⚡️AI Bundle Pack 01⚡️
รวมไว้ให้แล้ว 🔥 คอร์สที่จะนำทุกท่านสู่ยุคสมัยของ AI อัจฉริยะ 🌏🤖 ทอัดแน่นด้วยเนื้อหามากกว่า 100 ชั่วโมง 🔥
.
สำหรับใครที่อยากเข้าใจการทำงานของ AI 🙌 แต่ไม่รู้จะเริ่มต้นที่ไหนดี❓เราขอแนะนำ AI Bundle Pack 01⚡️ คอร์สที่จะทำให้ท่านเข้าใจการทำงานของ AI ในระดับ advance 👑 ซงประกอบไปด้วย
.
🚀 AI ที่เรียนรู้ได้ด้วยตนเองจากข้อมูลทุกรูปแบบ ไม่ว่าจะเป็น ตาราง, รูปภาพ, วิดีโอ, เสียง, ข้อความ (Deep Learning)
🚀 AI ที่เรียนรู้ด้วยตนเองผ่านการลองผิดลองถูก (Reinforcement Learning)
🚀 AI ที่ผสานกำลังของทั้ง 2 อย่างมาไว้ด้วยกัน (Deep Reinforcement Learning)
.
📍ทำไมถึงควรเรียนกับเรา
– เรียบเรียงเนื้อหาอย่างพิถีพิถันและเป็นขั้นเป็นตอน 🗂
– อธิบายคณิตศาสตร์ที่ซับซ้อนด้วยภาพที่เข้าใจง่าย 📑
– มีตัวอย่างการคำนวณ เพื่อให้ท่านเข้าใจการทำงานของ AI อย่างละเอียด 🖊
– มี workshop เพื่อให้ท่านได้ฝึกฝน และเห็นตัวอย่างการนำไปใช้งานจริง 🖥
.
.
📚ใน AI Bundle Pack 01 จะประกอบไปด้วยคอร์ส
1. Deep Learning the Series (18,000 บาท)
2. Reinforcement Learning (21,000 บาท)
3. Deep Reinforcement Learning (19,900 บาท)
.
💥💥ในราคาสุดพิเศษเพียง 39,900 บาท (จาก 58,900 บาท)💥💥
.
วิธีการเรียน
– เรียนออนไลน์ผ่าน https://madebyai.io
– สามารถเรียนได้ตลอดชีวิต
.
🛒 สมัครเรียนได้ที่ https://madebyai.io/course/ai-bundle-pack-01/
.
🗣 สามารถดูรีวิวการสอนได้ที่ https://madebyai.io/reviews/
.
.
📕Deep Learning the Series
.
– Data Preparation
– Linear Regression
– Improvement of Linear Regression
– Workshop of Linear Regression
– Logistic Regression
– Improvement of Logistic Regression
– Workshop of Logistic Regression
– Neural Network
– Deep Learning
– Improvement of Deep Learning
– Workshop of Deep Learning
.
.
📗Reinforcement Learning
.
– Multi-Armed Bandit Problem
– Markov Decision Process
– Dynamic Programming
– Monte Carlo
– Temporal Difference
– N-step Temporal Difference
– Off-Policy
– Planning
.
.
📘Deep Reinforcement Learning
.
– Episodic and Continuing Tasks
– State-Value Function
– Action-Value Function
– Q-Table Improvement
– Deep Q Network
– Fixed Q-Targets
– Experience Replay
– Workshop of Deep RL
.
.
แล้วเจอกันในคลาสนะครับ 💖💖💖
Course Features
- Lectures 140
- Quizzes 0
- Duration Lifetime access
- Skill level All levels
- Language English
- Students 2
- Assessments Yes
-
Deep Learning the Series
- Week 1 – Welcome
- Week 1 – AI Overview
- Week 1 – Introduction
- Week 1 – Model Creation
- Week 1 – ตอบคำถาม SSE มีไว้ใช้ทำอะไร?
- Week 1 – Data Preparation
- Week 2 – Recap Week 1
- Week 2 – Model Evaluation for Regression
- Week 2 – Basic Workshop – Code Pipeline
- Week 2 – Basic Workshop – AI in Marketing
- Week 2 – Basic Workshop – AI in Investment
- Week 2 – Basic Workshop – Smart Farm
- Week 2 – ตอบคำถามนักเรียน
- Week 2 – Basic Workshop – AI in Rental Business
- Week 2 – Basic Workshop – AI in Insurance
- Week 3 – Model Improvement – Strong Assumption
- Week 3 – Model Improvement – Weak Assumption
- Week 3 – Model Improvement – Problem with Linearly Dependent
- Week 3 – ตอบคำถาม ข้อเสียของการ drop one hot
- Week 3 – Model Improvement – Solution
- Week 3 – Model Improvement – Regularization
- Week 3 – ตอบคำถาม Regularization
- Week 3 – Cross Validation
- Week 3 – Data Preparation – Feature Scaling
- Week 3 – Advanced Workshop
- Week 4 – Roadmap
- Week 4 – DL102 – Introduction
- Week 4 – LoR (2-class) – Introduction
- Week 4 – LoR (2-class) – Data
- Week 4 – LoR (2-class) – Model Creation part1
- Week 4 – LoR (2-class) – Model Creation part2
- Week 4 – LoR (2-class) – Prediction
- Week 4 – LoR (2-class) – Improvement
- Week 4 – Model Evaluation for Classification
- Week 4 – Workshop LoR (2-class) – Code Pipeline
- Week 4 – Workshop LoR (2-class) – AI in Healthcare
- Week 4 – Workshop LoR (2-class) – AI in Agriculture
- Week 4 – Workshop LoR (2-class) – Fake News
- week 5 – Recap – LoR (2-class)
- Week 5 – LoR (multi-class) – เกริ่นนำ
- Week 5 – LoR (multi-class) – Introduction – LoR with Multiclass
- Week 5 – LoR (multi-class) – Introduction – Why Softmax?
