no code implementations • 28 Mar 2024 • Yuhang Li, Xin Dong, Chen Chen, Jingtao Li, Yuxin Wen, Michael Spranger, Lingjuan Lyu
Synthetic image data generation represents a promising avenue for training deep learning models, particularly in the realm of transfer learning, where obtaining real images within a specific domain can be prohibitively expensive due to privacy and intellectual property considerations.
no code implementations • NeurIPS 2020 • Oscar Chang, Lampros Flokas, Hod Lipson, Michael Spranger
We propose an MNIST based test as an easy instance of the symbol grounding problem that can serve as a sanity check for differentiable symbolic solvers in general.
1 code implementation • 26 Jun 2023 • Samy Badreddine, Luciano Serafini, Michael Spranger
A significant trend in the literature involves integrating axioms and facts in loss functions by grounding logical symbols with neural networks and operators with fuzzy semantics.
2 code implementations • ICLR 2023 • Junyuan Hong, Lingjuan Lyu, Jiayu Zhou, Michael Spranger
The proposed MECTA is efficient and can be seamlessly plugged into state-of-theart CTA algorithms at negligible overhead on computation and memory.
no code implementations • 23 Oct 2022 • Junyuan Hong, Lingjuan Lyu, Jiayu Zhou, Michael Spranger
As deep learning blooms with growing demand for computation and data resources, outsourcing model training to a powerful cloud server becomes an attractive alternative to training at a low-power and cost-effective end device.
no code implementations • 12 Oct 2022 • Homayun Afrabandpey, Michael Spranger
Through user studies, we demonstrate that incorporating causal constraints during CF generation results in significantly better explanations in terms of feasibility and desirability for participants.
no code implementations • 10 Apr 2022 • Kenzo Lobos-Tsunekawa, Akshay Srinivasan, Michael Spranger
Multi-agent RL is rendered difficult due to the non-stationary nature of environment perceived by individual agents.
no code implementations • 11 Nov 2021 • Ryuji Imamura, Takuma Seno, Kenta Kawamoto, Michael Spranger
We demonstrate that the proposed method performs expert human-level vehicle control under high-speed driving scenarios even with game screen images as high-dimensional inputs.
no code implementations • 29 Sep 2021 • Uchenna Akujuobi, Xiangliang Zhang, Sucheendra Palaniappan, Michael Spranger
In this paper, we study the automatic hypothesis generation (HG) problem, focusing on explainability.
no code implementations • ICLR Workshop Learning_to_Learn 2021 • Badr AlKhamissi, Muhammad ElNokrashy, Michael Spranger
In this work, we analyze the reinstatement mechanism introduced by Ritter et al. (2018) to reveal two classes of neurons that emerge in the agent's working memory (an epLSTM cell) when trained using episodic meta-RL on an episodic variant of the Harlow visual fixation task.
no code implementations • 1 Jan 2021 • Kana Maruyama, Michael Spranger
We propose and test two variants of the model.
1 code implementation • 25 Dec 2020 • Samy Badreddine, Artur d'Avila Garcez, Luciano Serafini, Michael Spranger
In this paper, we present Logic Tensor Networks (LTN), a neurosymbolic formalism and computational model that supports learning and reasoning through the introduction of a many-valued, end-to-end differentiable first-order logic called Real Logic as a representation language for deep learning.
no code implementations • NeurIPS 2020 • Uchenna Akujuobi, Jun Chen, Mohamed Elhoseiny, Michael Spranger, Xiangliang Zhang
Then, the key is to capture the temporal evolution of node pair (term pair) relations from just the positive and unlabeled data.
1 code implementation • 27 Aug 2019 • Andreas Gerken, Michael Spranger
This paper presents a novel model-free Reinforcement Learning algorithm for learning behavior in continuous action, state, and goal spaces.
no code implementations • 15 Jun 2019 • Samy Badreddine, Michael Spranger
Facts are provided as background knowledge a priori to learning a policy for how to act in the world.
no code implementations • 15 May 2019 • Artur d'Avila Garcez, Marco Gori, Luis C. Lamb, Luciano Serafini, Michael Spranger, Son N. Tran
In spite of the recent impact of AI, several works have identified the need for principled knowledge representation and reasoning mechanisms integrated with deep learning-based systems to provide sound and explainable models for such systems.
1 code implementation • WS 2017 • Wojciech Kusa, Michael Spranger
This paper evaluates the impact of various event extraction systems on automatic pathway curation using the popular mTOR pathway.
no code implementations • 7 Jul 2017 • Jens Nevens, Michael Spranger
This paper investigates the role of tutor feedback in language learning using computational models.
1 code implementation • 30 Sep 2016 • Michael Spranger, Katrien Beuls
This paper discusses lexicon word learning in high-dimensional meaning spaces from the viewpoint of referential uncertainty.
BIG-bench Machine Learning Vocal Bursts Intensity Prediction
no code implementations • WS 2016 • Michael Spranger, Sucheendra K. Palaniappan, Samik Ghosh
This paper evaluates the difference between human pathway curation and current NLP systems.
1 code implementation • WS 2015 • Michael Spranger, Sucheendra K. Palaniappan, Samik Ghosh
This paper describes an an open-source software system for the automatic conversion of NLP event representations to system biology structured data interchange formats such as SBML and BioPAX.
no code implementations • 26 Jul 2016 • Michael Spranger, Jakob Suchan, Mehul Bhatt, Manfred Eppe
This paper presents a computational model of the processing of dynamic spatial relations occurring in an embodied robotic interaction setup.
no code implementations • 26 Jul 2016 • Michael Spranger
This paper discusses grounded acquisition experiments of increasing complexity.
no code implementations • 20 Jul 2016 • Michael Spranger, Jakob Suchan, Mehul Bhatt
We present a system for generating and understanding of dynamic and static spatial relations in robotic interaction setups.