Search results for "Computer Science - Artificial Intelligence"

showing 10 items of 82 documents

Unlocking the potential of deep learning for marine ecology: overview, applications, and outlook

2022

The deep learning revolution is touching all scientific disciplines and corners of our lives as a means of harnessing the power of big data. Marine ecology is no exception. These new methods provide analysis of data from sensors, cameras, and acoustic recorders, even in real time, in ways that are reproducible and rapid. Off-the-shelf algorithms can find, count, and classify species from digital images or video and detect cryptic patterns in noisy data. Using these opportunities requires collaboration across ecological and data science disciplines, which can be challenging to initiate. To facilitate these collaborations and promote the use of deep learning towards ecosystem-based management…

FOS: Computer and information sciences0106 biological sciencesArtificial intelligenceComputer Science - Machine LearningEcologyComputer Science - Artificial IntelligenceComputer Vision and Pattern Recognition (cs.CV)010604 marine biology & hydrobiologyComputer Science - Computer Vision and Pattern RecognitionMarine monitoringMarine bioacousticsAquatic ScienceEcosystem-based managementOceanography010603 evolutionary biology01 natural sciencesMachine Learning (cs.LG)VDP::Teknologi: 500Artificial Intelligence (cs.AI)13. Climate actionMachine learning14. Life underwaterEcology Evolution Behavior and Systematics
researchProduct

Finding optimal finite biological sequences over finite alphabets: the OptiFin toolbox

2017

International audience; In this paper, we present a toolbox for a specific optimization problem that frequently arises in bioinformatics or genomics. In this specific optimisation problem, the state space is a set of words of specified length over a finite alphabet. To each word is associated a score. The overall objective is to find the words which have the lowest possible score. This type of general optimization problem is encountered in e.g 3D conformation optimisation for protein structure prediction, or largest core genes subset discovery based on best supported phylogenetic tree for a set of species. In order to solve this problem, we propose a toolbox that can be easily launched usin…

FOS: Computer and information sciences0301 basic medicineTheoretical computer scienceOptimization problemComputer Science - Artificial IntelligenceComputer science[INFO.INFO-SE]Computer Science [cs]/Software Engineering [cs.SE]Quantitative Biology - Quantitative MethodsSet (abstract data type)[INFO.INFO-IU]Computer Science [cs]/Ubiquitous Computing03 medical and health sciences[INFO.INFO-CR]Computer Science [cs]/Cryptography and Security [cs.CR]State spaceMetaheuristicQuantitative Methods (q-bio.QM)Protein structure prediction[INFO.INFO-MO]Computer Science [cs]/Modeling and SimulationToolboxCore (game theory)Artificial Intelligence (cs.AI)030104 developmental biology[INFO.INFO-MA]Computer Science [cs]/Multiagent Systems [cs.MA]FOS: Biological sciences[INFO.INFO-ET]Computer Science [cs]/Emerging Technologies [cs.ET][INFO.INFO-DC]Computer Science [cs]/Distributed Parallel and Cluster Computing [cs.DC]Word (computer architecture)
researchProduct

Selectivity in Probabilistic Causality: Drawing Arrows from Inputs to Stochastic Outputs

2011

Given a set of several inputs into a system (e.g., independent variables characterizing stimuli) and a set of several stochastically non-independent outputs (e.g., random variables describing different aspects of responses), how can one determine, for each of the outputs, which of the inputs it is influenced by? The problem has applications ranging from modeling pairwise comparisons to reconstructing mental processing architectures to conjoint testing. A necessary and sufficient condition for a given pattern of selective influences is provided by the Joint Distribution Criterion, according to which the problem of "what influences what" is equivalent to that of the existence of a joint distr…

FOS: Computer and information sciencesArtificial Intelligence (cs.AI)91E45 (Primary) 60A05 (Secondary)Computer Science - Artificial IntelligencePhysics - Data Analysis Statistics and ProbabilityFOS: Biological sciencesProbability (math.PR)FOS: MathematicsFOS: Physical sciencesQuantitative Biology - Quantitative MethodsMathematics - ProbabilityData Analysis Statistics and Probability (physics.data-an)Quantitative Methods (q-bio.QM)
researchProduct

On Trivalent Logics, Compound Conditionals, and Probabilistic Deduction Theorems

2023

In this paper we recall some results for conditional events, compound conditionals, conditional random quantities, p-consistency, and p-entailment. Then, we show the equivalence between bets on conditionals and conditional bets, by reviewing de Finetti's trivalent analysis of conditionals. But our approach goes beyond de Finetti's early trivalent logical analysis and is based on his later ideas, aiming to take his proposals to a higher level. We examine two recent articles that explore trivalent logics for conditionals and their definitions of logical validity and compare them with our approach to compound conditionals. We prove a Probabilistic Deduction Theorem for conditional events. Afte…

