Informed machine learning–a taxonomy and survey of integrating prior knowledge into learning systems

L Von Rueden, S Mayer, K Beckh… - … on Knowledge and …, 2021 - ieeexplore.ieee.org
Despite its great success, machine learning can have its limits when dealing with insufficient
training data. A potential solution is the additional integration of prior knowledge into the …

Iconqa: A new benchmark for abstract diagram understanding and visual language reasoning

P Lu, L Qiu, J Chen, T **a, Y Zhao, W Zhang… - arxiv preprint arxiv …, 2021 - arxiv.org
Current visual question answering (VQA) tasks mainly consider answering human-
annotated questions for natural images. However, aside from natural images, abstract …

Deep learning with logical constraints

E Giunchiglia, MC Stoian, T Lukasiewicz - arxiv preprint arxiv:2205.00523, 2022 - arxiv.org
In recent years, there has been an increasing interest in exploiting logically specified
background knowledge in order to obtain neural models (i) with a better performance,(ii) …

Self-training with weak supervision

G Karamanolakis, S Mukherjee, G Zheng… - arxiv preprint arxiv …, 2021 - arxiv.org
State-of-the-art deep neural networks require large-scale labeled training data that is often
expensive to obtain or not available for many tasks. Weak supervision in the form of domain …

A causal framework to quantify the robustness of mathematical reasoning with language models

A Stolfo, Z **, K Shridhar, B Schölkopf… - arxiv preprint arxiv …, 2022 - arxiv.org
We have recently witnessed a number of impressive results on hard mathematical reasoning
problems with language models. At the same time, the robustness of these models has also …

Stochastic dispatch of energy storage in microgrids: An augmented reinforcement learning approach

Y Shang, W Wu, J Guo, Z Ma, W Sheng, Z Lv, C Fu - Applied Energy, 2020 - Elsevier
The dynamic dispatch (DD) of battery energy storage systems (BESSs) in microgrids
integrated with volatile energy resources is essentially a multiperiod stochastic optimization …

Neupsl: Neural probabilistic soft logic

C Pryor, C Dickens, E Augustine, A Albalak… - arxiv preprint arxiv …, 2022 - arxiv.org
In this paper, we introduce Neural Probabilistic Soft Logic (NeuPSL), a novel neuro-symbolic
(NeSy) framework that unites state-of-the-art symbolic reasoning with the low-level …

[PDF][PDF] Informed machine learning–towards a taxonomy of explicit integration of knowledge into machine learning

L Von Rueden, S Mayer, J Garcke, C Bauckhage… - Learning, 2019 - researchgate.net
Despite the great successes of machine learning, it can have its limits when dealing with
insufficient training data. A potential solution is to incorporate additional knowledge into the …

[PDF][PDF] Learning Where and When to Reason in Neuro-Symbolic Inference.

C Cornelio, J Stuehmer, SX Hu, TM Hospedales - NeSy, 2023 - cs.ox.ac.uk
The imposition of hard constraints on the output of neural networks is a highly desirable
capability, as it instills confidence in AI by ensuring that neural network predictions adhere to …

AI2D-RST: A multimodal corpus of 1000 primary school science diagrams

T Hiippala, M Alikhani, J Haverinen… - Language Resources …, 2021 - Springer
This article introduces AI2D-RST, a multimodal corpus of 1000 English-language diagrams
that represent topics in primary school natural sciences, such as food webs, life cycles …