pa2 project template
Pa2 project templatePa2 project template
Pa2 project templateaiclub_slides
 
Knn intro advanced_middleschool
Knn intro advanced_middleschoolKnn intro advanced_middleschool
Knn intro advanced_middleschoolaiclub_slides
 
M1 regression metrics_middleschool
M1 regression metrics_middleschoolM1 regression metrics_middleschool
M1 regression metrics_middleschoolaiclub_slides
 
Ai in real life face detection
Ai in real life   face detectionAi in real life   face detection
Ai in real life face detectionaiclub_slides
 
Res net high level intro
Res net high level introRes net high level intro
Res net high level introaiclub_slides
 
Neural networks and flattened images
Neural networks and flattened imagesNeural networks and flattened images
Neural networks and flattened imagesaiclub_slides
 
What is a_neural_network
What is a_neural_networkWhat is a_neural_network
What is a_neural_networkaiclub_slides
 
Introduction to deep learning image classification
Introduction to deep learning   image classificationIntroduction to deep learning   image classification
Introduction to deep learning image classificationaiclub_slides
 
Accuracy middleschool
Accuracy middleschoolAccuracy middleschool
Accuracy middleschoolaiclub_slides
 
Introduction to classification_middleschool
Introduction to classification_middleschoolIntroduction to classification_middleschool
Introduction to classification_middleschoolaiclub_slides
 
Introduction to the cloud
Introduction to the cloudIntroduction to the cloud
Introduction to the cloudaiclub_slides
 
Ai lifecycle and navigator
Ai lifecycle and navigatorAi lifecycle and navigator
Ai lifecycle and navigatoraiclub_slides
 
How AIs are different from us level 1
How AIs are different from us   level 1How AIs are different from us   level 1
How AIs are different from us level 1aiclub_slides
 

More from aiclub_slides (20)

Linear regression middleschool
Linear regression middleschoolLinear regression middleschool
Linear regression middleschool
 
Pa2 project template
Pa2 project templatePa2 project template
Pa2 project template
 
Knn intro advanced_middleschool
Knn intro advanced_middleschoolKnn intro advanced_middleschool
Knn intro advanced_middleschool
 
M1 regression metrics_middleschool
M1 regression metrics_middleschoolM1 regression metrics_middleschool
M1 regression metrics_middleschool
 
Pa1 json requests
Pa1 json requestsPa1 json requests
Pa1 json requests
 
Mnist images
Mnist imagesMnist images
Mnist images
 
Mnist images
Mnist imagesMnist images
Mnist images
 
Ai in real life face detection
Ai in real life   face detectionAi in real life   face detection
Ai in real life face detection
 
Cnn
CnnCnn
Cnn
 
Res net high level intro
Res net high level introRes net high level intro
Res net high level intro
 
Neural networks and flattened images
Neural networks and flattened imagesNeural networks and flattened images
Neural networks and flattened images
 
What is a_neural_network
What is a_neural_networkWhat is a_neural_network
What is a_neural_network
 
Introduction to deep learning image classification
Introduction to deep learning   image classificationIntroduction to deep learning   image classification
Introduction to deep learning image classification
 
Accuracy middleschool
Accuracy middleschoolAccuracy middleschool
Accuracy middleschool
 
Introduction to classification_middleschool
Introduction to classification_middleschoolIntroduction to classification_middleschool
Introduction to classification_middleschool
 
Introduction to the cloud
Introduction to the cloudIntroduction to the cloud
Introduction to the cloud
 
Basics of data
Basics of dataBasics of data
Basics of data
 
Ai basics
Ai basicsAi basics
Ai basics
 
Ai lifecycle and navigator
Ai lifecycle and navigatorAi lifecycle and navigator
Ai lifecycle and navigator
 
How AIs are different from us level 1
How AIs are different from us   level 1How AIs are different from us   level 1
How AIs are different from us level 1
 

Recently uploaded

microwave assisted reaction. General introduction
microwave assisted reaction. General introductionmicrowave assisted reaction. General introduction
microwave assisted reaction. General introductionMaksud Ahmed
 
