21 papers · ranked by Valyu relevance
Tarek R. Besold, Artur S. d’Avila Garcez, Sebastian Bader, Howard Bowman + 10 more
'Howard Bowman' 'Pedro Domingos' 'Pascal Hitzler' 'Kai-Uwe Küehnberger' 'Luís C. Lamb' 'Daniel Lowd' 'Priscila Machado Vieira Lima' 'Leo de Penning' 'Gadi Pinkas' 'Hoifung Poon' 'Gerson Zaverucha'] | Tarek R. Besold | tarek-r.besold@city.ac.uk | | --- | --- | | Department of Computer Science, City, University of London…
Pascal Hitzler, Aaron Eberhart, Monireh Ebrahimi, Md Kamruzzaman Sarker + 1 more
'Md Kamruzzaman Sarker' 'Lu Zhou'] Neuro-symbolic artificial intelligence refers to a field of research and applications that combines machine learning methods based on artificial neural networks, such as deep learning, with symbolic approaches to computing and artificial intelligence (AI), as can be found for example…
Artur S. d’Avila Garcez, Marco Gori, Luís C. Lamb, Luciano Serafini + 2 more
'Michael Spranger' 'Son N. Tran'] Current advances in Artificial Intelligence and machine learning in general, and deep learning in particular have reached unprecedented impact not only across research communities, but also over popular media channels. However, concerns about interpretability and accountability of AI…
Nuri Cingillioglu, Alessandra Russo
Humans have the ability to seamlessly combine low-level visual input with high-level symbolic reasoning often in the form of recognising objects, learning relations between them and applying rules. Neurosymbolic systems aim to bring a unifying approach to connectionist and logic-based principles for visual processing…
Md Kamruzzaman Sarker, Lu Zhou, Aaron Eberhart, Pascal Hitzler
Neuro-Symbolic Artificial Intelligence – the combination of symbolic methods with methods that are based on artificial neural networks – has a long-standing history. In this article, we provide a structured overview of current trends, by means of categorizing recent publications from key conferences. The article is…
Authors not listed
The exponentially growing body of scientific literature has made manual synthesis and hypothesis generation increasingly impractical, introducing an essential bottleneck in the scientific discovery pipeline. While large language models (LLMs) have unprecedented capability to process and summarize textual knowledge…
Hugo Latapie, Ozkan Kilic, Kristinn R. Thórisson, Pei Wang + 1 more
'Patrick Hammer'] A cognitive architecture aimed at cumulative learning must provide the necessary information and control structures to allow agents to learn incrementally and autonomously from their experience. This involves managing an agent's goals as well as continuously relating sensory information to these in…
Alvaro Velasquez, Neel Bhatt, Ufuk Topcu, Zhangyang Wang + 5 more
'Katia Sycara' 'Simon Stepputtis' 'Sandeep Neema' 'Gautam Vallabha' 'Derek Abbott'] Title: Abstract The recent progress in machine learning has shifted the trends in artificial intelligence (AI) toward an overreliance on increasing amounts of data, computing power, and model parameters. These trends have resulted in…
Artur S. d’Avila Garcez, Luís C. Lamb
Current advances in Artificial Intelligence (AI) and Machine Learning (ML) have achieved unprecedented impact across research communities and industry. Nevertheless, concerns about trust, safety, interpretability and accountability of AI were raised by influential thinkers. Many have identified the need for…
Kenneth J. Hayworth, Adam H. Marblestone
The thalamus appears to be involved in the flexible routing of information among cortical areas, yet the computational implications of such routing are only beginning to be explored. Here we create a connectionist model of how selectively gated cortico-thalamo-cortical relays could underpin both symbolic and…
Garrett E. Katz, Akshay, Gregory P. Davis, Rodolphe J. Gentili + 1 more
'James A. Reggia'] We present a neurocomputational controller for robotic manipulation based on the recently developed “neural virtual machine” (NVM). The NVM is a purely neural recurrent architecture that emulates a Turing-complete, purely symbolic virtual machine. We program the NVM with a symbolic algorithm that…
Anthony Strock, Ruizhe Liu, Rishab Iyer, Percy K. Mistry + 1 more
The mapping between nonsymbolic quantities and symbolic numbers lays the foundation for mathematical development in children. However, the neural mechanisms underlying this crucial cognitive bridge remain unclear. Here, we investigate the computational principles governing symbolic-nonsymbolic integration using a…
Ceca Kraišniković, Wolfgang Maass, Robert Legenstein
The brain uses recurrent spiking neural networks for higher cognitive functions such as symbolic computations, in particular, mathematical computations. We review the current state of research on spike-based symbolic computations of this type. In addition, we present new results which show that surprisingly small…
Authors not listed
The modeling of chemical reactions using artificial intelligence is rapidly advancing but still heavily relies on abundant and costly experimental data. In the context of computational chemistry, we present SymChemAI, a chemically informed neural network capable of simulating the dynamic evolution of reactions from…
Lucas Y. Tian, Kedar U. Garzón Gupta, Daniel J. Hanuska, Adam G. Rouse + 5 more
A hallmark of intelligence is proficiency in solving new problems, including those that differ dramatically from problems seen before. Problem-solving, in turn, depends on goal-directed generation of novel ideas and behaviors^1^, which has been proposed to rely on internal representations of discrete units, or symbols…
Wandemberg Gibaut, Leonardo Pereira, Fabio Grassiotto, Alexandre Osorio + 4 more
'Alexandre Osorio' 'Eder Gadioli' 'Amparo Munõz' 'Sildolfo Gomes' 'Claudio dos Santos'] Neurosymbolic AI deals with models that combine symbolic processing, like classic AI, and neural networks, as it's a very established area. These models are emerging as an effort toward Artificial General Intelligence (AGI) by both…
Gabriele Di Antonio, Sofia Raglio, Maurizio Mattia
A general mathematical description of the way the brain encodes ordinal knowledge of sequences is still lacking. Coherently with the well-established idea of mixed selectivity in high-dimensional state spaces, we conjectured the existence of a linear solution for serial learning tasks. In this theoretical framework…
Lucas Y. Tian, Kedar U. Garzón, Adam G. Rouse, Mark A. G. Eldridge + 4 more
At the core of intelligence is proficiency in solving new problems, including those that differ dramatically from problems seen before. Problem-solving, in turn, depends on goal-directed generation of novel thoughts and behaviors^1^, which has been proposed to rely on internal representations of discrete units, or…
Authors not listed
Step-by-step thinking is essential in all domains of chemical sciences and engineering. While machine learning tools are broadly used, algorithms that automate reasoning are far less common. We elaborate on seven categories of human reasoning activities and connect each to applications in chemical science and…
Authors not listed
Real-world datasets in chemical engineering and bioengineering processes--such as those from catalytic reactors, multiphase flows, polymerization reactors, bioreactors, and clinical trials--can often be unlabelled or disorganized, rendering the training of existing supervised learning models ineffective at learning the…
Nathan Frey, Ryan Soklaski, Simon Axelrod, Siddharth Samsi + 3 more
Massive scale, both in terms of data availability and computation, enables significant breakthroughs in key application areas of deep learning such as natural language processing (NLP) and computer vision. There is emerging evidence that scale may be a key ingredient in scientific deep learning, but the importance of…