Zobrazeno 1 - 10
of 16
pro vyhledávání: '"Ahmetoğlu, Alper"'
Discovering the symbols and rules that can be used in long-horizon planning from a robot's unsupervised exploration of its environment and continuous sensorimotor experience is a challenging task. The previous studies proposed learning symbols from s
Externí odkaz:
http://arxiv.org/abs/2401.01123
Exploratoration and self-observation are key mechanisms of infant sensorimotor development. These processes are further guided by parental scaffolding accelerating skill and knowledge acquisition. In developmental robotics, this approach has been ado
Externí odkaz:
http://arxiv.org/abs/2309.00904
In this paper, we propose and realize a new deep learning architecture for discovering symbolic representations for objects and their relations based on the self-supervised continuous interaction of a manipulator robot with multiple objects on a tabl
Externí odkaz:
http://arxiv.org/abs/2309.00889
In this paper, we propose a concept learning architecture that enables a robot to build symbols through self-exploration by interacting with a varying number of objects. Our aim is to allow a robot to learn concepts without constraints, such as a fix
Externí odkaz:
http://arxiv.org/abs/2208.01021
Autor:
Gokay, Dilara, Simsar, Enis, Atici, Efehan, Ahmetoglu, Alper, Yuksel, Atif Emre, Yanardag, Pinar
In this paper, we propose a graph-based image-to-image translation framework for generating images. We use rich data collected from the popular creativity platform Artbreeder (http://artbreeder.com), where users interpolate multiple GAN-generated ima
Externí odkaz:
http://arxiv.org/abs/2108.09752
Abstraction is an important aspect of intelligence which enables agents to construct robust representations for effective decision making. In the last decade, deep networks are proven to be effective due to their ability to form increasingly complex
Externí odkaz:
http://arxiv.org/abs/2106.10354
We propose a novel general method that finds action-grounded, discrete object and effect categories and builds probabilistic rules over them for non-trivial action planning. Our robot interacts with objects using an initial action repertoire that is
Externí odkaz:
http://arxiv.org/abs/2012.02532
Recent works show that learning contextualized embeddings for words is beneficial for downstream tasks. BERT is one successful example of this approach. It learns embeddings by solving two tasks, which are masked language model (masked LM) and the ne
Externí odkaz:
http://arxiv.org/abs/2011.04451
Autor:
Ahmetoğlu, Alper, Alpaydın, Ethem
Generative adversarial networks (GANs) are deep neural networks that allow us to sample from an arbitrary probability distribution without explicitly estimating the distribution. There is a generator that takes a latent vector as input and transforms
Externí odkaz:
http://arxiv.org/abs/1911.02069
Publikováno v:
In Neural Networks February 2022 146:22-35
