Logic Tensor Networks

نویسندگان

چکیده

Attempts at combining logic and neural networks into neurosymbolic approaches have been on the increase in recent years. In a system, symbolic knowledge assists deep learning, which typically uses sub-symbolic distributed representation, to learn reason higher level of abstraction. We present Logic Tensor Networks (LTN), framework that supports querying, learning reasoning with both rich data abstract about world. LTN introduces fully differentiable logical language, called Real Logic, whereby elements first-order signature are grounded onto using computational graphs fuzzy semantics. show provides uniform language represent compute efficiently many most important AI tasks such as multi-label classification, relational clustering, semi-supervised regression, embedding query answering. implement illustrate each above several simple explanatory examples TensorFlow 2. The results indicate can be general powerful for AI.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Logic Tensor Networks for Semantic Image Interpretation

Semantic Image Interpretation (SII) is the task of extracting structured semantic descriptions from images. It is widely agreed that the combined use of visual data and background knowledge is of great importance for SII. Recently, Statistical Relational Learning (SRL) approaches have been developed for reasoning under uncertainty and learning in the presence of data and rich knowledge. Logic T...

متن کامل

Resource modalities in tensor logic

The description of resources in game semantics has never achieved the simplicity and precision of linear logic, because of the misleading conception that linear logic is more primitive than game semantics. Here, we defend the opposite view, and thus advocate that game semantics is conceptually more primitive than linear logic. This revised point of view leads us to introduce tensor logic, a pri...

متن کامل

Tensor Contraction&Regression Networks

To date, most convolutional neural network architectures output predictions by flattening 3rd-order activation tensors, and applying fully-connected output layers. This approach has two drawbacks: (i) we lose rich, multi-modal structure during the flattening process and (ii) fully-connected layers require many parameters. We present the first attempt to circumvent these issues by expressing the...

متن کامل

Tensor Switching Networks

We present a novel neural network algorithm, the Tensor Switching (TS) network, which generalizes the Rectified Linear Unit (ReLU) nonlinearity to tensor-valued hidden units. The TS network copies its entire input vector to different locations in an expanded representation, with the location determined by its hidden unit activity. In this way, even a simple linear readout from the TS representa...

متن کامل

Logic Tensor Networks: Deep Learning and Logical Reasoning from Data and Knowledge

We propose Logic Tensor Networks: a uniform framework for integrating automatic learning and reasoning. A logic formalism called Real Logic is defined on a first-order language whereby formulas have truth-value in the interval [0,1] and semantics defined concretely on the domain of real numbers. Logical constants are interpreted as feature vectors of real numbers. Real Logic promotes a well-fou...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: Artificial Intelligence

سال: 2022

ISSN: ['2633-1403']

DOI: https://doi.org/10.1016/j.artint.2021.103649