Výsledky vyhledávání - "Kissner, Michael"

Report

An All-Optical General-Purpose CPU and Optical Computer Architecture

Autor: Kissner, Michael, Del Bino, Leonardo, Päsler, Felix, Caruana, Peter, Ghalanos, George

Energy efficiency of electronic digital processors is primarily limited by the energy consumption of electronic communication and interconnects. The industry is almost unanimously pushing towards replacing both long-haul, as well as local chip interc

Externí odkaz: http://arxiv.org/abs/2403.00045

Zobrazit plný text záznamu

Report

A Neural-Symbolic Framework for Mental Simulation

Autor: Kissner, Michael

We present a neural-symbolic framework for observing the environment and continuously learning visual semantics and intuitive physics to reproduce them in an interactive simulation. The framework consists of five parts, a neural-symbolic hybrid netwo

Externí odkaz: http://arxiv.org/abs/2008.02356

Zobrazit plný text záznamu

Report

Hacking Neural Networks: A Short Introduction

Autor: Kissner, Michael

A large chunk of research on the security issues of neural networks is focused on adversarial attacks. However, there exists a vast sea of simpler attacks one can perform both against and with neural networks. In this article, we give a quick introdu

Externí odkaz: http://arxiv.org/abs/1911.07658

Zobrazit plný text záznamu

Report

Adding Intuitive Physics to Neural-Symbolic Capsules Using Interaction Networks

Autor: Kissner, Michael, Mayer, Helmut

Many current methods to learn intuitive physics are based on interaction networks and similar approaches. However, they rely on information that has proven difficult to estimate directly from image data in the past. We aim to narrow this gap by infer

Externí odkaz: http://arxiv.org/abs/1905.09891

Zobrazit plný text záznamu

Report

A Neural-Symbolic Architecture for Inverse Graphics Improved by Lifelong Meta-Learning

Autor: Kissner, Michael, Mayer, Helmut

Publikováno v: 41st German Conference, GCPR 2019, Proceedings

We follow the idea of formulating vision as inverse graphics and propose a new type of element for this task, a neural-symbolic capsule. It is capable of de-rendering a scene into semantic information feed-forward, as well as rendering it feed-backwa

Externí odkaz: http://arxiv.org/abs/1905.08910

Zobrazit plný text záznamu