The Most Excellent Way | 1 Corinthians 13
The Most Excellent Way | 1 Corinthians 13The Most Excellent Way | 1 Corinthians 13
The Most Excellent Way | 1 Corinthians 13Steve Thomason
 
_Math 4-Q4 Week 5.pptx Steps in Collecting Data
_Math 4-Q4 Week 5.pptx Steps in Collecting Data_Math 4-Q4 Week 5.pptx Steps in Collecting Data
_Math 4-Q4 Week 5.pptx Steps in Collecting DataJhengPantaleon
 
POINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptx
POINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptxPOINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptx
POINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptxSayali Powar
 
Industrial Policy - 1948, 1956, 1973, 1977, 1980, 1991
Industrial Policy - 1948, 1956, 1973, 1977, 1980, 1991Industrial Policy - 1948, 1956, 1973, 1977, 1980, 1991
Industrial Policy - 1948, 1956, 1973, 1977, 1980, 1991RKavithamani
 
Alper Gobel In Media Res Media Component
Alper Gobel In Media Res Media ComponentAlper Gobel In Media Res Media Component
Alper Gobel In Media Res Media ComponentInMediaRes1
 
Incoming and Outgoing Shipments in 1 STEP Using Odoo 17
Incoming and Outgoing Shipments in 1 STEP Using Odoo 17Incoming and Outgoing Shipments in 1 STEP Using Odoo 17
Incoming and Outgoing Shipments in 1 STEP Using Odoo 17Celine George
 
Science 7 - LAND and SEA BREEZE and its Characteristics
Science 7 - LAND and SEA BREEZE and its CharacteristicsScience 7 - LAND and SEA BREEZE and its Characteristics
Science 7 - LAND and SEA BREEZE and its CharacteristicsKarinaGenton
 
Contemporary philippine arts from the regions_PPT_Module_12 [Autosaved] (1).pptx
Contemporary philippine arts from the regions_PPT_Module_12 [Autosaved] (1).pptxContemporary philippine arts from the regions_PPT_Module_12 [Autosaved] (1).pptx
Contemporary philippine arts from the regions_PPT_Module_12 [Autosaved] (1).pptxRoyAbrique
 
Employee wellbeing at the workplace.pptx
Employee wellbeing at the workplace.pptxEmployee wellbeing at the workplace.pptx
Employee wellbeing at the workplace.pptxNirmalaLoungPoorunde1
 
Solving Puzzles Benefits Everyone (English).pptx
Solving Puzzles Benefits Everyone (English).pptxSolving Puzzles Benefits Everyone (English).pptx
Solving Puzzles Benefits Everyone (English).pptxOH TEIK BIN
 
A Critique of the Proposed National Education Policy Reform
A Critique of the Proposed National Education Policy ReformA Critique of the Proposed National Education Policy Reform
A Critique of the Proposed National Education Policy ReformChameera Dedduwage
 
Presiding Officer Training module 2024 lok sabha elections
Presiding Officer Training module 2024 lok sabha electionsPresiding Officer Training module 2024 lok sabha elections
Presiding Officer Training module 2024 lok sabha electionsanshu789521
 
“Oh GOSH! Reflecting on Hackteria's Collaborative Practices in a Global Do-It...
“Oh GOSH! Reflecting on Hackteria's Collaborative Practices in a Global Do-It...“Oh GOSH! Reflecting on Hackteria's Collaborative Practices in a Global Do-It...
“Oh GOSH! Reflecting on Hackteria's Collaborative Practices in a Global Do-It...Marc Dusseiller Dusjagr
 
Measures of Central Tendency: Mean, Median and Mode
Measures of Central Tendency: Mean, Median and ModeMeasures of Central Tendency: Mean, Median and Mode
Measures of Central Tendency: Mean, Median and ModeThiyagu K
 
PSYCHIATRIC History collection FORMAT.pptx
PSYCHIATRIC   History collection FORMAT.pptxPSYCHIATRIC   History collection FORMAT.pptx
PSYCHIATRIC History collection FORMAT.pptxPoojaSen20
 
Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...
Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...
Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...Krashi Coaching
 
Crayon Activity Handout For the Crayon A
Crayon Activity Handout For the Crayon ACrayon Activity Handout For the Crayon A
Crayon Activity Handout For the Crayon AUnboundStockton
 

Recently uploaded (20)

microwave assisted reaction. General introduction
microwave assisted reaction. General introductionmicrowave assisted reaction. General introduction
microwave assisted reaction. General introduction
 
The Most Excellent Way | 1 Corinthians 13
The Most Excellent Way | 1 Corinthians 13The Most Excellent Way | 1 Corinthians 13
The Most Excellent Way | 1 Corinthians 13
 
_Math 4-Q4 Week 5.pptx Steps in Collecting Data
_Math 4-Q4 Week 5.pptx Steps in Collecting Data_Math 4-Q4 Week 5.pptx Steps in Collecting Data
_Math 4-Q4 Week 5.pptx Steps in Collecting Data
 
POINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptx
POINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptxPOINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptx
POINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptx
 
Industrial Policy - 1948, 1956, 1973, 1977, 1980, 1991
Industrial Policy - 1948, 1956, 1973, 1977, 1980, 1991Industrial Policy - 1948, 1956, 1973, 1977, 1980, 1991
Industrial Policy - 1948, 1956, 1973, 1977, 1980, 1991
 
Model Call Girl in Tilak Nagar Delhi reach out to us at 🔝9953056974🔝
Model Call Girl in Tilak Nagar Delhi reach out to us at 🔝9953056974🔝Model Call Girl in Tilak Nagar Delhi reach out to us at 🔝9953056974🔝
Model Call Girl in Tilak Nagar Delhi reach out to us at 🔝9953056974🔝
 
Alper Gobel In Media Res Media Component
Alper Gobel In Media Res Media ComponentAlper Gobel In Media Res Media Component
Alper Gobel In Media Res Media Component
 
Incoming and Outgoing Shipments in 1 STEP Using Odoo 17
Incoming and Outgoing Shipments in 1 STEP Using Odoo 17Incoming and Outgoing Shipments in 1 STEP Using Odoo 17
Incoming and Outgoing Shipments in 1 STEP Using Odoo 17
 
Science 7 - LAND and SEA BREEZE and its Characteristics
Science 7 - LAND and SEA BREEZE and its CharacteristicsScience 7 - LAND and SEA BREEZE and its Characteristics
Science 7 - LAND and SEA BREEZE and its Characteristics
 
Contemporary philippine arts from the regions_PPT_Module_12 [Autosaved] (1).pptx
Contemporary philippine arts from the regions_PPT_Module_12 [Autosaved] (1).pptxContemporary philippine arts from the regions_PPT_Module_12 [Autosaved] (1).pptx
Contemporary philippine arts from the regions_PPT_Module_12 [Autosaved] (1).pptx
 
TataKelola dan KamSiber Kecerdasan Buatan v022.pdf
TataKelola dan KamSiber Kecerdasan Buatan v022.pdfTataKelola dan KamSiber Kecerdasan Buatan v022.pdf
TataKelola dan KamSiber Kecerdasan Buatan v022.pdf
 
Employee wellbeing at the workplace.pptx
Employee wellbeing at the workplace.pptxEmployee wellbeing at the workplace.pptx
Employee wellbeing at the workplace.pptx
 
Solving Puzzles Benefits Everyone (English).pptx
Solving Puzzles Benefits Everyone (English).pptxSolving Puzzles Benefits Everyone (English).pptx
Solving Puzzles Benefits Everyone (English).pptx
 
A Critique of the Proposed National Education Policy Reform
A Critique of the Proposed National Education Policy ReformA Critique of the Proposed National Education Policy Reform
A Critique of the Proposed National Education Policy Reform
 
Presiding Officer Training module 2024 lok sabha elections
Presiding Officer Training module 2024 lok sabha electionsPresiding Officer Training module 2024 lok sabha elections
Presiding Officer Training module 2024 lok sabha elections
 
“Oh GOSH! Reflecting on Hackteria's Collaborative Practices in a Global Do-It...
“Oh GOSH! Reflecting on Hackteria's Collaborative Practices in a Global Do-It...“Oh GOSH! Reflecting on Hackteria's Collaborative Practices in a Global Do-It...
“Oh GOSH! Reflecting on Hackteria's Collaborative Practices in a Global Do-It...
 
