Výsledky vyhledávání - "Pirnay, Jonathan"

Report

GraphXForm: Graph transformer for computer-aided molecular design with application to extraction

Autor: Pirnay, Jonathan, Rittig, Jan G., Wolf, Alexander B., Grohe, Martin, Burger, Jakob, Mitsos, Alexander, Grimm, Dominik G.

Generative deep learning has become pivotal in molecular design for drug discovery and materials science. A widely used paradigm is to pretrain neural networks on string representations of molecules and fine-tune them using reinforcement learning on

Externí odkaz: http://arxiv.org/abs/2411.01667

Zobrazit plný text záznamu

Report

Take a Step and Reconsider: Sequence Decoding for Self-Improved Neural Combinatorial Optimization

Autor: Pirnay, Jonathan, Grimm, Dominik G.

Publikováno v: 27th European Conference on Artificial Intelligence (ECAI), 2024

The constructive approach within Neural Combinatorial Optimization (NCO) treats a combinatorial optimization problem as a finite Markov decision process, where solutions are built incrementally through a sequence of decisions guided by a neural polic

Externí odkaz: http://arxiv.org/abs/2407.17206

Zobrazit plný text záznamu

Report

Self-Improvement for Neural Combinatorial Optimization: Sample without Replacement, but Improvement

Autor: Pirnay, Jonathan, Grimm, Dominik G.

Publikováno v: Transactions on Machine Learning Research (TMLR) 06/2024, Featured Certification

Current methods for end-to-end constructive neural combinatorial optimization usually train a policy using behavior cloning from expert solutions or policy gradient methods from reinforcement learning. While behavior cloning is straightforward, it re

Externí odkaz: http://arxiv.org/abs/2403.15180

Zobrazit plný text záznamu

Report

Deep reinforcement learning uncovers processes for separating azeotropic mixtures without prior knowledge

Autor: Göttl, Quirin, Pirnay, Jonathan, Burger, Jakob, Grimm, Dominik G.

Process synthesis in chemical engineering is a complex planning problem due to vast search spaces, continuous parameters and the need for generalization. Deep reinforcement learning agents, trained without prior knowledge, have shown to outperform hu

Externí odkaz: http://arxiv.org/abs/2310.06415

Zobrazit plný text záznamu

Report

Policy-Based Self-Competition for Planning Problems

Autor: Pirnay, Jonathan, Göttl, Quirin, Burger, Jakob, Grimm, Dominik Gerhard

Publikováno v: The Eleventh International Conference on Learning Representations, 2023

AlphaZero-type algorithms may stop improving on single-player tasks in case the value network guiding the tree search is unable to approximate the outcome of an episode sufficiently well. One technique to address this problem is transforming the sing

Externí odkaz: http://arxiv.org/abs/2306.04403

Zobrazit plný text záznamu

Report

Convex Envelope Method for determining liquid multi-phase equilibria in systems with arbitrary number of components

Autor: Göttl, Quirin, Pirnay, Jonathan, Grimm, Dominik G., Burger, Jakob

The determination of liquid phase equilibria plays an important role in chemical process simulation. This work presents a generalization of an approach called the convex envelope method (CEM), which constructs all liquid phase equilibria over the who

Externí odkaz: http://arxiv.org/abs/2304.12025

Zobrazit plný text záznamu

Report

Inpainting Transformer for Anomaly Detection

Autor: Pirnay, Jonathan, Chai, Keng

Anomaly detection in computer vision is the task of identifying images which deviate from a set of normal images. A common approach is to train deep convolutional autoencoders to inpaint covered parts of an image and compare the output with the origi

Externí odkaz: http://arxiv.org/abs/2104.13897

Zobrazit plný text záznamu