My portfolio seems too static. What should I do to make it more interactive and fun while also applying my NLP knowledge on it?
Recently, I just developed an AI-powered portfolio, which aims to level-up my static web portfolio. I embedded a personal AI assistant that can answer your queries about me, naturally, with the right response!
Whether you are a recruiter, a colleague, or anyone on the internet, if you ask “him” the right question, you will know me better! (PS: “He” knows almost anything about me).
Feel free to interact with my personal AI assistant here. In…
A sudden spike in credit money refund, an enormous increase in website traffic, and unusual weather behavior are some of the examples of anomaly detection use-cases in time-series data.
Here, in Bukalapak, we’re also faced with many such use-cases, which gives rise to the need for an in-house anomaly detection system. Through this article, we will share some of our approaches to solve those problems.
There are many articles and tutorials available out there on how to develop a time-series anomaly detection system, starting from utilizing time-series decomposition, statistical forecasting algorithm, or even by exploiting the power of Neural Network.
How often that phrase came out of your mind when you have a chat with “someone” in your favorite app or messenger?
I believe almost all of us have had the experience of interacting with a chatbot. Sometimes we could immediately know that it’s a bot, but sometimes we couldn't since it replied to our messages in a very natural way.
Here, in Bukalapak, we have also developed chatbots for several use-cases. …
Let say you have blasted your beautifully curated Google Form to the public.
You have received their responses and monitor them in a real-time dashboard.
Based on their responses, you then saw that you have to send them more follow-up questions.
For the sake of a better user experience, arguably it’s better that you already provide default answers for some questions that are more likely have not changed over a short period of time.
Those questions can be related to demographic questions, such as gender, age, income, or contacts, such as email or WhatsApp.
Of course, you don’t want to…
In the first part of this series, we’ve learned about some important terms and concepts in Reinforcement Learning (RL). We’ve also learned how RL is applied in an autonomous race car in the second part.
In this article, we will learn about the taxonomy of Reinforcement Learning algorithms. We will not only learn about one taxonomy but several taxonomies from many different points of view.
After we have familiar with the taxonomy, we will learn more about each of the branches in future episodes. …
In the first part of this series, we’ve learned about some important terms and concepts in Reinforcement Learning (RL). We’ve also learned how RL works at a high-level.
Before we dive deeper into the theory behind RL, I invite you to learn with me about RL based on its SUPER cool application, AWS DeepRacer.
AWS DeepRacer is an autonomous 1/18th scale race car designed to test RL models by racing on a physical track. There are three race types in AWS DeepRacer:
Are you in a situation where…
…you save dozens of memorable photos with your loved one and want to give him/her something memorable that is made by yourself?
…you are both an art and tech enthusiast who want to produce something not only artsy but also techy?
…you just want to build a mosaic image generator out of curiosity and challenge the limit of yourself?
If so, then this article is for you!!
For me, it was all started during my internship at one of Computer Vision-focused startups in Indonesia. It was very exciting for me to learn how to…
An open invitation for all aspiring Reinforcement Learning (RL) practitioner to learn RL together with me in the next 3 months
Not so while ago, I joined an RL Bootcamp held by AWS and Jakarta Machine Learning (JML). We, the participants, will be intensively mentored by the experienced representatives from AWS. The mentors will guide and introduce us to the ‘right path’ to learn about RL in the next 3 months. Not only learning the theories but we will also learn how to apply it in the real application!
Isn’t it interesting?? What makes this more interesting for you is:
Let say your Google Form is shared to the public.
You want to monitor the updates of the response in a dashboard which can be filtered using several variables and presented in the multi-variable charts.
Moreover, you want it to be in real-time and shareable to any of your stakeholders.
Clearly the “Responses” section in your Google Form is not the answer for this scenario. In this article, I will give a step-by-step tutorial on how to visualize real-time Google Form responses in Streamlit dashboard, starting from importing responses in google sheets until the deployment of the dashboard. …
Is it possible to do text-classification with 150 target classes using only 10 labelled samples for each class but still get a good performance?
Starting from that simple question, I start to do research in order to answer that question. After spending several hours, I ended up with GAN-BERT. What is GAN-BERT? What experiment that I did using GAN-BERT? In this article, I will try to give a brief introduction of GAN-BERT and also the implementation of it for Intent Classification using CLINC150 Dataset.
In Natural Language Processing (NLP) field, BERT or Bidirectional Encoder Representations from Transformers is a well-known…
Data Science Consultant at The World Bank | AI Research Engineer at Bukalapak