Research & Talks

research

E-Commerce Merchant Categorization using Website Information

🇰🇷 9th International Conference on Web Intelligence, Mining and Semantics, Seoul

Estimating the Collected Funding Amount of the Social Projects in a Crowdfunding Platform

🇮🇩 2017 International Conference on Advanced Computer Science and Information Systems (ICACSIS), Jakarta

talks

You can view the public feedback that people have given about my talks/workshops on Twitter here.
If you need a speaker bio, check it out here.

2020

Workshop: BERT for Text Classificaiton with Keras/TensorFlow 2

🇲🇾🇸🇬 WTM DevFest Kuala Lumpur - Singapore 2020

In this workshop, we'll learn how we can utilize BERT, a technique for natural language processing (NLP) pre-training to perform our own tasks. For this workshop we will use BERT in TensorFlow 2 for a text classification task.

slidesnotebook

Crisis to Change: How to create your own opportunities and building your developer career

🇮🇩 DevFest Indonesia 2020

Roundtable discussion on career development and personal growth.

video

Build Your Own Image Classifier with Transfer Learning

🇮🇩 Belajar Bareng Tim Data Science Gojek

Most deep learning tasks are notorious for requiring a large amount of data, but worry not, in this talk we'll go through the step by step on how you can build your own image classifier trained on a small dataset with the help of transfer learning.

All ticket sales will be donated to help daily workers impacted by COVID-19

Introduction to Machine Learning

🇮🇩 UX Indonesia • 🇮🇩 Nusantech Webinar

Machine learning is becoming a part of many products that we design, build, and use today. But what is machine learning actually and how does it work? This talk will help you understand the definition of machine learning and its difference from traditional programming, how machine learning works, and how machine learning powers various applications and products.

slides (UX Indonesia)slides (Nusantech webinar)code (Nusantech webinar)

Keynote: A Whirlwind Tour of Machine Learning with TensorFlow

🇮🇩 International Women's Day 2020

This talk is an open invitation for everyone—from students, web developers, data scientists, and many others—to come on board and explore the world of machine learning with the help of TensorFlow. We will discuss about what machine learning is and what it can do, the things that you need to know before you build machine learning applications, go through examples and demos of various machine learning applications to spark your ideas, and see what's next in machine learning.

slides

First Steps Towards Your First Machine Learning Project

🇧🇳 Girls in ICT Brunei

slides

Call for Proposals (CFP) 101

🇮🇩 Global Diversity CFP Day

slides

2019

Machine Learning on the Web

🇧🇳 DevFest Brunei • 🇸🇬 DevFest Singapore • 🇲🇲 DevFest Yangon • 🇮🇩 JSDay Indonesia

Machine learning is now more accessible than ever thanks to the recent developments of various libraries & tools. In this talk, we'll learn about the things you need to know before you build machine learning applications, how to get started with machine learning using JavaScript and libraries such as TensorFlow.js and ml5.js (a higher-level library built on top of TensorFlow.js), how we can run and train machine learning models right on the browser, and how we can make our models interact with input sources with just a few steps.

codeslides (DevFest)slides (JSDay ID)

Data Science in the Browser with Iodide

🇸🇬 MozTechSpeakers Meetup

slides

Workshop: Data Preparation with Python

🇮🇩 DQLab Meetup

codeslides

Introduction to Word Embeddings

🇨🇿 PyCon CZ 2019

France is to Paris like Czechia is to _______. If I ask you to fill the blank, you would answer "Prague" right away even without me giving a clue such as "the answer is a capital city". However, computers don't know that Prague belongs to the same "category" as Paris and other capital cities unless we tell them so. If we want to get computers to understand human language as well as we do, there are way too many things that we need to teach computers explicitly. Is there a better way? With word embeddings, we represent words by a series of numbers. We'll delve into the details of what word embeddings actually are and why we need them, popular word embedding models, what problems you can solve using word embeddings, and how you can use word embeddings with Python.

codeslidesvideo