2020 to 2021: predictive AI
The first two years, where classic machine learning and deep learning were learned in public, one classifier at a time.
- Status
- stable
- Trust
- human-reviewedhuman:rrizwan98 ·
- Approved
- human:rrizwan98 ·
The account opens on 19 September 2020 with two repositories pushed the same day: a cat-versus-dog classifier and a facial-expression model. What follows in 2021 is a year of learning in public: 23 repositories, every one of them public, and not a single private one.1
What happened
The work of this era is classic machine learning and deep learning, the kind that lives in a notebook:2
- Image classification. Cats versus dogs, facial expressions, Fashion-MNIST, fruit, chest X-rays, eyes, lung-cancer detection and, by the end of 2021, lung-cancer stage segmentation.
- Predictive models. Used-car price prediction, customer segmentation, climate data, an e-commerce dataset.
- NLP basics. Tokenisation, English-to-French translation, Amazon and Play Store review classification, an Arabic and English Quran text project.
- First cloud ML. AWS SageMaker for MNIST classification and house pricing, in May 2021.
- First chatbot. A chatbot for the Software Engineering department at SSUET that answers students' questions, in September 2021.
- A first look sideways. A TypeScript repository and a Web 3.0 projects repository at the very end of the year, the trace of the Panaverse programme that ran alongside the AI work.
Beside the original repositories sit forks of course material from the PIAIC and Saylani AI programmes and a bootcamp submission, which is where much of this year's learning came from. Forks are not counted as Raza's own work.1
The public repositories
Eleven of the 2021 repositories were pushed on one day, 9 March 2021, which reads like a portfolio being assembled at the end of a course.
| Created | Repository | What it is |
|---|---|---|
| 2020-09-19 | cat-and-dog-classification | Cats versus dogs image classifier |
| 2020-09-19 | Facial-Expression | Facial-expression model; its own description also mentions an Amazon Reviews deep neural network exercise |
| 2021-02-13 | Arabic-Quran-English-Quran | Arabic and English Quran text project |
| 2021-03-09 | E_Commerce | E-commerce dataset work |
| 2021-03-09 | Amazon_Reviews | Amazon review classification |
| 2021-03-09 | Usa_Cars_Price_Prediction | Used-car price prediction |
| 2021-03-09 | Chest_X_ray | Chest X-ray classification |
| 2021-03-09 | Fruit_CLassification | Fruit image classification |
| 2021-03-09 | Fashion_mnist_Classification | Fashion-MNIST classifier |
| 2021-03-09 | Climate | Climate data model |
| 2021-03-09 | Eye | Eye image classification |
| 2021-03-09 | English_To_French_Translation | Sequence-to-sequence translation |
| 2021-03-09 | Nlp_Tokenization | NLP tokenisation exercises |
| 2021-03-09 | Play_Store_Reviews_Classification | Play Store review classification |
| 2021-05-17 | AWS-Sagemaker-MNIST-Classification-Data | First SageMaker training job |
| 2021-05-17 | AWS-Sagemaker-House-pricing | SageMaker regression |
| 2021-06-20 | rrizwan98 | The GitHub profile repository |
| 2021-07-03 | Computer-Vision | Computer-vision exercises |
| 2021-07-27 | Typescript | TypeScript learning |
| 2021-08-19 | Lungs-Cancer-Dedection | Lung-cancer detection |
| 2021-09-03 | Natural-Language-Processing-NLp- | NLP exercises |
| 2021-09-12 | SSUET-chatbot | Chatbot for the SSUET Software Engineering department |
| 2021-12-17 | ML-Projects-Customer-Segmentation | Customer segmentation |
| 2021-12-27 | Projects-Web-3.0- | Web 3.0 projects: blockchain, AI, cloud, IoT |
| 2021-12-29 | Lungs-cancer-stage-segmentation-cancer-stage-classification | Lung-cancer stage segmentation and classification |
Private repositories this era: none.1
What this era taught
How models actually learn, and how far a notebook is from a product.2 The next two years are about closing that distance.
Next: 2022 to 2023: MLOps.
Footnotes
Sources
- [^github-repos]GitHub API, repositories owned by rrizwan98, read 26 August 2026
- [^journey-note]From Predictive AI to Forward Deployed Engineer: My 6-Year Journey, Raza Rizwan, July 2026
The journey, 2020 to 2026
How Raza Rizwan went from training image classifiers in notebooks to deploying AI systems that run real business operations, one era at a time.
2022 to 2023: MLOps
Two years spent learning to ship models, with CI/CD, DVC, MLflow, YOLO object detection in production, SageMaker endpoints and the first private client work.