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
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.
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.
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.
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.
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.
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.
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.
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.