• Natural Language Processing (NLP)
  • Natural Language Processing
  • Machine Translation
  • From Linguistics to Formal Grammars (Automata)
  • Text Processing & BERT
    Question & Ansering Thai BERT
  • Web Scraping and Document Classification
• Image Processing
  • Introduction and Advanced Image processing
  • Computer vision
  • Introduction to Point Cloud (Digital Geometry Processing)
  • Introduction to Point Cloud (2D-3D Reconstruction)
  • Introduction to Point Cloud (3D Deep Learning and PointNet)
• Internet of Things and Robotics
  • Arm Robotics and Robot Kinematics
  • Introduction and Advanced Internet of Things
• Data Science
  • Finance on Reinforcement Learning
  • Stock Manipulation
• Signal Processing
  • Automatic Speech Recognition (ASR)
• Machine Learning
  • Machine Learning
  • Advanced Machine Learning
  • Ensemble Method
  • One-Class Classification
  • Principal Component Analysis (PCA)
• Deep Learning
  • Introduction Deep Learning
  • Advanced Deep Learning
• Mathematics for AI
  • Introduction Mathematics for AI
  • Advanced Mathematics for AI
• Programming and Tools
  • Basic of Python Programming
  • Introduction to Linux
  • Introduction to Kaggle
  • Introduction to Google Colab
  • Introduction to GitHub
  • Microservices and Docker Compose
  • Introduction to Docker
  • Introduction to Deployment

Natural Language Processing (NLP)

Natural Language Processing (2 Hours)

ID	Description
Module 1	Introduction to NLP / Text preprocessing / Tokenisation/ Named Entity Recognition
Module 2	Syntax, Grammars and Parsing Techniques
Module 3	Features, Augmented Grammars, and Its Application
Module 4	Parsing Preference/Deterministic Parsing/Lexicalized and Probabilistic Parsing
Module 5	Regular Expression, Morphology and Finite-State Transducers
Module 6	N-gram and Part-of-Speech Tagging/Word Sense Disambiguation
Module 7	Semantics and Logical Form – Linking Syntax and Semantics/ Local Discourse and Reference
Module 8	HMM and Speech Recognition / Applications: Question Answering & Machine Translation

---

Machine Translation (3 Hours)

ID	Description
Module 1	Introduction to Machine Translation
Module 2	Rule-based Machine Translation / Corpus-based Machine Translation
Module 3	Statistical Machine Translation
Module 4	Neural Machine Translation
Module 5	Neural Machine Translation with Attention
Module 6	Transformer for MT
Module 7	Machine Translation Evaluation
Module 8	Data Preparation for MT

---

From Linguistics to Formal Grammars (Automata) (3 Hours)

ID	Description
Module 1	Linguistics as Pattern Observation
Module 2	Formal Language / Chomsky Hierarchy of Formal Grammars
Module 3	Regular Languages
Module 4	Context-Free Language
Module 5	Mildly Context-Sensitive Languages
Module 6	Context-Sensitive
Module 7	Recursively Enumerable Language
Module 8	Pumping Lemmas

---

Text Processing & BERT
Question & Ansering Thai BERT (5 Hours)

ID	Description
Module 1	NLP Transformer
Module 2	Feature Representation / Sequence Models and Seq2Seq Model
Module 3	Encoder and Decoder Performance / Inside Encoder and Decoder
Module 4	GPT-1/ BERT: Theory / Task Specific Methods / Practical / Fine Tuning
Module 5	Other Transformer-based Models and GPT-2
Module 6	Introduction to BERT / BERT for QA Model and Huggingface / Tokenization and Pipeline
Module 7	Text Classification with Wongnai Dataset
Module 8	Text Classification with Custom Dataset / Thai Automatic Question Answering

---

Web Scraping and Document Classification (3 Hours)

ID	Description
Module 1	Overview Web Scraping
Module 2	Basic HTML Document and Web Scraping
Module 3	Regular Expressions with Python
Module 4	Document Classification
Module 5	Preprocessing and Problems
Module 6	Topic Modeling and Tag Suggestion
Module 7	Phishing Web Detection and Sentiment Analysis
Module 8	Document Classification Workshop

---

Image Processing

Introduction and Advanced Image processing (3 Hours)

