This repository contains a project for classifying brain MRI images using transfer learning with VGG16. It aims to improve early detection of brain tumors, making a significant impact in medical imaging. 🧠💻

"**Exposure: Illuminate the Path to High-Performance, Real-Time Systems.**"

**Gradient Network** is a Layer-2 scaling platform on Testnet, allowing developers to build scalable, high-performance decentralized applications with optimized resource management.

This repository contains a study on predicting and preventing traffic accidents using machine learning in Greater London. It also examines how to automate these processes with MLOps. 🚦🛠️

Unofficial implementation of TimeGAN (Yoon et al., NIPS 2019) in TensorFlow 2.

Xiaoyang Song's Research with Dr. Wenbo Sun, Prof. Raed AI Kontar and Prof. Judy Jin from University of Michigan. This research focus on Out-of-Distribution Computer Vision data generation and detection.

A simple DCGAN that converts random noise to MNIST images

Unofficial implementation of TimeGAN (Yoon et al., NIPS 2019) in PyTorch 2.

GAN/diffusion model to generate synthetic financial time series data that preserves real-world statistical properties.

This repository contains a collection of deep learning projects implemented from scratch and using Keras/TensorFlow. The focus is on learning and experimenting with different neural network architectures for both foundational understanding and practical application.

Deep Learning for Computer Vision: A collection of 6 end-to-end applied AI projects focusing on training Neural Networks.

GAN-based imitation learning of user mouse movements

Synthetic data generation for tabular data

What if we replace the Convolution Layers inside GANs (Generative Adversarial Networks) with Cellular Automata. And train the Cellular Automata using a Genetic Algorithm.

HyMPS will be a platform-indipendent software suite for advanced audio/video contents production.

Benchmarking synthetic data generation methods.

A face generation model based on DCGAN architecture and WGAN-GP loss to prevent mode collapse

Conditional GAN for generating synthetic tabular data.

Code to accompany our International Conference on Pattern Recognition (ICPR) paper entitled - Leveraging Synthetic Subject Invariant EEG Signals for Zero Calibration BCI.