SECURE IT Academy

Generative Adversarial Networks (GANs) is a modern machine learning technique to produce realistic but fake samples. GANs have two AI components, often modeled as deep neural networks, that play a zero-sum game to improve each other’s performance.

Learning a probability model from data is a key challenge in machine learning and statistics. A classical approach to this problem is to fit (approximately) an explicit probability model to the training data via a maximum likelihood estimation. However, there has been another approach to this problem using Generative Adversarial Networks (GANs). GANs view this problem as a game between two sets of functions: a generator whose goal is to generate fake samples that are close to the real data training samples and a discriminator whose goal is to distinguish between the real and fake samples. In this project, we aim to train some of the state-of-the-art GAN architectures on image datasets and produce fake but believable images. Through this, students will gain some familiarity with Python and PyTorch.

Researchers

Soheil Feizi
Assistant Professor, UMD Department of Computer Science

Aya Ismail
Graduate Student

Imagine that you are searching for a lost person in a forested environment. Or you are a first-responder searching for a survivor to rescue after a disaster. Searching for people or objects in the physical world is an important task in many societally important scenarios. In many of these scenarios, robots that are equipped with appropriate sensors (e.g., RGB and thermal cameras) can be used as scouts. These robots can assist human searchers, multiply their capabilities since they can operate tirelessly, and can reduce the risk to human lives especially when searching in unknown, potentially dangerous environments. In this project, we will develop algorithms for efficiently searching with a team of robots. https://youtu.be/BjJ2IhITya8

Researchers

Pratap Tokekar
Assistant Professor, UMD Department of Computer Science

Harnaik Dhami
Graduate Student

Vishnu Sharma
Graduate Student

Peihong Yu
Graduate Student...