Abstractive Scientific Text Summarization using Generative Adversarial Networks
-
Updated
Feb 28, 2018 - TeX
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.
Abstractive Scientific Text Summarization using Generative Adversarial Networks
Generative Adversarial Networks(GANs) | Semester 7 Artificial Intelligence & Data Science Seminar files
Fast Cross-Domain Unsupervised Object detection through Online Style Transfer
Text of Bachelor's Thesis - Generating Faces with Generative Adversarial Networks.
Répertoire du Rapport de projet Salamandre
thesis research on applying deep learning in asset pricing with Generative Adversarial Model
Applying Dual averaging method to Saddle point problem in GAN
This repository contains the code for the paper "Icon Generation with Conditional GANs".
Project for DSA5204: Image to Image Translation Study
CapsNet based DCGAN, B.E Capstone project
The LaTeX codes of the paper that was accpeted to GECCO 2020.
covert-ml is a GAN-based covert communication method that enables establishing a reliable, undetectable covert channel within autoencoder wireless communication systems with the minimum impact.
Weak Segmentation-Guided GAN for Realistic Color Edition presented at ICIAP 2023
Training a GAN using superconductivity data
Deep Generative Models course, 2021
time series forecasting with deep learning
Released June 10, 2014