ID	Description
Module 1	Basic image processing Color, Light, and Image Formation
Module 2	Convolution / Image Gradient / Corner Detection / SIFT
Module 3	Histogram Equalization
Module 4	Integral Image
Module 5	Local Intensity Distribution Equalization (LIDE)
Module 6	Maximum Likelihood
Module 7	Mixture Model
Module 8	Pixel Sorting

---

Computer vision (2 Hours)

ID	Description
Module 1	What is Computer Vision
Module 2	Mathematics for Computer Vision
Module 3	Filters, Contrast, Transformation, and Morphology
Module 4	Image restoration, Sizing, Noise, Segmentation, and Contours
Module 5	Color Detection / Background Subtraction: With Background /
Module 6	Adding Noises / Background Subtraction: Without Background
Module 7	Line Sensor / Perspective Transform
Module 8	Example of Computer Vision

---

Introduction to Point Cloud (Digital Geometry Processing) (2 Hours)

ID	Description
Module 1	Introduction of Point Cloud
Module 2	How is Point Cloud Generated
Module 3	What Format is Point Cloud Stored
Module 4	Point Cloud Processing: Registration and Keypoints
Module 5	Feature Descriptors
Module 6	Correspondences Estimation
Module 7	Transformation Estimation
Module 8	Applications and Tools

---

Introduction to Point Cloud (2D-3D Reconstruction) (3 Hours)

ID	Description
Module 1	Point Cloud Registration / 2D to 3D Registration
Module 2	Camera and object motion tracking
Module 3	Feature Extraction and Matching
Module 4	2D to 3D Reconstruction and Surface Reconstruction
Module 5	Explicit and Implicit Surface
Module 6	2D to 3D Reconstruction and Vanilla ICP
Module 7	Normalization Depth and World Origin
Module 8	Tools and Pytorch 3D / 3D Machine Learning, 3D Dataset and ABC / VoxelNet and Geometric Deep learning

---

Introduction to Point Cloud (3D Deep Learning and PointNet) (2 Hours)

ID	Description
Module 1	Introduction 3D Deep Learning and voxel-based
Module 2	Point-based and Graph-based
Module 3	Point Net – Introduction and Input / Embedding Space, OOS and Result
Module 4	Generating Mesh-based Shapes From learned latent of Point Cloud with VAE-GAN
Module 5	Point Attention Network for Gesture Recognition Using Point Cloud Data
Module 6	Gather, Scatter, and Mesh base / Keypoint 3D and VAE-GAN
Module 7	Library Installation and Data Processing / Pytorch-geometric Concept, Data Loader and Model Function / Create Dataset Using Pytorch
Module 8	Model Deployment / Dynamic Graph CNN for Learning on Point Clouds Model / Message Passing Networks

---

Internet of Things and Robotics

Arm Robotics and Robot Kinematics (6 Hours)

ID	Description
Module 1	Introduction to Robotics / The basic principles of robotics
Module 2	Robot Types
Module 3	Introduction to Robot Mechanics
Module 4	Robot Controller
Module 5	Sensors and actuators
Module 6	Overview Introduction to Robot Kinematics
Module 7	The Fundamental Concepts of Kinematics
Module 8	Notation and Matrix Representation

---

Introduction and Advanced Internet of Things (6 Hours)

ID	Description
Module 1	Smart IoT Device / IoT Introduction & Computing System / The Internet of Things
Module 2	IoT Components / IoT & AIoT Concept / Embedded Board & Programming Languages
Module 3	Arduino Introduction / Basic I/O / Simulator – Digital Input-Output / Analog (Input, Output)
Module 4	IoT Connectivity / IoT Application
Module 5	Tool and Supplements / IoT Network Protocol
Module 6	Setup Docker Desktop / Case Study: Temp/Humid Monitoring and Control
Module 7	Node-RED Simulation / Node-RED Brain Process
Module 8	Databases / Grafana

---

Data Science

Finance on Reinforcement Learning (2 Hours)

ID	Description
Module 1	Introduction Machine Learning in Finance
Module 2	Reinforcement Learning (RL) Concept
Module 3	Markov Decision Process (MDP), Task, Value Functions, and Optimum Policy
Module 4	How to solve RL Problem (Dynamic Programing)
Module 5	Q-Learning
Module 6	Policy Gradient RL
Module 7	Rewards & BackTest
Module 8	RL Architecture and Other RL

---

Stock Manipulation (2 Hours)

