For the past 7 cohorts (since January 6th 2018), we have offered free machine learning classes to more than 1000 Nigerians and we are excited to continue our long-standing tradition. This document will serve as a guideline for our students, as well as other communities looking to replicate the AI Saturdays Lagos model ❤️. Each cohort has a different flavor, so do check out our Cohort 7 guideline as well.
- 17 weeks of Main class and 1 week break 😎
- 10 practicals
- 1 Main project
- Exercises to put your knowledge to test
- Certificate of participation if all the requirements are fulfiled (more details below)
Our classes are streamed weekly and can be accessed online, at anytime - for free!
We are extremely grateful to our selfless volunteers - class and practical instructors, lab instructors, mentors, and many more. Our community is truly fortunate to have such an amazing, talented, kind, and incredible group of people ☘️.
Are you interested in joining our next cohort? Please follow us on our various socials media platforms to keep in touch ✨.
If you wish to support our work and the initiatives we undertake, we kindly invite you to consider making a donation on our Patreon page. Your generosity will play a crucial role in furthering our mission and helping us make a positive impact in the African AI community.
- You are expected to have about 60% or more participation in class. Participation will be monitored by taking attendance
- You are expected to have about 60% or more participation in Labs. Participation will be monitored by taking attendance
- You are expected to have atleast 30% in assignments
- You are expected to have a 100% participation in final Project
We will primarily be using the three fantastic courses listed below as a source of reference. However, each volunteer course instructor has full autonomy in choosing which materials to use to teach their classes.
| Week | Date | Topic | Resources | Instructors | Topics Covered |
|---|---|---|---|---|---|
| 0 | 05-Aug | Python Refresher | Notebook, Youtube | Steven Kolawole | Hello, Python; Functions and Getting Help; Booleans and Conditionals; Lists; Loops and List Comprehensions; Sorts; Strings and Dictionaries; Working with External Libraries; Mathematics with Python |
| 1 | 12-Aug | Numerical Computing with Python and Numpy | Notebook, Youtube | Khadija Iddrisu | Going from Python lists to Numpy arrays; Multi-dimensional Numpy arrays and their benefits; Arrray operations, broadcasting, indexing, and slicing; Working with CSV data files using Numpy; Working with pandas and sklearn |
| 2 | 19-Aug | Introduction to Data Science | Slide, Youtube | Emefa Duah | What is data science; What is not data science; Data Science vs Machine Learning; (A few) data science examples; The skillset of data scientists; Data science pipeline |
| 3 | 26-Aug | Data Collection and Scraping | Slide, Youtube | Akintayo Jabar | Data collection process; Common data formats and handling; Regular expression and parsing |
| 4 | 02-Sep | Relational Data | Slide, Youtube | Akintayo Jabar | Overview of relational data; Entity relationships; Pandas and SQLite; Joins; SQLite examples; DB joins |
| 5 | 09-Sep | Visualization and Data Exploration | Slide, Youtube | Aseda Addai-Deseh | Basics of visualization; Data types and visualization types; Software plotting libraries |
| 6 | 16-Sep | Linear Algebra | Slide, Notebook, Youtube | Kenechi Dukor | Matrices and vectors; Basics of linear algebra; Solving linear equations; Libraries for matrices and vectors; Sparse matrices |
| 7 | 23-Sep | Free Text and Natural Language Processing | Slide, Youtube | Wuraola Oyewusi | Free text in data science; Bag of words and TFIDF; Tokenization; Embedding representation; Language models and N-gramsp Example motivation: ChatGPT |
| 8 | 30-Sep | Introduction to Machine Learning | Slide, Youtube | Allen Akinkunle | Least squares regression: a simple example; Machine learning notation; Linear regression revisited; Matrix / vector notation and analytic solutions; Finding good parameters; The gradient descent algorithm; Implementing linear regression |
| 9 | 07-Oct | Linear Classification | Slide, Youtube | Olumide Okubadejo | Example motivation; Classification in machine learning; Example classification algorithms: Logistic regression and Support vector machines; Libraries for machine learning |
