-
DL the Series ครั้งที่ 1 21
-
WelcomeLecture1.1
-
Map of Linear RegressionLecture1.2
-
AI Overview part1Lecture1.3
-
AI Overview part2Lecture1.4
-
AI Overview part3Lecture1.5
-
Introduction – What is Linear Regression?Lecture1.6
-
Introduction – Extension to Neural NetworkLecture1.7
-
Introduction – Real World ApplicationLecture1.8
-
Model Creation – Data – Data StatingLecture1.9
-
Model Creation – Data – Data RequirementLecture1.10
-
Model Creation – Model – AssumptionLecture1.11
-
Model Creation – Model – Real Face of the ModelLecture1.12
-
Model Creation – Model – Cost FunctionLecture1.13
-
Model Creation – Model – How to Create Model (math) part1Lecture1.14
-
Model Creation – Model – How to Create Model (math) part2Lecture1.15
-
Model Creation – Model – How to Create Model (code)Lecture1.16
-
Model Creation – Model – Further ReadingLecture1.17
-
Model Creation – PredictionLecture1.18
-
Data Prepration – NaNLecture1.19
-
Data Preparation – OutlierLecture1.20
-
Data Preparation – Feature EncodingLecture1.21
-
-
DL the Series ครั้งที่ 2 20
-
Recap ครั้งที่1Lecture2.1
-
Model Evaluation – Introduction & R2Lecture2.2
-
Model Evaluation – MSELecture2.3
-
Model Evaluation – MAELecture2.4
-
Model Evaluation – MAPELecture2.5
-
Model Evaluation – ConclusionLecture2.6
-
ตอบคำถามนักเรียน เหตุผลที่ performance ต่างกันทั้งสร้างด้วย model เดียวกันLecture2.7
-
Basic Workshop – Supervised Learning WorkflowLecture2.8
-
Basic Workshop – CP – Import LibrariesLecture2.9
-
Basic Workshop – CP – Read DataLecture2.10
-
Basic Workshop – CP – Clean DataLecture2.11
-
Basic Workshop – CP – Split Dataset into Traing & Test SetsLecture2.12
-
Basic Workshop – CP – Data PreparationLecture2.13
-
Basic Workshop – CP – Create Model & PredictionLecture2.14
-
Basic Workshop – CP – Model EvaluationLecture2.15
-
Basic Workshop – AI in MarketingLecture2.16
-
Basic Workshop – AI in InvestmentLecture2.17
-
Basic Workshop – Smart FarmLecture2.18
-
Basic Workshop – AI in BusinessLecture2.19
-
Basic Workshop – AI in InsuranceLecture2.20
-
-
DL the Series ครั้งที่ 3 18
-
Recap ครั้งที่2Lecture3.1
-
Assumption – Linear RelationshipLecture3.2
-
Assumption – Normality of ResidualsLecture3.3
-
Assumption – HomoscedasticityLecture3.4
-
Check Assumption & วิธีการจัดการเมื่อไม่ตรง AssumptionLecture3.5
-
อธิบายแนวทางการสอน Strong AssumptionLecture3.6
-
Assumption – No Missing Feature & Feature ImportanceLecture3.7
-
Assumption – No MulticollinearityLecture3.8
-
Problem with Linearly DependentLecture3.9
-
Solution part1Lecture3.10
-
Solution part2Lecture3.11
-
Regularization – What is Regularization?Lecture3.12
-
Regularization – Ridge Regression part1Lecture3.13
-
Regularization – Ridge Regression part2Lecture3.14
-
Regularization – Lasso Regression part1Lecture3.15
-
Regularization – Lasso Regression part2Lecture3.16
-
Regularization – Elastic NetLecture3.17
-
Regularization – ConclusionLecture3.18
-
-
DL the Series ครั้งที่ 4 28
-
Recap ครั้งที่3Lecture4.1
-
ตอบคำถามนักเรียน – ridge, lasso, elastic แก้ปัญหาอะไรบ้าง?Lecture4.2
-
Cross Validation – OverviewLecture4.3
-
Cross Validation – What is CV?Lecture4.4
-
Cross Validation – Step to CalculateLecture4.5
-
ตอบคำถามนักเรียน – จำนวน fold ที่นิยมใช้เป็นเท่าไหร่? & performance ของแต่ละ fold คิดอย่างไร?Lecture4.6
-
Cross Validation – Advantage of CVLecture4.7
-
Cross Validation – Extension (Special Topic)Lecture4.8
-
Cross Validation – ConclusionLecture4.9
-
Feature Scaling – Overview & What is Feature Scaling?Lecture4.10
-
