deep-learning

Introduction to MLX for Swift developers

Whispers in the Machine: Confidentiality in Agentic Systems

A Bach music generator with Artificial Intelligence. This model is made by a VQ-VAE + Transformer (decoder-only). Sequences of midi 1 quarter length are compressed into 16 codebooks via VQ-VAE and a transformer learns how to generate the codebooks sequence to obtain a midi score.

Google QUEST Q&A Labeling Kaggle Competition 6th Place Solution

APDTFlow is a modern and extensible forecasting framework for time series data that leverages advanced techniques including neural ordinary differential equations (Neural ODEs), transformer-based components, and probabilistic modeling. Its modular design allows researchers and practitioners to experiment with multiple forecasting models and easily

An implementation of Conformer: Convolution-augmented Transformer for Speech Recognition, a Transformer Variant in TensorFlow/Keras

Implementation of GATO style Generalist Multimodal model capable of image, text, RL and Robotics tasks

🤹 MultiTRON: Pareto Front Approximation for Multi-Objective Session-Based Recommender Systems, accepted at ACM RecSys 2024.

Code for evaluating uncertainty estimation methods for Transformer-based architectures in natural language understanding tasks.

Designing and Deploying LLM Pipelines

Implementation of Z-BERT-A: a zero-shot pipeline for unknown intent detection.

Pre-rendered regularization images of men and women, mainly faces, seeking to generate more realistic images (without wax skin)

In this project, several approaches for training/finetuning an audio gender recognition is provided. The code can simply be used for any other audio classification task by simply changing the number of classes and the input dataset.

Baseline model for multimodal classification based on images and text. Text representation obtained from pretrained BERT base model and image representation obtained from VGG16 pretrained model.

An end-to-end image captioning project using a CNN encoder (ResNet-50) and LSTM decoder in PyTorch. Includes vocabulary building, preprocessing, training with BLEU evaluation, and inference. Generates natural language captions for images with saved metrics, model checkpoints, and visualization outputs.

ONNX-compatible Fast SeamlessM4T—Massively Multilingual & Multimodal Machine Translation

Building a suicidal text detection model and mental health chatbot with deep learning models and transformers.

This repo contains my work & The code base for this Deep Learning Specialization offered by deeplearning.AI

RATransformers 🐭- Make your transformer (like BERT, RoBERTa, GPT-2 and T5) Relation Aware!

Official implementation of the paper: Unsupervised MRI Reconstruction via Zero-Shot Learned Adversarial Transformers