| 10 | 14-Oct | **No Lecture and No Lab** |
|||
| 11 | 21-Oct | Nonlinear Modeling, Cross-Validation | Slide, Youtube | Tejumade Afonja | Example motivation; Overfitting, generalization, and cross validation; Regularization; General nonlinear features; Kernels; Nonlinear classification |
| 12 | 28-Oct | Basics of Probability | Slide, Youtube | Emefa Duah | Probability in data science; Basic rules of probability; Some common distributions; Example application |
| 13 | 04-Nov | Maximum Likelihood Estimation, Naive bayes | Slide, Youtube | Tejumade Afonja | Maximum likelihood estimation; Naive Bayes; Spam classification with Naive Bayes |
| 14 | 11-Nov | Unsupervised Learning | Slide, Youtube | Deborah Kanubala | Unsupervised learning; K-means; Principal Component Analysis |
| 15 | 18-Nov | Decision Trees, Interpretable Models | Slide, Youtube | Oluwatoyin Yetunde Sanni | Decision Trees; Training (classification) decision trees; Interpretating predictions; Boosting; Examples |
| 16 | 25-Nov | Recommendation Systems | Slide, Youtube | Foutse Yuehgoh | Recommendation systems; Collaborative filtering; User-user and item-item approaches; Matrix factorization; Examples |
| 17 | 2-Dec | Introduction to Deep Learning | Slide, Youtube | Femi Ogunbode | Recent history in machine learning; Machine learning with neural networks; Training neural networks; Specialized neural network architectures; Deep learning in data science; Brief overview of popular deep learning-based generative models |
| 18 | 9-Dec | **No Lecture and No Lab** |
|||
| 19 | 16-Dec | Project Presentations |
| Week | Date | Topic | Resources | Tutor |
|---|---|---|---|---|
| 0 | 05-Aug | **No Lab** |
||
| 1 | 12-Aug | **No Lab** |
||
| 2 | 19-Aug | Introduction to Git and Github | Slide, Youtube | Sandra Oriji |
| 3 | 26-Aug | Data Collection and Scraping | Notebook, Youtube | Ejiro Onose |
| 4 | 02-Sept | Relational Data and SQL | Notebook, Youtube | Afolabi Animashaun |
| 5 | 09-Sept | Lab Postponed to Next Week |
||
| 6 | 16-Sept | Data exploration and visualization | Notebook, Youtube | Oluwaseun Ajayi |
| 7 | 23-Sept | Text Processing | Notebook, Youtube | Fortune Adekogbe |
| 8 | 30-Sept | **No Lab** |
||
| 9 | 7-Oct | Linear Regression and Classification | Notebook, Youtube | Lawrence Francis |
| 10 | 14-Oct | **No Lecture and No Lab** |
||
| 11 | 21-Oct | Non-linear Modeling | Notebook, Youtube | Tejumade Afonja |
| 12 | 28-Oct | **No Lab** |
||
| 13 | 04-Nov | **No Lab** |
||
| 14 | 11-Nov | Unsupervised Learning | Notebook, Youtube | Joscha Cüppers |
| 15 | 18-Nov | **No Lab** |
||
| 16 | 25-Nov | Recommendation Systems | Notebook, **Lab Cancelled due to technical difficulties** |
Ejiro Onose |
| 17 | 2-Dec | Neural Networks | Notebook, Youtube | Funmito Adeyemi |
| 18 | 9-Dec | **No Lecture and No Lab** |
||
| 19 | 16-Dec | Project Presentations |
| N/A | Release Date | Week-Topic | Links | Deadline |
|---|---|---|---|---|
| 1 | 03-Sept | 03-Data Collection and Scraping | Assignment, Submission | 9th September 2023 |
| 2 | 11-Sept | 04-Relational Data and SQL | Assignment, Submission | 17th September 2023 |
| 3 | 27-Sept | 05-Data Exploration and Visualization | Assignment, Submission | 8th October 2023 |
| 4 | 15-Oct | 07-Free Text and NLP | Assignment, Submission | 29th October 2023 |
| 5 | 25-Nov | 11-Nonlinear Modeling | Assignment, Submission | 10th December 2023 |
As a prerequisite for successfully concluding this cohort, participants are presented with two structural options based on prefrence. They may choose to engage in a collaborative group project or undertake an individual project. The primary objective of this initiative is to afford participants the opportunity to apply their theoretical knowledge gained throughout the cohort in a practical setting. Throughout the project engagement, participants will receive guidance from industry experts in Artificial Intelligence. These mentors will play a pivotal role in providing support and direction, ensuring the successful completion of the projects. Notably, there are currently 15 groups, each named after prominent African world leaders, symbolizing their significant contributions and advancements. The Solo-Ransome-Kuti group members are embarking on individually-led projects.
