Day 1 wazz up ai
•
0 likes•100 views
In the first day of How-to-AI Series, you will learn some fundamental knowledge about the AI and Machine Learning field.
Report
Share
Day 1 wazz up ai
- 7. How-to-AI Series Unlock Potential GDSC HCMUT 2021
- 8. Break the ice How do you understand AI?
- 9. Introduction ● How-to-AI Series will be held on 5 days, each day during the event you will be introduced to different topics about AI and Machine Learning. ● Understand the common terms and be able to build an AI/ML product.
- 10. Timeline Day 1: WazzUp AI 05/12/2021 Day 2: Build Up your own Neural Network 11/12/2021 Day 3: Take Up Convolutional Neural Network 12/12/2021 Day 4: Level Up your model 02/01/2022 Day 5: Meet Up with experts 09/01/2022
- 11. GDSC AI Challenge Training your first AI model ● A competition hosted on Kaggle platform to help attendees revise what they have learned in the first 3 workshops and build their own Machine Learning models. ● Timeline: 12/12/2021 - 26/12/2021 ● Total prizes: 3 million VND
- 12. Opening Speech From TMA Solution
- 13. how-to-AI Series: Unlock Potential Day 1: WazzUp AI Nguyễn Luật Gia Khôi @giakhoi.nguyenluat Nguyễn Hoàng Trung @hoangtrung.nguyen
- 14. Outline 1. Break the ice 2. Introduction to How-to-AI Series: Unlock Potential 3. Introduction to AI/ML 4. What can AI/ML do ? 5. Introduction to Deep Learning
- 15. Introduction to AI/ML Let’s dive into the world of AI !
- 16. What is AI ? An artificial intelligence (AI) is basically the mechanism to incorporate human intelligence into machines through a set of rules (algorithm).
- 17. Example
- 18. ANI, AGI, and ASI
- 19. ANI Artificial Narrow Intelligence ● Artificial narrow intelligence (ANI or narrow AI) refers to a computer’s ability to perform a single task extremely well, such as crawling a webpage or playing chess. ● Siri, Face ID and the Google Assistant, to self-driving cars, etc. ● The only form of AI that we have been able to develop so far. If you can think about any form of AI that you know exists today, it is ANI.
- 21. AGI Artificial general intelligence Artificial general intelligence (AGI) is when a computer program can perform any intellectual task that a human could.
- 22. ASI Artificial super intelligence Artificial super intelligence (ASI) is an AI that surpasses human intellect.
- 23. “A year spent in artificial intelligence is enough to make one believe in God.” - Alan Perlis -
- 24. What is Machine Learning ? A subset of AI that uses statistical learning algorithms to build smart systems that can automatically learn and improve without explicitly being programmed.
- 25. Data Data can be texts or numbers written on papers, or it can be bytes and bits inside the memory of electronic devices, or it could be facts that are stored inside a person’s mind.
- 26. Data in AI/ML A good dataset? Some problems when choosing dataset ? A good data set is one that has either well-labeled fields and members or a data dictionary so you can re-label the data yourself.
- 27. Data in AI/ML A good dataset? Some problems when choosing dataset ? ● Wrong Data ● Missing Data ● Outliers in Data ● Redundancy in Data ● Unbalanced Data ● Lack of Variability in Data
- 28. AI/ML Keywords Find out some common keywords
- 29. Features
- 30. Welcome my friend, Jack Height Weight Age Vaccination Travel Habitat
- 33. Dataset
- 34. Machine Learning Deep Learning Features engineering Learn features by themselves
- 35. Preprocessing
- 37. Resize salary age salary age Scale Welcome to day 1 of AI Series. /Welcome/ /to/ /day/ /1/ /of/ /AI/ /Series/ /./ Tokenization
- 38. Supervised vs Unsupervised vs Reinforcement Learning
- 39. Supervised vs Unsupervised ● Supervised learning: Learning on labeled data. The goal is to learn a general rule that maps inputs to outputs ● Unsupervised learning: Learning on unlabeled data. The goal is to cluster the similar examples into classes.
- 42. How can it know which step led to the failure? Sparse reward Reward shaping
- 43. Application ● Supervised learning: regression, classification, etc. ● Unsupervised learning: segmentation, recommendation system, etc. ● Reinforcement learning: self-driving car, gaming, etc.
- 45. ● Supervised learning Similarities: ● Learn the mapping function f(x) -> y
- 46. Differences ● Regression: mapping input value to continuous output variable ● Classification: mapping input value to discrete or categorical values.
- 47. Application ● Regression: housing price prediction, bitcoin value prediction, scoring, etc. ● Classification: object detection, image segmentation, etc.
- 50. Overfitting in classification ● Training set ● Test set Prediction: Not a dog
- 52. Underfitting in classification Prediction: Dog Dog ● Training ● Test
- 53. Reasons ● Training data is not cleaned and contains noise. ● Complex model but small data set. ● Lack of features. ● The model is too simple ● Small size of dataset For Overfitting: For Underfitting:
- 54. Solution ● Get/Generate more data ● Regularization For Overfitting: ● Spend more time for preprocessing data ● Increase the training duration (# epochs) ● Increase model complexity For Underfitting: ● Spend more time for feature engineering (ML)
- 55. What AI/ML can do
- 57. Why not see it ourselves? teachablemachine.withgoogle.com
- 58. However...
- 59. Introduction to Deep Learning
- 61. Inside your brains unit = neuron?
- 63. Deep Learning vs Machine Learning
- 64. How it works?
- 65. Learning resources Then, how to start?
- 66. Where to start?
- 67. Light desserts
- 68. Q&A
- 70. Thank You! Nguyễn Luật Gia Khôi @giakhoi.nguyenluat Nguyễn Hoàng Trung @hoangtrung.nguyen