Informed machine learning–a taxonomy and survey of integrating prior knowledge into learning systems
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 …
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
Current visual question answering (VQA) tasks mainly consider answering human-
annotated questions for natural images. However, aside from natural images, abstract …
annotated questions for natural images. However, aside from natural images, abstract …
Deep learning with logical constraints
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) …
background knowledge in order to obtain neural models (i) with a better performance,(ii) …
Self-training with weak supervision
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 …
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
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 …
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
The dynamic dispatch (DD) of battery energy storage systems (BESSs) in microgrids
integrated with volatile energy resources is essentially a multiperiod stochastic optimization …
integrated with volatile energy resources is essentially a multiperiod stochastic optimization …
Neupsl: Neural probabilistic soft logic
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 …
(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
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 …
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.
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 …
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
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 …
that represent topics in primary school natural sciences, such as food webs, life cycles …