Generative adversarial networks (GAN) are a class of generative machine learning frameworks. A GAN consists of two competing neural networks, often termed the Discriminator network and the Generator network. GANs have been shown to be powerful generative models and are able to successfully generate new data given a large enough training dataset.
Benchmarking synthetic data generation methods.
HyMPS will be a platform-indipendent software suite for advanced audio/video contents production.
Main folder. Material related to my books on synthetic data and generative AI. Also contains documents blending components from several folders, or covering topics spanning across multiple folders..
🎓 Decompose Korean component by using opencv
Synthetic data generation for tabular data
Image-to-Image Translation in PyTorch
Conditional GAN for generating synthetic tabular data.
Synthetic data generators for tabular and time-series data
Extreme value theory and GANs to generate compound coastal hazards (wind speed + sea level pressure) from ERA5 reanalysis data over the Bay of Bengal.
The Super-Resolution for Renewable Resource Data (sup3r) software uses generative adversarial networks to create synthetic high-resolution wind and solar spatiotemporal data from coarse low-resolution inputs.
My notes / works on deep learning from Coursera
A machine learning library for detecting anomalies in signals.
Official codebase for the SCULPT paper published in CVPR 2024
Synthetic Data Generation for mixed-type, multivariate time series.
Official PyTorch implementation for ChimeraMix: Image Classification on Small Datasets via Masked Feature Mixing (IJCAI 2022)
iSeeBetter: Spatio-Temporal Video Super Resolution using Recurrent-Generative Back-Projection Networks | Python3 | PyTorch | GANs | CNNs | ResNets | RNNs | Published in Springer Journal of Computational Visual Media, September 2020, Tsinghua University Press
This is a chat-bot API for a GAN based text-to-image generator
Generative Adversarial Networks for generating handwritten digits. Model trained on handwritten digit dataset using TensorFlow for 10000 epochs.
Generating tabular datasets under differential privacy
C++ Implementation of PyTorch Tutorials for Everyone
Released June 10, 2014