https://github.com/yasenstar/ai-ml-dl
Learning repository for Artificial Intelligence (AI), Machine Learning (ML) and Deep Learning (DL)
https://github.com/yasenstar/ai-ml-dl
ai artificial-intelligence deep-learning dl gl machine-learning ml
Last synced: 2 months ago
JSON representation
Learning repository for Artificial Intelligence (AI), Machine Learning (ML) and Deep Learning (DL)
- Host: GitHub
- URL: https://github.com/yasenstar/ai-ml-dl
- Owner: yasenstar
- License: gpl-3.0
- Created: 2024-11-27T05:13:03.000Z (6 months ago)
- Default Branch: main
- Last Pushed: 2025-02-01T05:32:37.000Z (4 months ago)
- Last Synced: 2025-03-19T21:49:45.167Z (2 months ago)
- Topics: ai, artificial-intelligence, deep-learning, dl, gl, machine-learning, ml
- Language: Python
- Homepage: https://yasenstar.github.io/ai-ml-dl/
- Size: 3.97 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- Funding: .github/FUNDING.yml
- License: LICENSE
Awesome Lists containing this project
README
# AI - ML - DL and Data Science
Learning repository for Artificial Intelligence (AI), Machine Learning (ML) and Deep Learning (DL)
- [AI - Artificial Intelligence](AI/README.md)
- [ML - Machine Learning](ML/README.md)
- [DL - Deep Learning](DL/README.md)
Illustration of the overall relationships of those "learnings" and "analytics":
Thanks Source: https://www.linkedin.com/pulse/how-does-ai-ml-dl-gi-fit-together-anang-b-singh/
## High Level Comparison: AI vs ML vs DL
Thanks Source: https://www.analyticsvidhya.com/articles/machine-learning-vs-artificial-intelligence-vs-deep-learning/
| Artificial Intelligence (AI) | Machine Learning (ML) | Deep Learning (DL) |
| :-- | :-- | :-- |
| AI simulates human intelligence to perform tasks and make decisions. | ML is a subset of AI that uses algorithms to learn patterns from data. | DL is a subset of ML that employs artificial neural networks for complex tasks. |
| AI may or may not require large datasets; it can use predefined rules. | ML heavily relies on labeled data for training and making predictions. | DL requires extensive labeled data and performs exceptionally with big datasets. |
| AI can be rule-based, requiring human programming and intervention. | ML automates learning from data and requires less manual intervention. | DL automates feature extraction, reducing the need for manual enginnering. |
| AI can handel various tasks, from simple to complex, across domains. | ML specializes in data-driven tasks like classification, regression, etc. | DL excels at complext tasks like image recognition, natural language processing, and more. |
| AI algorithms can be simple or complex, depending on the application. | ML employes various algorithms like decision trees, SVM, and random forests. | DL relies on deep neural networks, which can have numerous hidden layers for complex learning. |
| AI may require less training time and resources for rule-based systems. | ML training time varies with the algorithm complexity and dataset size. | DL training demands substantial computational resources and time for deep networks. |
| AI systems may offer interpretable results based on human rules. | ML models can be interpretable or less interpretable baesd on the algorithm. | DL models are often considered less interpretable due to complex network architectures. |
| AI is used in virtual assitants, recommendation systems, and more. | ML is applied in image recognition, spam filtering, and other data tasks. | DL is utilized in autonomous vehicles, speech recognition, and advanced AI applications. |
## Tools used in this Repository
- [FreePlane](https://docs.freeplane.org/): open source mindmapping tool
---
Welcome questions and suggestions, send to [here](mailto:[email protected]) directly, or using [Discussion board](https://github.com/yasenstar/ai-ml-dl/discussions).