![[Nov 26] introduction to AI / ML](https://image.slidesharecdn.com/nov26introductiontoaiml-211127034520/85/Nov-26-introduction-to-AI-ML-1-320.jpg)
[Nov 26] introduction to AI / ML
- 2. ARTIFICIAL INTELLIGENCE & MACHINE LEARNING Chung Minh Nhat @nhatchung14 An Introduction!
- 3. Agenda ❑ Era of Artificial Intelligence ❑ What is AI? ❑ General vs. Narrow AI ❑ Rule-based AI ❑ Machine Learning ❑ Deep Learning ❑ AI Dev
- 5. https://medium0.com/future-today/understanding-artificial-intelligence-f800b51c767f
- 6. TODAY’S ARTIFICIAL INTELLIGENCE IS ❑ POWERFUL ❑ ACCESSIBLE TO ALL https://www.healthcareitnews.com/news/new-ai-diagnostic-tool-knows-when-defer-human-mit-researchers-say https://www.infosearchbpo.com/3d-lidar-annotation.php
- 7. WHAT IS AI?
- 8. Definition 1: AI is the machine imitation of human intelligence Ideal
- 9. Less Ideal Definition 2: AI is a system that perceives its environment and takes actions that maximize its chance of achieving its goals
- 10. Wu Hong Definition 3: AI is an algorithm that tackles a real-life problem in a human-like manner Practical for Devs
- 11. GENERAL VS. NARROW AI
- 12. ❑ Philosophically no body, no childhood and no cultural practice, computers cannot acquire true intelligence: https://www.nature.com/articles/s4159 9-020-0494-4#Sec8 ❑ Technologically, self-programming AI demands vast data across multiple branches, tremendous computations, and complex math models. Not currently feasible. ❑No reliance on human programming to learn and do. ❑Like humans, general AI can adapt to its environment. General AI are self-programming AI Properties Availability
- 13. Narrow AI for a single task, where knowledge gained will not automatically be applied to other tasks Rule-based AI Machine Learning AI Some experts argue that this is not AI! https://www.ck12.org/book/ck-12-basic-geometry-concepts/section/2.3/ Types ❑Search-driven AI ❑Expert System https://www.researchgate.net/pu blication/330217507_Application _of_machine_learning_in_rheum atic_disease_research Its Trendy Subfield: Deep Learning Found in ❑Gaming ❑Management Systems ❑computer algorithms that can improve automatically through experience and by the use of data
- 14. RULE-BASED AI Gaming AI – gfycat/witcher By Nbro, https://commons.wikimedia.org/wiki/File:Animation_of_alpha-beta_pruning.gif
- 15. Search-driven Simple Chess AI - freecodecamp ❑ Decision-making by solving a search problem based on heuristics or mathematical reasoning. ❑ Navigate through trees of possibilities to find the best possible outcome → partial game trees to make computation feasible https://giphy.com/explore/pathfinding
- 16. Expert Systems simulates the behavior and judgement of human experts. ❑ Knowledge base: Knowledge, rules and form procedures of the domain. ❑ Rules engine: Function to get relevant data from the knowledge base, interpret it, and to find a solution. ❑ User interface: Function to allow a non-expert user to interact with the expert system and find solutions. ❑ Knowledge acquisition and learning module: Function to acquire more data from various sources. https://www.mygreatlearning. com/blog/expert-systems-in- artificial-intelligence/ ❑ For non-experts to gain information. ❑ Used in various areas of medical diagnosis, accounting, coding, gaming and more. Properties Components https://www.javatpoint.com/expert-systems-in-artificial-intelligence
- 17. Old Google Search http://infolab.stanford.edu/~backrub/google.html https://www.wired.com/2016/02/ai-is-changing-the-technology-behind-google-searches/ ❑In the past, Google relied mostly on algorithms that followed a strict set of rules set by humans “Academic citation literature has been applied to the web, largely by counting citations or backlinks to a given page. This gives some approximation of a page's importance or quality. PageRank extends this idea by not counting links from all pages equally, and by normalizing by the number of links on a page.” Further Readings Google as a Search Expert
- 19. Machine learning uses an algorithm to learn and generalize from historical data in order to make predictions on new data. Machine Learning Rule-based AI is probabilistic is deterministic adapt in accordance with training information streams require manual data analysis and modification of rules needs full demographic data details of the domain needs experts to set up objective rules changing parameters hard-coded rules