- Week 5 – LoR (multi-class) – Introduction – Extension to Neural Network
- Week 5 – LoR (multi-class) – Introduction – Real World Application
- Week 5 – ตอบคำถาม sigmoid vs softmax
- Week 5 – LoR (multi-class) – Data
- Week – LoR (multi-class) – Model
- Week 5 – LoR (multi-class) – Prediction
- Week 5 – LoR (multi-class) – Improvement
- Week 5 – Workshop LoR (multi-class) – AI in Fruit Industry
- Week 5 – Workshop LoR (multi-class) – AI in News Categorization
- Week 5 – Cross Entropy
- Week 6 – Roadmap
- Week 6 – DL103 – Introduction
- Week 6 – NN&DL – What is NN?
- Week 6 – NN&DL – Why we need NN?
- Week 6 – NN&DL – Real World Application
- Week 6 – NN&DL – Architecture of NN
- Week 6 – NN&DL – Component of NN
- Week 6 – NN&DL – How NN Work
- Week 6 – ตอบคำถาม decision boundary เปลี่ยนแปลงตามเวลาไหม?
- Week 6 – NN&DL – What is DL?
- Week 6 – NN&DL – Architecture of DL
- Week 6 – NN&DL – Component of DL
- Week 6 – NN&DL – Why we need DL?
- Week 6 – NN&DL – How DL Work
- Week 6 – DL for Regression
- Week 6 – DL for Binary Classification
- Week 6 – DL for Multiclass Classification
- Week 7 – Recap – NN&DL
- Week 7 – DL Workshop – Workflow
- Week 7 – DL Workshop – Overview
- Week 7 – DL Workshop – Code Pipeline Part1
- Week 7 – DL Workshop – Code Pipeline Part2
- Week 7 – DL Workshop – Code Pipeline Part3
- Week 7 – DL Workshop – AI in Civil Engineering
- Week 7 – DL Workshop – AI in Healthcare
- Week 7 – DL Workshop – AI in Skin Cancer
- Week 7 – ตอบคำถาม underfit & overfit คืออะไร?
- Week 7 – DL Interpretation – 1st Hidden Layer
- Week 7 – DL Interpretation – 2nd Hidden Layer
- Week 7 – DL Interpretation – 3rd Hidden Layer & Conclusion
- Week 7 – DL Interpretation – Conclusion & Adaptation
- Week 8 – Recap – DL Interpretation
- Week 8 – Improvement of DL – Overview
- Week 8 – Speed Up with GPU – What is GPU?
- Week 8 – Speed Up with GPU – How GPU Accelerate DL?
- Week 8 – Speed Up with GPU – Welcome to Colab
- Week 8 – Speed Up with GPU – Train Model with GPU
- Week 8 – Imbalanced Class
- Week 8 – L2, L1, Elastic Net
- Week 8 – Dropout Regularization part1
- Week 8 – Dropout Regularization part2
- Week 8 – Gradient Descent Variants
- Week 8 – Momentum
- Week 8 – Adagrad & RMSProp & Adam
- Week 8 – Advanced Workshop – Code Pipeline
- Week 8 – Advanced Workshop – AI in Real Estate Business
- Week 8 – Advanced Workshop – AI in Diagnosing Alzheimer’s
- Week 8 – Advanced Workshop – AI in Speech Recognition
- Week 8 – สรุปคอร์ส DL the Series
-
Reinforcement Learning
- Week 1 – Introduction + Multi-Armed Bandit Problem part1
- Week 1 – Multi-Armed Bandit Problem part2 + Markov Decision Process part1
- Week 2 – Markov Decision Process part2
- Week 3 – Markov Decision Process part3
- Week 3 – Dynamic Programming
- Week 4 – Monte Carlo
- Week 4 – Temporal Difference part1
- Week 5 – Temporal Difference part2
- Week 5 – n-step Temporal Difference
- Week 5 – Off-Policy + Roll Out
- Week 6 – Code of Reinforcement Learning
-
Deep Reinforcement Learning
- Document – Deep RL
- Introduction to Deep RL
- Fundamentals of RL – Core Concepts
- Fundamentals of RL – Markov Decision Process
- Fundamentals of RL – Episodic and Continuing Tasks
- Fundamentals of RL – The Reward Hypothesis
- Fundamentals of RL – Discounted Return
- RL Algorithms – Policy
- RL Algorithms – State-Value Function
- RL Algorithms – Action-Value Function
- RL Algorithms – RL Algorithms
- Q-learning – Introduction to Q-Learning
- Q-learning – Epsilon Greedy
- Q-learning – Q-Table Improvement
- Q-learning – Q-Learning Examples
- Deep Q-Networks – Introduction to DQN
- Deep Q-Networks – Deep Learning
- Deep Q-Networks – Deep Q Network
- Deep Q-Networks – Fixed Q-Targets
- Deep Q-Networks – Experience Replay
- Deep Q-Networks – DQN Algorithms
- DQN Code – Breakout Environment
- DQN Code – Import Libraries and Environment Setup
- DQN Code – DQN Implementation
- DQN Code – Training DQN
- DQN Code – Update DQN
- DQN Code – Step-by-Step Walkthrough
- DQN Code – Code Execution
