Repositories (8)
A comprehensive implementation of a Neurosymbolic framework for Visual Question Answering (VQA) on the CLEVR dataset. This project translates natural language questions into symbolic programs using three different learning strategies: Supervised (LSTM & Transformer), Reinforcement Learning (REINFORCE), and In-Context Learning (LLM).
A from-scratch PyTorch implementation of Low-Rank Adaptation (LoRA) to efficiently fine-tune BERT models for text classification. This project compares the performance and parameter efficiency of LoRA, full fine-tuning, and from-scratch training.
An exploration of self-supervised and contrastive learning techniques (SimSiam) on CIFAR-10 dataset, comparing them against a supervised baseline in a low-data regime.
A from-scratch implementation of a scaled-down GPT-2 model in PyTorch, trained on the Snappfood dataset for sentiment-controlled Persian text generation.
An exploration of AI-driven symbolic regression, implementing and analyzing two key methods: Equation Learner (EQL) neural networks and a Seq2Seq Transformer model.
A complete implementation of the "Attention Is All You Need" Transformer model from scratch using PyTorch. This project focuses on building and training a Transformer for neural machine translation (English-to-Italian) on the OpusBooks dataset.
A scratch-built NumPy implementation of a Fully Connected Neural Network, with a sequential model API, a variety of layers (Linear, ReLU, BatchNorm), loss functions (MSE, SoftmaxCrossEntropy), and a robust training `Solver` to create and train multi-layer perceptrons for both classification and regression.
A project exploring agentic AI for Visual Question Answering. Compares zero-shot VLM performance (Transformers) against advanced pipelines using OpenCV (tool-use) and Chain-of-Thought (reasoning).