Project Proposal Deadline: October 15, 2023
Project Submission Deadline: December 10, 2023
Presentation Day: December 16, 2023
| Team Name | Project | Members | Resources | Mentor |
|---|---|---|---|---|
| Solo-Ransome-Kuti-Ladipo | NSL-2-Audio: Nigerian Sign Language to Audio | Ipadeola Ladipo | Github | Tejumade Afonja |
| Solo-Ransome-Kuti-Oyeneye | Adaptive Melodies: A User-Shift Preference Music Recommendation System | Samuel Oyeneye | Github | Tejumade Afonja |
| Solo-Ransome-Kuti-Adai | Predicting Credit Card Approvals | Christopher Adai | Github | Afolabi Animashaun |
| Sankara | MovieSense: Movie Recommender System | Olugbade Ifeoluwa, Ogbobe Charles, Ehimwenman Edemakhiota, -Moshood Sanusi, -Muhammad Yahya | Github | David Onyeali |
| Johnson-Sirleaf | Machine Learning Approach to Predicting Diabetes Risk | Buraimoh Glory, Dolamu Oludare, Chinedu Oguazu, Usman Daudu, -Oluwafemi Akinode | Github | Olawale Abimbola |
| Maathai | Customer Churn Prediction | Jack Oraro, Oyelayo Seye, Adenike Ayodeji, Ayooluwa Jesuniyi, -Elijah Mesagan, -Lucky Nkwocha | Github | Foutse Yuehgoh |
| Nkrumah | Sentiment Analysis on Social Media | Samuel Ekuma,Rapheal Alemoh, Chinelo Okafor, -Chisom Nenna, -Oluwafunto Daramola | Github | Olumide Okubadejo |
| Mandela | Air Quality Monitoring and Anomaly Detection System | Peter Agida, Damilola Akin-Adamu, Oluwapolore Oyeniji, Abdul-lateef Asafa, Yetunde Afolabi, -Folashade Akintola | Github | Joscha Cüppers |
| Ahmed-Ibrahim | Building Prices Prediction Model | Peter Oni, Daniel Eze, Oluwapelumi Olaniyi, Joanna Yadeka, Elisha Babalola | Github | Emefa Duah |
| Kapwepwe | Analysing Reviews of Hotels and Restaurants in Nigeria to Determine Customer Sentiment | Daniel Otulagun, Olatunde Ogunboyejo, Sarah Akinkunmi, -Iyanu Gbiri, -Olushola Yusuf | Github | Orevaoghene Ahia |
| Anomah-Ngu | Handwritten Digits Recognition Model | Mofiyinfoluwa Aladesuyi, Jedaiah Akimsah, Taiwo Olorunnishola, Victor Bassey, Mukhtar Abdulquadir | Github | Akintayo Jabar |
| Bourguiba | Implementation of Medical FAQ Chatbot | Monsurat Ariyo, Ayodeji Akande, Caleb Balogun, Martins Joseph, Bala Mairiga Abduljalil, -Waris Akorede | Github | Fortune Adekogbe |
| Elnadi | Flood Chat | Etietop Udofia, -Basil Makama, -Okosa Uche, -Akorede Salaam, -Joshua Michael, -Okosa Uche | Github | Sandra Onyinyechi |
| Selassie | Diabetic Risk Prediction using Random Forest and Logistic Regression | Ebunoluwa Amoo, Ayodeji Adesegun, Funbi Bolarinwa, Abraham Ugwa, Oyindamola Olatunji | Github | Oluwaseun Ajayi |
| Lumumba | - | Ayorinde Alase, Gamaliel Okudo, Nurudeen Alase, Precious Ita, Chitom Uzokwe | Github | Oluwafemi Azeez |
| Nyerere | - | Temitope Ajibade, Kelvin Obi, Oluwabukola Ogunbunmi, Muhammad Gimba, Eniola Adetunji | Github | Femi Ogunbode |
| Machel | - | Olorundara Akojede, Tope Rufai, Anuoluwapo Ogunrinde, Jamiu Ahmed, Bilikis Olanrewaju | Github | Kenechi Dukor |
