Related papers: Holography Transformer
Motivated by the close relations of the renormalization group with both the holography duality and the deep learning, we propose that the holographic geometry can emerge from deep learning the entanglement feature of a quantum many-body…
We investigate the behaviors of entanglement entropy in the holographical insulator/superconductor phase transition. We calculate the holographic entanglement entropy for two kinds of geometry configurations in a completely back-reacted…
Text-to-image generation is conducted through Generative Adversarial Networks (GANs) or transformer models. However, the current challenge lies in accurately generating images based on textual descriptions, especially in scenarios where the…
We explore holographic entanglement entropy in ten-dimensional supergravity solutions. It has been proposed that entanglement entropy can be computed in such top-down models using minimal surfaces which asymptotically wrap the compact part…
In this article, we review recent progresses on the holographic understandings of the entanglement entropy in the AdS/CFT correspondence. After reviewing the general idea of holographic entanglement entropy, we will explain its applications…
We compute the holographic entanglement entropy in the gravity with higher curvature terms dual to d=4 N=2 SCFTs in F-theory using the method proposed in arXiv:1011.5819. The log term of this entanglement entropy reproduces the A-type…
In the age of big data, the demand for hidden information mining in technological intellectual property is increasing in discrete countries. Definitely, a considerable number of graph learning algorithms for technological intellectual…
Complex-valued signals encode both amplitude and phase, yet most deep models treat attention as real-valued correlation, overlooking interference effects. We introduce the Holographic Transformer, a physics-inspired architecture that…
Progress in the application of machine learning techniques to the prediction of solid-state and molecular materials properties has been greatly facilitated by the development state-of-the-art feature representations and novel deep learning…
In this paper we continue the study of renormalized entanglement entropy introduced in [1]. In particular, we investigate its behavior near an IR fixed point using holographic duality. We develop techniques which, for any static holographic…
Graph neural networks have recently achieved remarkable success in representing graph-structured data, with rapid progress in both the node embedding and graph pooling methods. Yet, they mostly focus on capturing information from the nodes…
The holographic superconductors, as one of the most important application of gauge/gravity duality, promote the study of strongly coupled superconductors via classical general relativity living in one higher dimension. One of the…
We report a GPT-based multi-sentence language model for dialogue generation and document understanding. First, we propose a hierarchical GPT which consists of three blocks, i.e., a sentence encoding block, a sentence generating block, and a…
Recently, knowledge graph embedding, which projects symbolic entities and relations into continuous vector space, has become a new, hot topic in artificial intelligence. This paper addresses a new issue of multiple relation semantics that a…
Word vector representations are central to deep learning natural language processing models. Many forms of these vectors, known as embeddings, exist, including word2vec and GloVe. Embeddings are trained on large corpora and learn the word's…
Processing treatments of alloys, despite being influential to alloy properties, are often neglected in machine-learning aided alloy designs due to the difficulties in expressing this information. We investigated the expressiveness of…
Large language models based on transformers have achieved great empirical successes. However, as they are deployed more widely, there is a growing need to better understand their internal mechanisms in order to make them more reliable.…
We perform a detailed analysis of holographic entanglement R\'enyi entropy in some modified theories of gravity with four dimensional conformal field theory duals. First, we construct perturbative black hole solutions in a recently proposed…
This paper studies interpretable and fair artificial intelligence architectures for understanding English reading. Introduced transformer-based models, integrating advanced attention mechanisms and gradient-based feature attribution. The…
Hypergraph structure learning, which aims to learn the hypergraph structures from the observed signals to capture the intrinsic high-order relationships among the entities, becomes crucial when a hypergraph topology is not readily available…