Projects

Tip: Feel free to ask the chatbot to summarize any project that interests you if the descriptions seem too long!

Skills Gained and Tools Used from Projects

Communication
Computer Vision
Convolutional Neural Networks
Data Augmentation
Data Visualization
Deep Learning
Fine-Tuning
Flask
Front-End Development
Gradio
Hugging Face
Image Classification
Machine Learning
Matplotlib
Natural Language Processing
Neural Network
Neural Network Implementation
NumPy
Pandas
Paper Reading
PyTorch
Python
React
Scikit-learn
Seaborn
Speech Recognition
Streamlit
TailwindCSS
Teamwork
TypeScript
UI/UX Design

Makemore Character Level Language Model (GPT)

Built a GPT implementation based on Karpathy's Makemore, exploring the fundamentals behind ChatGPT. Developed models from bigram to neural networks, implementing core operations from scratch to understand the math. Used techniques like He initialization and batch normalization to solve vanishing gradients. Trained a character-level GPT on Indonesian Twitter poems.

PythonPyTorchNeural Network ImplementationPaper ReadingNatural Language ProcessingDeep Learning

Narrative Nest - Team Project

An AI-powered storyboard creator for filmmakers using SDXL Lightning API. Users can quickly generate storyboard frames through AI prompts. Led UI/UX design, front-end development, and AI model integration with Gradio API.

ReactTypeScriptTailwindCSSGradioUI/UX DesignFront-End DevelopmentTeamworkCommunication

Monelytics - Team Project

AI-powered stock prediction streamlit web app for Indonesia's big four banks. Uses multiple ML models (Linear Regression, SVR, Random Forest, ARIMA, Decision Trees) and DL models (CNN, ANN, LSTM, Prophet) with RMSE and MAE metrics. Led data exploration, pre-processing, feature engineering, and LSTM implementation.

PythonScikit-learnPandasNumPyMatplotlibSeabornStreamlitMachine LearningDeep LearningData VisualizationTeamworkCommunication

NeuroCraft: Craft your own Neural Network

A web app for deep learning beginners to design neural networks without coding. Explore fundamentals like dense layers, batch-normalization, activation functions, and dropout while testing on MNIST and Fashion-MNIST datasets.

ReactTypeScriptPythonPyTorchTailwindCSSFlaskNeural NetworkDeep Learning

ResNet Image Classifier on CIFAR-10

Implemented ResNet architecture for image classification on CIFAR-10. Analyzed different architectures and the impact of data augmentation on model performance.

PythonPyTorchConvolutional Neural NetworksImage ClassificationData AugmentationPaper ReadingComputer VisionDeep Learning

Rebuilding Micrograd Library from Scratch

Rebuilding the Micrograd library from scratch to understand the underlying math and operations of a simple deep learning library. Implemented forward and backward propagation, gradient descent, and backpropagation using only pure Python Syntax.

Python

MNIST Digit Classifier: Building a Neural Network from Scratch

Building a neural network from scratch to classify handwritten digits from the MNIST dataset. Implemented forward and backward propagation, gradient descent, and backpropagation using only Numpy and basic mathematical operations.

PythonNumPyNeural Network ImplementationPaper ReadingDeep Learning

Fine-Tuning Whisper-Tiny for Speech Recognition

Experiment with fine-tuning the Whisper-Tiny model to improve speech recognition performance in France and Germany. There are 2 variant of models which were fine-tuned on the French and German subsets. The model was evaluated on the test set and compared with the original model and the performance is improved.

PythonHugging FaceSpeech RecognitionFine-TuningDeep LearningNatural Language Processing
[V3.5] Orchestrated & Created by Han 2025