Feature Scaling – Why need Feature Scaling?Lecture4.11
-
Feature Scaling – StandardizationLecture4.12
-
Feature Scaling – Min-Max ScalingLecture4.13
-
Feature Scaling – ConclusionLecture4.14
-
ตอบคำถามนักเรียน – ถ้าทำ feature scaling แล้วไปสร้าง linear regression จะเกิดปัญหาไหม?Lecture4.15
-
Advanced Workshop – Car PriceLecture4.16
-
AI102 – OverviewLecture4.17
-
LoR (2-class) – Introduction – What is LoR?Lecture4.18
-
ตอบคำถามนักเรียน – ตัวอย่างการคำนวณ z และ yhat ของ LoRLecture4.19
-
LoR (2-class) – Introduction – Extension to Neural NetworkLecture4.20
-
LoR (2-class) – Introduction – Real World ApplicationLecture4.21
-
LoR (2-class) – DataLecture4.22
-
LoR (2-class) – Model – AssumptionLecture4.23
-
LoR (2-class) – Model – Real Face of the ModelLecture4.24
-
LoR (2-class) – Model – Cost Function & Cost LandscapeLecture4.25
-
LoR (2-class) – Model – How to Create Model – Problem with LSMLecture4.26
-
LoR (2-class) – Model – How to Create Model – Gradient DescentLecture4.27
-
ให้กำลังใจนักเรียน – trade-off & potential ของ Machine LearningLecture4.28
-
-
DL the Series ครั้งที่ 5 27
-
Recap ครั้งที่4Lecture5.1
-
Recap – How to Create ModelLecture5.2
-
LoR (2-class) – Model – How to Create Model – Calculation ExampleLecture5.3
-
LoR (2-class) – Model – How to Create Model (Code)Lecture5.4
-
เล่าเรื่อง – Machine Learning ทุกรูปแบบLecture5.5
-
LoR (2-class) – Prediction – 1-sampleLecture5.6
-
LoR (2-class) – Prediction – multi-sampleLecture5.7
-
LoR (2-class) – Prediction – CodeLecture5.8
-
LoR (2-class) – Improvement – Imbalanced ClassLecture5.9
-
LoR (2-class) – Improvement – RegularizationLecture5.10
-
ตอบคำถามนักเรียน – w ใน LoR มีสิทธิมีหลายคำตอบใช่ไหม?Lecture5.11
-
Model Evaluation – IntroductionLecture5.12
-
Model Evaluation – Confusion MatrixLecture5.13
-
Model Evaluation – AccuracyLecture5.14
-
Model Evaluation – PrecisionLecture5.15
-
Model Evaluation – RecallLecture5.16
-
Model Evaluation – F1 ScoreLecture5.17
-
Model Evaluation – ConclusionLecture5.18
-
Workshop of LoR (2-class) – Supervised Learning WorkflowLecture5.19
-
Workshop of LoR (2-class) – Code Pipeline part1Lecture5.20
-
Workshop of LoR (2-class) – Code Pipeline part2Lecture5.21
-
Workshop of LoR (2-class) – Code Pipeline part3Lecture5.22
-
ตอบคำถามนักเรียน – ต้องเลือกว่าจะให้ positive เป็น accept หรือ reject ใช่ไหม?Lecture5.23
-
ตอบคำถามนักเรียน – เราเลือก positive จาก class ที่ให้ score สูง ๆ ใช่ไหม?Lecture5.24
-
Workshop of LoR (2-class) – AI in HealthcareLecture5.25
-
Workshop of LoR (2-class) – AI in AgricultureLecture5.26
-
Workshop of LoR (2-class) – Fake NewsLecture5.27
-
-
DL the Series ครั้งที่ 6 27
-
Recap ครั้งที่5Lecture6.1
-
LoR (multi-class) – OverviewLecture6.2
-
LoR (multi-class) – Introduction – Concept part1Lecture6.3
-
LoR (multi-class) – Introduction – Concept part2Lecture6.4
-
ตอบคำถามนักเรียน – เราสามารถใช้ softmax กับปัญหา 2 class ได้ไหม?Lecture6.5
-
LoR (multi-class) – Introduction – Why Softmax?Lecture6.6
-
LoR (multi-class) – Introduction – Extension to Neural NetworkLecture6.7
-
LoR (multi-class) – Introduction – Real World ApplicationLecture6.8
-
LoR (multi-class) – Data – Stating & RequirementLecture6.9
-
LoR (multi-class) – Data – More about TargetLecture6.10
-
LoR (multi-class) – Model – Assumption & Real Face of the ModelLecture6.11
-
LoR (multi-class) – Model – Cost Function & Cost LandscapeLecture6.12
-
LoR (multi-class) – Model – How to Create Model part1Lecture6.13
-
LoR (multi-class) – Model – How to Create Model part2Lecture6.14
-
