KLay: Accelerating Neurosymbolic AI
A popular approach to neurosymbolic AI involves mapping logic formulas to arithmetic circuits (computation graphs consisting of sums and products) and passing the outputs of a neural network through these circuits. This approach enforces symbolic constraints onto a neural network in a principled and end-to-end differentiable way. Unfortunately, arithmetic circuits are challenging to run on modern AI accelerators as they exhibit a high degree of irregular sparsity. To address this limitation, we introduce knowledge layers (KLay), a new data structure to represent arithmetic circuits that can be efficiently parallelized on GPUs. Moreover, we contribute two algorithms used in the translation of traditional circuit representations to KLay and a further algorithm that exploits parallelization opportunities during circuit evaluations. We empirically show that KLay achieves speedups of multiple orders of magnitude over the state of the art, thereby paving the way towards scaling neurosymbolic AI to larger real-world applications.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
MVRackLay: Monocular Multi-View Layout Estimation for Warehouse Racks and Shelves
In this paper, we propose and showcase, for the first time, monocular multi-view layout estimation for warehouse racks and shelves. Unlike typical layout estimation methods, MVRackLay estimates multi-layered layouts, whe…
Monocular Multi-Layer Layout Estimation for Warehouse Racks
Given a monocular colour image of a warehouse rack, we aim to predict the bird's-eye view layout for each shelf in the rack, which we term as multi-layer layout prediction. To this end, we present RackLay, a deep neural …
Dataset GenerationMaskLayer: Enabling scalable deep learning solutions by training embedded feature sets
Deep learning-based methods have shown to achieve excellent results in a variety of domains, however, some important assets are absent. Quality scalability is one of them. In this work, we introduce a novel and generic …
Defining neurosymbolic AI
Neurosymbolic AI focuses on integrating learning and reasoning, in particular, on unifying logical and neural representations. Despite the existence of an alphabet soup of neurosymbolic AI systems, the field is lacking a…
Neurosymbolic Reinforcement Learning and Planning: A Survey
The area of Neurosymbolic Artificial Intelligence (Neurosymbolic AI) is rapidly developing and has become a popular research topic, encompassing sub-fields such as Neurosymbolic Deep Learning (Neurosymbolic DL) and Neuro…
reinforcement-learningReinforcement LearningReinforcement Learning (RL)Survey