ID	Description
Module 1	Introduction Recurrent Neural Network (RNN) – Introduction RNN
Module 2	RNN, Type of RNN and Applications
Module 3	Backpropagation Through Time(BPTT) and Long Short Term Memory(LSTM)
Module 4	Activity: understand how RNN works?
Module 5	Word2Vec Model, Language Translation and Problem
Module 6	Attention Mechanism(Self-Attention)
Module 7	Transformer / Detection of Stock Manipulation
Module 8	Machine Learning for Manipulation Detection

---

Signal Processing

Automatic Speech Recognition (ASR) (4 Hours)

ID	Description
Module 1	Introduction to Automatic Speech Recognition
Module 2	Speech recognizer
Module 3	ASR Technique and Partii Demo
Module 4	Basic structure ASR System
Module 5	KALDI – Introduction
Module 6	Example script – common voice
Module 7	Data preparation: Thai syllable system
Module 8	Language model preparation

---

Machine Learning

Machine Learning (6 Hours)

ID	Description
Module 1	Introduction of Machine Learning
Module 2	Pre-machine learning: rule-base/ Supervised Learning/ Unsupervised Learning / Linear Regression: Loss Function
Module 3	Evaluation, Labeling, Matrics, and Error / K-means Clustering and KNN Classification
Module 4	The centroid for Cosine Similarity / Selecting-K, Variance and Hierarchical Clustering
Module 5	Other Flavors of Supervision and Reinforcement Learning / self-supervised
Module 6	Model Selection and Literature Review / My Personal Picks (Regression, KNN, XGboost, DL)
Module 7	Data size and Class Imbalance
Module 8	Bias, Variance and Double Descent Problem / Diagnosis

---

Advanced Machine Learning (2 Hours)

ID	Description
Module 1	SVM and Kernel Methods
Module 2	Kernel Function / Dual and Kernel Perceptron
Module 3	Margin and Generalization
Module 4	Dual Problem
Module 5	Maximum Margin Classifier
Module 6	Support Vector Machine(SVM)
Module 7	Kernel Principal Component Analysis (PCA)
Module 8	Fancy Kernel

---

Ensemble Method (1 Hours)

ID	Description
Module 1	Introduction to Ensemble Method
Module 2	Bagging Method
Module 3	Decision Tree and Random Forest
Module 4	Splitting Strategy
Module 5	Training Model
Module 6	Prediction and Evaluation

---

One-Class Classification (3 Hours)

ID	Description
Module 1	Introduction and Anomaly Detection
Module 2	Outlier
Module 3	Overview One-Class Classification
Module 4	Structure One-Class Classification
Module 5	None One-Class Support Vector Machine
Module 6	Generative Adversarial Network (GAN)
Module 7	Deep One-Class Classification
Module 8	Applications: Example 1-4 and Conclusion

---

Pricipal Component Analysis (PCA) (3 Hours)

ID	Description
Module 1	Matrix and Vector
Module 2	Subspace Projection and Variance
Module 3	Principal Component Analysis (PCA) / Lagrangian
Module 4	PCA Axes Selection / PCA Algorithm and Reconstruction Error
Module 5	Eigen-Decomposition: Jacobi Method
Module 6	PCA: For Small and Large Sample Size Data
Module 7	Kernel PCA (KPCA) / Kernel Trick and Summary of KPCA / How to Apply KPCA to Set of 10,000 Vectors
Module 8	Related Techniques

---

Deep Learning

Introduction Deep Learning (5 Hours)

ID	Description
Module 1	Introduction to TensorFlow
Module 2	Overview of Neural Networks
Module 3	Loss Function / Back Propagation / Activation Functions
Module 4	Tensor Operations / Linear and Nonlinear Regression
Module 5	Deep Learning and MNIST Dataset / One-Hot Encoder and Muti-Layer Perceptron (MLP)
Module 6	2D Discrete Cross-correlation / Convolutional Neural Network (CNN) / 2D Convolutional layer / The First CNN: LeNet5
Module 7	Transfer Learning and Example Transfer Learning
Module 8	Deeper Network: VGG, Adam and Example VGG16

---

Advanced Deep Learning (4 Hours)