LoR (multi-class) – Model – How to Create Model part3Lecture6.15
-
LoR (multi-class) – Model – How to Create Model part4Lecture6.16
-
LoR (multi-class) – Model – How to Create Model (Code)Lecture6.17
-
LoR (multi-class) – Model – ConclusionLecture6.18
-
LoR (multi-class) – Prediction – 1-sampleLecture6.19
-
LoR (multi-class) – Prediction – multi-sample & CodeLecture6.20
-
LoR (multi-class) – ImprovementLecture6.21
-
Workshop of LoR (multi-class) – SL WorkflowLecture6.22
-
Workshop of LoR (multi-class) – AI in Fruit IndustryLecture6.23
-
Workshop of LoR (multi-class) – AI in News CategorizationLecture6.24
-
Cross Entropy – OverviewLecture6.25
-
Cross Entropy – What is KL DivergenceLecture6.26
-
Cross Entropy – KL as Cost FunctionLecture6.27
-
-
DL the Series ครั้งที่ 7 30
-
Map of this CourseLecture7.1
-
AI103 – OverviewLecture7.2
-
NN&DL – What is Neural Network?Lecture7.3
-
NN&DL – Why we need Neural NetworkLecture7.4
-
NN&DL – Real World ApplicationLecture7.5
-
NN&DL – Architecture of Neural NetworkLecture7.6
-
NN&DL – Component of NN part1Lecture7.7
-
NN&DL – Component of NN part2Lecture7.8
-
NN&DL – Component of NN part3Lecture7.9
-
NN&DL – Component of NN part4Lecture7.10
-
NN&DL – How Neural Network WorkLecture7.11
-
NN&DL – What is Deep Learning?Lecture7.12
-
NN&DL – Architecture of Deep LearningLecture7.13
-
NN&DL – Component of DLLecture7.14
-
NN&DL – Why we need Deep LearningLecture7.15
-
ตอบคำถามนักเรียน – การจะใช้ DL ต้องมี input จำนวนมาก ๆ เพื่อให้แม่นยำไหม?Lecture7.16
-
ตอบคำถามนักเรียน – เมื่อเทียบกันระหว่าง NN กับ DL ทรัพยากรเครื่องที่ใช้ต่างกันเท่าไหร่?Lecture7.17
-
ตอบคำถามนักเรียน – เราสามารถพูดได้เลยไหมว่า DL ดีกว่า NN?Lecture7.18
-
NN&DL – How Deep Learning WorkLecture7.19
-
DL for Regression part1Lecture7.20
-
DL for Regression part2Lecture7.21
-
DL for Regression part3Lecture7.22
-
DL for Regression part4Lecture7.23
-
DL for Binary Classification part1Lecture7.24
-
DL for Binary Classification part2Lecture7.25
-
DL for Binary Classification part3Lecture7.26
-
DL for Multi-Class Classification part1Lecture7.27
-
DL for Multi-Class Classification part2Lecture7.28
-
DL for Multi-Class Classification part3Lecture7.29
-
ทบทวนเนื้อหา ครั้งที่7Lecture7.30
-
-
DL the Series ครั้งที่ 8 21
-
Recap ครั้งที่7Lecture8.1
-
Supervised Learning อย่างละเอียดLecture8.2
-
Basic Workshop of NN&DL – Workshop OverviewLecture8.3
-
Basic Workshop of NN&DL – Code Pipeline part1Lecture8.4
-
Basic Workshop of NN&DL – Code Pipeline part2Lecture8.5
-
Basic Workshop of NN&DL – Code Pipeline part3Lecture8.6
-
Basic Workshop of NN&DL – Code Pipeline part4Lecture8.7
-
Basic Workshop of NN&DL – Code Pipeline part5Lecture8.8
-
Basic Workshop of NN&DL – AI in Civil EngineeringLecture8.9
-
Basic Workshop of NN&DL – AI in HealthcareLecture8.10
-
Basic Workshop of NN&DL – AI in Skin CancerLecture8.11
-
DL Interpretation – ObjectiveLecture8.12
-
DL Interpretation – Effect of Number of Node in 1st HL part1Lecture8.13
-
DL Interpretation – Effect of Number of Node in 1st HL part2Lecture8.14
-
DL Interpretation – Effect of Number of Node in 1st HL part3Lecture8.15
-
DL Interpretation – Effect of Number of Node in 2nd HLLecture8.16
-
DL Interpretation – Effect of Number of Node in 3rd HLLecture8.17
-
DL Interpretation – Conclusion part1Lecture8.18
-
DL Interpretation – Conclusion part2Lecture8.19
-
DL Interpretation – AdaptationLecture8.20
-
ตอบคำถามนักเรียน – ทำความเข้าใจ 2nd HL ให้มากขึ้นLecture8.21
-
This content is protected, please login and enroll course to view this content!