FOS: Computer and information sciencesArtificial Intelligence (cs.AI)Computer Science - Artificial Intelligence
researchProduct

Knowledge Representation on the Web revisited: Tools for Prototype Based Ontologies

2016

In recent years RDF and OWL have become the most common knowledge representation languages in use on the Web, propelled by the recommendation of the W3C. In this paper we present a practical implementation of a different kind of knowledge representation based on Prototypes. In detail, we present a concrete syntax easily and effectively parsable by applications. We also present extensible implementations of a prototype knowledge base, specifically designed for storage of Prototypes. These implementations are written in Java and can be extended by using the implementation as a library. Alternatively, the software can be deployed as such. Further, results of benchmarks for both local and web d…

FOS: Computer and information sciencesArtificial Intelligence (cs.AI)Computer Science - Artificial Intelligence
researchProduct

Leveraging Knowledge Graph Embedding Techniques for Industry 4.0 Use Cases

2018

Industry is evolving towards Industry 4.0, which holds the promise of increased flexibility in manufacturing, better quality and improved productivity. A core actor of this growth is using sensors, which must capture data that can used in unforeseen ways to achieve a performance not achievable without them. However, the complexity of this improved setting is much greater than what is currently used in practice. Hence, it is imperative that the management cannot only be performed by human labor force, but part of that will be done by automated algorithms instead. A natural way to represent the data generated by this large amount of sensors, which are not acting measuring independent variable…

FOS: Computer and information sciencesArtificial Intelligence (cs.AI)Computer Science - Artificial Intelligence
researchProduct

Towards Model-based Reinforcement Learning for Industry-near Environments

2019

Deep reinforcement learning has over the past few years shown great potential in learning near-optimal control in complex simulated environments with little visible information. Rainbow (Q-Learning) and PPO (Policy Optimisation) have shown outstanding performance in a variety of tasks, including Atari 2600, MuJoCo, and Roboschool test suite. While these algorithms are fundamentally different, both suffer from high variance, low sample efficiency, and hyperparameter sensitivity that in practice, make these algorithms a no-go for critical operations in the industry. On the other hand, model-based reinforcement learning focuses on learning the transition dynamics between states in an environme…

FOS: Computer and information sciencesArtificial Intelligence (cs.AI)Computer Science - Artificial Intelligence
researchProduct

FlashRL: A Reinforcement Learning Platform for Flash Games

2017

Reinforcement Learning (RL) is a research area that has blossomed tremendously in recent years and has shown remarkable potential in among others successfully playing computer games. However, there only exists a few game platforms that provide diversity in tasks and state-space needed to advance RL algorithms. The existing platforms offer RL access to Atari- and a few web-based games, but no platform fully expose access to Flash games. This is unfortunate because applying RL to Flash games have potential to push the research of RL algorithms. This paper introduces the Flash Reinforcement Learning platform (FlashRL) which attempts to fill this gap by providing an environment for thousands of…

FOS: Computer and information sciencesArtificial Intelligence (cs.AI)Computer Science - Artificial IntelligenceComputer Science - Computer Science and Game TheoryComputer Science and Game Theory (cs.GT)
researchProduct

Marginalizing in Undirected Graph and Hypergraph Models

2013

Given an undirected graph G or hypergraph X model for a given set of variables V, we introduce two marginalization operators for obtaining the undirected graph GA or hypergraph HA associated with a given subset A c V such that the marginal distribution of A factorizes according to GA or HA, respectively. Finally, we illustrate the method by its application to some practical examples. With them we show that hypergraph models allow defining a finer factorization or performing a more precise conditional independence analysis than undirected graph models.

FOS: Computer and information sciencesArtificial Intelligence (cs.AI)Computer Science - Artificial IntelligenceComputer Science::Discrete Mathematics
researchProduct

Contrastive Transformer: Contrastive Learning Scheme with Transformer innate Patches

2023

This paper presents Contrastive Transformer, a contrastive learning scheme using the Transformer innate patches. Contrastive Transformer enables existing contrastive learning techniques, often used for image classification, to benefit dense downstream prediction tasks such as semantic segmentation. The scheme performs supervised patch-level contrastive learning, selecting the patches based on the ground truth mask, subsequently used for hard-negative and hard-positive sampling. The scheme applies to all vision-transformer architectures, is easy to implement, and introduces minimal additional memory footprint. Additionally, the scheme removes the need for huge batch sizes, as each patch is t…

FOS: Computer and information sciencesArtificial Intelligence (cs.AI)Computer Science - Artificial IntelligenceComputer Vision and Pattern Recognition (cs.CV)Computer Science - Computer Vision and Pattern Recognition
researchProduct