ID	Description
Module 1	Transfer learning – VGG16
Module 2	Autoencoder Feature Extraction and Encoder, Reconstructor and Combine feature
Module 3	Autoencoder: Convolutional Neural Network (CNN) UpSampling 2D and Denoising
Module 4	Semantic Segmentation (SegNet) Batch Normalization / Lung Sementation (SegNet) U-Net and Dropout / Residual Neural Network (ResNet)
Module 5	CIFAR – 10 (Datasets) / Traditional
Module 6	Generative Adversarial Networks (GANs) / Super Resolution GAN (SRGAN)
Module 7	Audio (STFT, MFCC) Example Audio Recognition (CNN)
Module 8	Time series, Simple NN Example Stock Prediction
Module 9	Text: Feature Extraction Word2Vec, RNN, and LSTM
Module 10	Example: Colab Code Audio, Time serial, and Text

---

Mathematics for AI

Introduction Mathematics for AI (3 Hours)

ID	Description
Module 1	Machine Learning Introduction
Module 2	Linear Algebra: Vector and Matrix
Module 3	Linear Algebra : Transformation & Determinant
Module 4	Linear Algebra: Eigenvectors
Module 5	Linear Algebra: Singular Value Decomposition (SVD)
Module 6	Probability: Basics of Probability and Weighted and Unweighted
Module 7	Calculus: Differential and Integral
Module 8	Statistical

---

Advanced Mathematics for AI (2 Hours)

ID	Description
Module 1	Features
Module 2	Loss Function
Module 3	Binary Cross-Entropy Loss
Module 4	Maximum Likelihood
Module 5	Linear Classifier
Module 6	Multinomial Model
Module 7	High Dimensional Data

---

Programming and Tools

Basic of Python Programming (2 Hours)

ID	Description
Module 1	Python Setup / Fundamental Data Types / Comparison and Logical Operators
Module 2	Control Flow Statements / IF-Then Statements
Module 3	Loops
Module 4	Built-in Python Expressions / Functions
Module 5	Classes & Objects
Module 6	Import Library
Module 7	Inputs and Outputs
Module 8	Files

---

Introduction to Linux (2 Hours)

ID	Description
Module 1	Linux Structure and Installation
Module 2	User Environment/ Text Editors/ Command-line Operations
Module 3	Local Security Principles / Network Operations
Module 4	Manipulating Text / Bash Shell Scripting / Advanced Bash Shell Scripting
Module 5	Processes
Module 6	Finding Linux Documentation
Module 7	File Operations
Module 8	Common Applications

---

Introduction to Kaggle (30 Minutes)

ID	Description
Module 1	Introduction to Kaggle
Module 2	Advanced to Kaggle
Module 3	Competition to Kaggle
Module 4	Kaggle Hands-on

---

Introduction to Google Colab (1 Hours)

ID	Description
Module 1	Introduction to Google Colab
Module 2	Google Colab Tour
Module 3	Basic Uses
Module 4	Advanced Uses and Conclusion
Module 5	Google Colab Hands-on

---

Introduction to GitHub (1 Hours)

ID	Description
Module 1	Introduction to GitHub and Version Control (Including Git installation)
Module 2	Text Editor and Extension
Module 3	Git Using in Project and Basic Commands
Module 4	Branch
Module 5	Github Registration and Authentication
Module 6	Github Repository Management

---

Microservices and Docker Compose (4 Hours)

ID	Description
Module 1	Introduction Microservice / Microservice as RESTful APIs / API Gateway
Module 2	Event-driven Communication, Secure Microservices, Data Management, Event Communication
Module 3	Success Factor and Grafana
Module 4	Introduction to Docker, Build and Run
Module 5	Old Style Deploy, The Matrix of Hell, Container Isolation, Glossary
Module 6	Install Docker, Command, and Network
Module 7	Docker Image / Docker-compose / Services / Networks, Volumes, Docker-compose
Module 8	Example and Showcase of Docker-compose

---

Introduction to Docker (2 Hours)

ID	Description
Module 1	Introduction Microservice / Microservice as RESTful APIs / API Gateway
Module 2	Event-driven Communication, Secure Microservices, Data Management, Event Communication
Module 3	Success Factor and Grafana
Module 4	Introduction to Docker, Build and Run
Module 5	Old Style Deploy, The Matrix of Hell, Container Isolation, Glossary
Module 6	Install Docker, Command, and Network
Module 7	Docker Image / Docker-compose / Services / Networks, Volumes, Docker-compose
Module 8	Example and Showcase of Docker-compose

---

Introduction to Deployment (2 Hours)

ID	Description
Module 1	Introduction to Application Programming Interface (API) and Deployment
Module 2	API Development with Python and Flask
Module 3	Machine Learning Model with Python
Module 4	Machine learning as a Service Development with API
Module 5	Testing API with Postman