- 20. Supervised learning Formulation: Given an input set X and the corresponding output set Y, supervised learning involves learning a function F such that F(X) = Ẏ matches Y as much as possible. Types: https://www.ceralytics.com/3-types-of-machine- learning/
- 21. Object Detection ❑Regression: Fitting bounding boxes to image points. ❑Classification: Identifying object in vehicle https://alexeyab84.medium.com/yolov4-the-most-accurate-real-time-neural-network- on-ms-coco-dataset-73adfd3602fe https://www.youtube.com/watch?v=nw1GexJzbCI&ab_channel=TzuTaLin Intense Labeling Great results
- 22. Unsupervised learning https://www.ceralytics.com/3-types-of-machine-learning/ Formulation: Given only an input set X, unsupervised learning involves learning a function F such that F(X) maps to the desired existing patterns in X. Types: https://medium.com/@jwu2/improving-collaborative-filtering-with- dimensionality-reduction-a99d08585dab https://www.javatpoint.com/clustering-in-machine-learning
- 23. https://en.wikipedia.org/wiki/Principal_component_analysis Dimensionality Reduction An Example with Principle Component Analysis https://archetypalecology.wordpress.com/2018/02/17/principal-component-analysis-in-r/
- 24. Reinforcement learning Robotic simulation https://gfycat.com/gifs/tag/sethbling Advanced Gaming AI https://www.freecodecamp.org/news/a-brief- introduction-to-reinforcement-learning- 7799af5840db/ Simplification: Given an environment E and a set of allowed actions A, the reinforcement learning model M learns to maximize a cumulative reward function F. It does so by producing a sequence of actions (trial) 𝐚𝟎, 𝐚𝟏, 𝐚𝟐, … Whenever a trial fails, F is penalized such that M is tuned to produce a better trial. Otherwise, F accumulates rewards. ❑ Learning to take suitable actions to maximize reward in a particular situation through trials and errors. ❑ Involves actions, states and reward functions more than just inputs, outputs → Balancing exploration and exploitation
- 25. Rewards can be exploited https://boingboing.net/2020/01/11/optimizers-curse.html https://gfycat.com/gifs/search/reinforcement+learning Not safe to test how tough your vehicles are!
- 27. Deep Learning The Universal Approx. Theorem a feed-forward network with a single hidden layer containing a finite number of neurons can solve any given problem to arbitrarily close accuracy as long as you add enough parameters. Thanks to ❑ Neural Networks → Indefinitely Flexible ❑ Gradient Descent → The tractable optimizing technique ❑ GPU → The actual computing technology that allows parallelization on Big Data https://www.montreal.ai/ai4all.pdf Forward Inference Backward Propagation is inspired by neural networks of the brain to build learning machines
- 28. F. Wang, M. Zhang, X. Wang, X. Ma and J. Liu, "Deep Learning for Edge Computing Applications: A State-of-the-Art Survey," in IEEE Access, vol. 8, pp. 58322-58336, 2020, doi: 10.1109/ACCESS.2020.2982411. Structures of different deep learning models.
- 29. https://www.montreal.ai/ai4all.pdf Rotation and translation of a GAN-generated car using GIRAFFE (created by author using https://github.com/autonomousvision/giraffe, MIT License). Deep Learning – An Example Advantages Disadvantages ❑ Approximating complex functions ❑ High accuracy ❑ Many existing frameworks and codes ❑Needs a lot of data for training ❑Domain changes requires more data ❑No clear mathematical understanding of parameters yet ❑Needs much GPU capabilities
- 30. AI DEV
- 31. Know your direction Image by Jash Rathod https://pub.towardsai.net/branches-in-artificial-intelligence-to-transform-your-business-f08103a91ab2
- 32. Know your language The majority of AI applications can be easily written in Python Thanks to their flexibility and great efficiency, you can push certain boundaries with C/C++
- 33. Know your framework ❑ Great Google Community ❑ Strong API ❑ Fast Inference ❑ Research-driven ❑ Very Pythonic ❑ Many Easy-to-Understand Tutorials
- 35. Know your trade-offs Due to domain complexity, there has always been a major dilemma between speed and accuracy https://www.researchgate.net/publication/328509150_Benchmark_Analysis_of_Representative_Deep_Neural_Net work_Architectures
- 36. Know your trade-offs HCMIU CVIP’s Work ❑ Domain Complexity - Medium ❑ Model Computational Expense - Low ❑ Model Accuracy - High
- 37. Know your trade-offs HCMIU CVIP’s Work ❑ Domain Complexity - High ❑ Model Computational Expense - High ❑ Model Accuracy - High
- 38. Learn a lot, and stay patient https://twitter.com/deeplearningai_/status/1290301458777284609 https://www.pinterest.com.au/pin/832954893568660546/
- 39. Say GDSC GEE, DEEE, ESSSS, CEEEEEEEEEE