23 papers · ranked by Valyu relevance
Zheng Gao, Ting Jiang, Mingming Zhang, Hao Wu + 1 more
We propose and validate a novel optical semantic transmission scheme using multimode fiber (MMF). By leveraging the frequency sensitivity of intermodal dispersion in MMFs, we achieve high-dimensional semantic encoding and decoding in the frequency domain. Our system maps symbols to 128 distinct frequencies spaced at…
Melissa Franch, Elizabeth A. Mickiewicz, James L. Belanger, Brad Joiner + 12 more
As we listen to speech, our brains track the meanings of the words we hear. Recent successes of large language models suggest that distributed population geometry can capture rich semantic relationships between words. Motivated by this idea, we hypothesized that semantic information in the brain may likewise be…
Zijian Liang, Kai Niu, Jin Xu, Ping Zhang + 1 more
Recent semantic communication methods explore effective ways to expand the communication paradigm and improve the performance of communication systems. Nonetheless, a common problem with these methods is that the essence of semantics is not explicitly pointed out and directly utilized. A new epistemology suggests that…
Melissa Franch, Elizabeth A. Mickiewicz, James L. Belanger, Assia Chericoni + 10 more
As we listen to speech, our brains actively compute the meaning of individual words. Inspired by the success of large language models (LLMs), we hypothesized that the brain employs vectorial coding principles, such that meaning is reflected in distributed activity of single neurons. We recorded responses of hundreds of…
Jona Sassenhagen, Christian J. Fiebach
How is semantic information stored in the human mind and brain? Some philosophers and cognitive scientists argue for vectorial representations of concepts, where the meaning of a word is represented as its position in a high-dimensional neural state space. At the intersection of natural language processing and…
Hai-Long Qin, Jincheng Dai, Sixian Wang, Xiaoqi Qin + 4 more
'Kai Niu' 'Wenjun Xu' 'Ping Zhang'] Abstract—Semantic communication, leveraging advanced deep learning techniques, emerges as a new paradigm that meets the requirements of next-generation wireless networks. However, current semantic communication systems, which employ neural coding for feature extraction from raw data…
Yong Xiao, Yiwei Liao, Yingyu Li, Guangming Shi + 4 more
'Walid Saad' 'Mérouane Debbah' 'Mehdi Bennis'] Abstract—Semantic-aware communication is a novel paradigm that draws inspiration from human communication focusing on the delivery of the meaning of messages. It has attracted significant interest recently due to its potential to improve the efficiency and reliability of…
Zhijin Qin, Xiaoming Tao, Jianhua Lu, Geoffrey Ye Li
Semantic communication, regarded as the breakthrough beyond the Shannon paradigm, aims at the successful transmission of semantic information conveyed by the source rather than the accurate reception of each single symbol or bit regardless of its meaning. This article provides an overview on semantic communications.…
Henry David Soldan, Carina Zoellner, Nora Alicia Herweg, Nurten Genc + 2 more
Episodic memory does not perfectly reproduce past experiences but combines encoded episode-specific information and semantic knowledge in a constructive way. Previous research has shown that semantic category knowledge can bias location memory for individual items, suggesting that similar mechanisms may affect other…
Jinke Ren, Zezhong Zhang, Jie Xu, Guanying Chen + 3 more
'Ping Zhang' 'Shuguang Cui'] Abstract—Semantic communication is widely touted as a key technology for propelling the sixth-generation (6G) wireless networks. However, providing effective semantic representation is quite challenging in practice. To address this issue, this article takes a crack at exploiting semantic…
Shengteng Jiang, Yueling Liu, Yichi Zhang, Peng Luo + 8 more
'Jun Xiong' 'Haitao Zhao' 'Jibo Wei' 'Onur Günlü' 'Rafael F. Schaefer' 'Holger Boche' 'H. Vincent Poor'] Semantic communication is a promising technology used to overcome the challenges of large bandwidth and power requirements caused by the data explosion. Semantic representation is an important issue in semantic…
Seonjung Kim, Yongjeong Oh, Yongjune Kim, Namyoon Lee + 1 more
—Semantic communication is an emerging paradigm that prioritizes transmitting task-relevant information over accurately delivering raw data bits. In this paper, we address an unequal error protection (UEP) problem in digital semantic communication, where bits of higher semantic importance require stronger protection.…
Heng Sun, Jian Weng, Guangchuang Yu, Richard H. Massawe + 1 more
'Guy J-P. Schumann'] Semantic technology plays a key role in various domains, from conversation understanding to algorithm analysis. As the most efficient semantic tool, ontology can represent, process and manage the widespread knowledge. Nowadays, many researchers use ontology to collect and organize data's semantic…
Zhanyu Yu, Yue Ma, Lijuan Wang
The sememe heredity of action semantics may be affected by the related association of a verb or noun in an action phrase and the related association between one action phrase and another. The motor encoding theory and the five-component view of the subject-performed task supported by the verb’s specificity highly…
Tagir Akhmetshin, Arkadii Lin, Timur Madzhidov, Alexandre Varnek
Autoencoders represent a promising technique for the inverse quantitative structure-activity relationship (QSAR) task. However, undesirable bias, such as atom ordering, affects the neighbourhood behaviour of autoencoders’ latent space and, consequently, usage of the latent vectors as variables in machine-learning…
Rachana Niranjan Murthy, Sai Teja Potu, Akhil Thomas, Lokesh Mishra + 2 more
Retrieving structured materials information from unstructured textual data is essential for data mining and automatically developing comprehensive ontologies. Information extraction is a complex task composed of multiple subtasks and thus often relies on systems of task-specialized language models. A foundation…
Authors not listed
Deep generative models are transforming early-stage drug discovery, yet most current approaches are not well suited for realistic, small-data settings and often rely on simplified molecular representations such as linear strings, overlooking the inherent graph-based structure of molecules. To address this, we first…
Miloje Rakočević
In some previous works (2018a,b; 2019, 2021a,b, 2022) we presented a new type of mirror symmetry, expressed in the set of protein amino acids; such a symmetry, that it simultaneously represents the semiotic essence of the genetic code. In this paper we provide new evidences that the genetic code represents the unity of…
Julia Steinberg, Haim Sompolinsky
A long standing challenge in biological and artificial intelligence is to understand how new knowledge can be constructed from known building blocks in a way that is amenable for computation by neuronal circuits. Here we focus on the task of storage and recall of structured knowledge in long-term memory. Specifically…
Zachary Humphreys, Xenophon Evangelopoulos, Stavros Gerolymatos, Edward O. Pyzer-Knapp + 1 more
Graph neural networks have recently met huge success in various inference tasks including materials property prediction amongst many others. Nevertheless, having an inherently locally-based representation capacity as they do, global representation of materials' structures can only only be achieved by expanding the…
Sanjar Adilov
Generative neural networks have shown promising results in de novo drug design. Recent studies suggest that one of the efficient ways to produce novel molecules matching target properties is to model SMILES sequences using deep learning in a way similar to language modeling in natural language processing. In this…
Jan Weinreich, Daniel Probst
In recent years, natural language processing approaches to machine learning, most prominently deep neural network-based transformers, have been extensively applied to molecular classification and regression tasks, including the prediction of pharmacokinetic and quantum-chemical properties. However, models based on deep…
Authors not listed
Compound similarity is fundamental to various cheminformatics analyses, particularly in the drug discovery industry, where the structure-activity principle is central to medicinal chemistry. Historically, binary fingerprints combined with Tanimoto and “Tanimoto-related metrics” (such as Dice, Sørensen–Dice, and…