• Website: http://www.malaysiamlstudyjam.com
• Subscribe to updates here: https://www.facebook.com/groups/TensorFlowMY
• Join the discourse channel
• Tweet about this StudyJam!
• ML Study Jam Info Booklet
• Registration Page

ML Study Jam is a learning opportunity orgainzed by Malaysia TensorFlow & Deep Learning User Group together with Sunway University Tech Club & Sunway DataXSight Research Cluster, which takes 4 weeks of time leveraging on Kaggle Courses. It includes hands-on assignments, tutoring, tech talks and group discussions. This is a great opportunity to bring members of your community together to learn something online.

Kaggle is the world’s largest data science and machine learning community. It offers a no-setup, customizable, Jupyter Notebooks environment, access to free GPUs and a huge repository of community published data & code.

This is a study program going through Kaggle courses sequentially. The goal of these assignments is to rapidly cover the most essential skills. Such as how to use TensorFlow or Pandas and how to build your first machine learning model. This online-oriented program suggests that the participants study by themselves. Studying with others is a more effective way to master courses sometimes, therefore, we’re suggested to study together online.

There will be short lectures/talks by industry practitioners (virtual & physical) event planned at the end of the week.

• Everyone who finishes a Kaggle course will receive a completion certificate.
• You can find your certificates by navigating to the Courses page: https://www.kaggle.com/learn-course-certificates

Aspired Data scientists/Data Analysts. Also software engineers and data engineers interested in learning Python programming, Machine Learning and Deep Learning.

• Basic Python programming knowledge (1+ years of professional experience)
• Basic Mathematics & Statistics knowledge
• Being comfortable with command line

13th August 2022 - 3rd September 2022

There are 8 modules planned in this ML Study Jam. Each module cosnsists of several lessons, exercises and homeworks.

• Review of python programmming
• Numpy
• Matplotlib

• How Models Work
• Basic Data Exploration
• Your First Machine Learning Model
• Model Validation
• Underfitting and Overfitting
• Random Forests
• Machine Learning Competitions

• Creating, Reading and Writing
• Indexing, Selecting & Assigning
• Summary Functions and Maps
• Grouping and Sorting
• Data Types and Missing Values
• Renaming and Combining

• Introduction to Intermediate Machine Learning
• Missing Values
• Categorical Variables
• Pipelines
• Cross-Validation
• XGBoost
• Data Leakage

• What Is Feature Engineering
• Mutual Information
• Creating Features
• Clustering With K-Means
• Principal Component Analysis
• Target Encoding

• A Single Neuron
• Deep Neural Networks
• Stochastic Gradient Descent
• Overfitting and Underfitting
• Dropout and Batch Normalization
• Binary Classification

• The Convolutional Classifier
• Convolution and ReLU
• Maximum Pooling
• The Sliding Window
• Custom Convnets
• Data Augmentation

• Linear Regression With Time Series
• Trend
• Seasonality
• Time Series as Features
• Hybrid Models
• Forecasting With Machine Learning

• Introduction to AI Ethics
• Human-Centered Design for AI
• Identifying Bias in AI
• AI Fairness
• Model Cards

• Poo Kuan Hoong, Ph.D
• Erhan Azrai
• Dr Tan Yan Bin
• Leong Lai Fong
• Prof Dr Raveendran Paramesran
• Dr Sean Tan Chi Wee

• Benjamin Chang
• Hafiz Faizal
• Muhammad Afiq Che Man