decentralized-ai
Tutorials & Insights
Thoughtful guides to help you get the most out of AIOZ AI R&D. Created and curated by the AIOZ AI team.
Decentralized AI
Take AIOZ AI Network from zero to production.
decentralized-ai
2. Introduction to Federated Learning.
decentralized-ai
3. Network Sytem and data silos for Federated Learning.
decentralized-ai
4. Topologies in Decentralized Federated Learning.
decentralized-ai
5. Smart Routing.
decentralized-ai
6. AI-driven routing (part 1) Centralized Routing.
decentralized-ai
7. AI-driven routing (part 2) Decentralize Routing.
decentralized-ai
8. AI-driven routing (part 3) Hybrid Routing.
decentralized-ai
9. AI-driven routing (part 4) Smart Routing Effectiveness.
decentralized-ai
10. AI-driven routing (part 5) Challenges and Open Issues.
decentralized-ai
11. Smart Caching.
decentralized-ai
12. Smart Transcoding (part 1) Introduction.
decentralized-ai
13. Smart Transcoding (part 2) Video Transcoding and Delivery with Blockchain.
decentralized-ai
14. Smart Transcoding (part 3) Three-stage STACKELBERG game.
decentralized-ai
15. Smart Transcoding (part 4) Effectiveness Evaluation.
decentralized-ai
16. Video Compression (Part 1)
decentralized-ai
17. Video Compression (Part 2)
decentralized-ai
18. Decentralized Federated Learning and Research Directions (Part 1).
decentralized-ai
19. Decentralized Federated Learning and Research Directions (Part 2).
decentralized-ai
20. Foundation Model and Federated Learning (part 1).
decentralized-ai
21. Foundation Model and Federated Learning (Part 2).
decentralized-ai
22. Federated Learning as a Paradigm Shift in Data Privacy.
decentralized-ai
23. Homomorphic Encryption as the Pillar of Secure Collaboration.
decentralized-ai
24. Combining Federated Learning and Homomorphic Encryption.
Computer Vision
If We Want Machines to Think, We Need to Teach Them to See.