Measures of Central Tendency: Mean, Median and Mode
Measures of Central Tendency: Mean, Median and ModeMeasures of Central Tendency: Mean, Median and Mode
Measures of Central Tendency: Mean, Median and Mode
 
PSYCHIATRIC History collection FORMAT.pptx
PSYCHIATRIC   History collection FORMAT.pptxPSYCHIATRIC   History collection FORMAT.pptx
PSYCHIATRIC History collection FORMAT.pptx
 
Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...
Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...
Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...
 
Crayon Activity Handout For the Crayon A
Crayon Activity Handout For the Crayon ACrayon Activity Handout For the Crayon A
Crayon Activity Handout For the Crayon A
 

How neural networks learn part iii

  • 2. AI Club How Neural Networks Learn – Part III
  • 3. The Model The Network and Its Weights w1 1 w1 2w1 3 w1 4 w6 1 w6 2w6 3 w6 4 Real life Neural Networks can have hundreds of hidden layers and 1000s of neurons per layer, or more! This means millions or billions of weights!
  • 4. How do you learn the weights ? AI Algorithm Training DATA Examples of happy and sad MODE L = weights of the neural network AI Algorithm Prediction PREDICT ANSWE R “Happy” • Weights of a neural network are learnt during training
  • 5. How do you learn the weights? • Weights of a neural network are learnt during training • Weights are learnt using a mechanism called stochastic gradient descent (SGD)
  • 6. Parameters of a neural network • Learning rate: The rate at which you will make changes to your model weights • For example: if initial weight = 1, should the change to a weight value be 0.1 or 0.01 or 0.001 resulting in 1.1 or 1.01 or 1.001
  • 7. Parameters of a neural network • Learning rate: The rate at which you will make changes to your model weights • For example: if initial weight = 1, should the change to a weight value be 0.1 or 0.01 or 0.001 resulting in 1.1 or 1.01 or 1.001 • Mini-batch size: The number of samples that will be used to make a change to the weights. • For example: I will look at 10 sample images to understand how I should change my model weights.
  • 8. Parameters of a neural network • Learning rate: The rate at which you will make changes to your model weights • For example: if initial weight = 1, should the change to a weight value be 0.1 or 0.01 or 0.001 resulting in 1.1 or 1.01 or 1.001 • Mini-batch size: The number of samples that will be used to make a change to the weights. • For example: I will look at 10 sample images to understand how I should change my model weights. • Epochs: Number of times you will go through the entire data to make changes to the weights. • For example: If epochs = 5, I have looked at all samples 5 times and made changes to weights (5*(samples/Mini-batch size)) number of times.
  • 9. Let us look at these parameters a bit more • Learning rate: The rate at which you will make changes to your model weights • For example: if initial weight = 1, should the change to a weight value be 0.1 or 0.01 or 0.001 resulting in 1.1 or 1.01 or 1.001 • What happens if it is too high or too low?
  • 10.
  • 11. Let us look at these parameters a bit more ● Mini-batch size: The number of samples that will be used to make a change to the weights. ○ For example: I will look at 10 sample images to understand how I should change my model weights. • What happens if it is too high or too low? • Too high - not much benefit, takes a lot longer and cost more • Too low, may not get good results
  • 12. Let us look at these parameters a bit more ● Epochs: Number of times you will go through the entire data to make changes to the weights. ○ For example: If epochs = 5, I have looked at all samples 5 times and made changes to weights (5*(samples/Mini-batch size)) number of times. • What happens if it is too high or too low? • Too high - not much benefit, takes a lot longer and cost more • Too low, may not get good results