computer-vision
1. Visual Question Reasoning
computer-vision
2. A quick guide on principal component analysis
computer-vision
3. Exemplar Geometry-Aware Neural Style Transfer
computer-vision
4. Pose-Controllable Talking Face Generation (part 1)
computer-vision
5. Pose-Controllable Talking Face Generation (part 2)
computer-vision
6. Video recognition and categorization (Part 1 - Introduction)
computer-vision
7. Video recognition and categorization (Part 2 - Datasets and Evaluate Metrics)
computer-vision
8. Video recognition and categorization (Part 3 - Applying RNN)
computer-vision
9. Video recognition and categorization (Part 4 - Applying Deep Learning)
computer-vision
10. Video recognition and categorization (Part 5 - Applying Deep Learning (cont.))
computer-vision
11. Video recognition and categorization (Part 6 - A basic tutorial)
computer-vision
12. Exemplar Geometry-Aware Neural Style Transfer (Part2)
computer-vision
13. Representation Learning
computer-vision
14. Abnormal Human Activity Recognition (Part 1 - Introduction)
computer-vision
15. Relationship between energy map and seam carving
computer-vision
16. Abnormal Human Activity Recognition (Part 2 - Two-Dimensional AbHAR)
computer-vision
17. Vision Transformer
computer-vision
18. Abnormal Human Activity Recognition (Part 3 - Two-Dimensional AbHAR (cont.))
computer-vision
19. Abnormal Human Activity Recognition (Part 4 - Three-Dimensional AbHAR)
computer-vision
20. Reproduce cartoon image
computer-vision
21. Abnormal Human Activity Recognition (Part 5 - Three-Dimensional AbHAR) (cont.)
computer-vision
22. A simple system for traffic anomaly detection
computer-vision
23. Model Object Detection and Classification
computer-vision
24. Abnormal Human Activity Recognition (Part 6 - Three-Dimensional AbHAR) (cont.)
computer-vision
25. Abnormal Human Activity Recognition (Part 7 - Deep features based action description)
computer-vision
26. Techniques for evaluating deep learning models.
computer-vision
27. Transfer Learning
computer-vision
28. Augmentation
computer-vision
29. Abnormal Human Activity Recognition (Part 8 - Deep features based action description)
computer-vision
30. Supervised representation learning
computer-vision
31. Introduction to Diffusion Models
computer-vision
32. A kind introduction to Multi Task Learning
computer-vision
33. Multi Task Learning and its effectiveness
computer-vision
34. Multi Task Learning and its correlation with Neural Network
computer-vision
35. Summarization of common loss functions
computer-vision
36. Abnormal Human Activity Recognition (Part 9 - Discussion)
computer-vision
37. Introduction to Diffusion Models (Part 2)
computer-vision
38. Autoencoder
computer-vision
39. Variational Autoencoders (VAE)
computer-vision
40. The overview of GAN (Generative Adversarial Networks)
computer-vision
41. The overview of GAN - Part 2
computer-vision
43. Object Affordance Detection
computer-vision
44. Object Affordance Detection (Part 2)
computer-vision
45. Abnormal Human Activity Recognition (Part 10 - Datasets)
computer-vision
46. Abnormal Human Activity Recognition (Part 11 - Overall Summary)
computer-vision
47. Latent Diffusion Models (Stable Diffusion)
computer-vision
48. Bidirectional Encoder Representations from Transformers
computer-vision
49. Diffusion Model: A breakthrough compared to Auto-encoder, GAN and Flow-based models
computer-vision
Introduction to Diffusion Models (Part 3)
Robotics
A layman, with a fleeting understanding of technology, would link it to robots.
Computer Graphics
If it looks like computer graphics, it is not good computer graphics.
computer-graphics
1. Human Pose & Motion Capture exploration (part 1) Defenition and 2D Human Pose Estimation.
computer-graphics
2. Human Pose & Motion Capture exploration (part 2).
computer-graphics
3. Human Pose & Motion Capture exploration (part 3).
computer-graphics
4. Human Pose & Motion Capture exploration (part 4).
computer-graphics
5. Human Pose & Motion Capture exploration (part 5).
computer-graphics
6. Human Pose & Motion Capture exploration (part 6)
computer-graphics
7. Human Pose & Motion Capture exploration (part 7)
computer-graphics
8. Human Pose & Motion Capture exploration (part 8)
computer-graphics
9. Shape reconstruction from a single RGB video
computer-graphics
10. Applying Neural radiance field in 3D reconstruction from monocular video (Part 1)
computer-graphics
11. Applying Neural radiance field in 3D reconstruction from monocular video (Part 2)
computer-graphics
12. Character Animation and Skinning (part 1)
computer-graphics
13. Character Animation and Skinning (part 2)
computer-graphics
14. Introduction to Human Body Model
computer-graphics
15. Music-Driven Dance Generation
computer-graphics
16. Multi-person motion prediction
computer-graphics
17. Music-Driven Group Dance Generation
computer-graphics
18. Populating 3D Scenes by Learning Human Scene Interaction (Part 1).
computer-graphics
19. Populating 3D Scenes by Learning Human Scene Interaction (Part 2).
computer-graphics
20. Populating 3D Scenes by Learning Human Scene Interaction (Part 3).
computer-graphics
21. Minkowski Engine - part 1
computer-graphics
22. Minkowski Engine - part 2
computer-graphics
23. DanceNet for Music-driven Dance Generation
computer-graphics
24. Music to Multi-People Dance Synthesis with Style Collaboration.
computer-graphics
25. Method comparison between three latest Dance Generation approaches.
computer-graphics
26. Music2Dance and GroupDancer comparison.
computer-graphics
27. 3D Downstream Tasks for Foundation Model (Part 1)
computer-graphics
27. 3D Downstream Tasks for Foundation Model (Part 2).
computer-graphics
29. 3D Downstream Tasks for Foundation Model (Part 1).
computer-graphics
30. 3D Downstream Tasks for Foundation Model (Part2).
computer-graphics
31. 3D Downstream Tasks for Foundation Model (Part 1).
computer-graphics
32. 3D Downstream Tasks for Foundation Model (Part 2).
computer-graphics
33. Introduction to dance generation recent works.
computer-graphics
34. Introduction to auto-regressive dance generation.
Medical Image Processing
The flashiest use of medical AI is to perform tasks that even the best human providers cannot yet do.
Machine Learning Operations (MLOps)
MLOps is the natural progression of DevOps in the context of AI.
ml-ops
1. Model Serving and NVIDIA Triton Inference Server.
ml-ops
2. Convert weight TF lite from Pytorch for Android app
ml-ops
3. Pytorch Mobile
ml-ops
4. Model Compression Part 1.
ml-ops
5. Model Compression Part 2.
ml-ops
6. Model Compression Part 3.
ml-ops
7. Model Compression Part 4.
ml-ops
8. Model Compression Part 5.
ml-ops
9. Model Compression Part 6.
ml-ops
10. Model Compression Part 7.
ml-ops
11. Model Compression Part 8 (Lightweight variations of Squeeze U-Net).
ml-ops
12. Benchmarking of GPEN, an image restoration method.
ml-ops
13. Quantization in Deep learning
ml-ops
14. Quantization on tensorflow
ml-ops