Link Prediction of Artificial Intelligence Concepts using Low
Computational Power
- URL: http://arxiv.org/abs/2202.03393v1
- Date: Mon, 7 Feb 2022 18:32:02 GMT
- Title: Link Prediction of Artificial Intelligence Concepts using Low
Computational Power
- Authors: Francisco Valente
- Abstract summary: The main goal of this paper was to predict the likelihood of future associations between machine learning concepts in a semantic network.
The developed methodology corresponds to a solution for a scenario of availability of low computational power only.
The reasons that motivated the developed methodologies will be discussed, as well as some results, limitations and suggestions of improvements.
- Score: 0.0
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: This paper presents an approach proposed for the Science4cast 2021
competition, organized by the Institute of Advanced Research in Artificial
Intelligence, whose main goal was to predict the likelihood of future
associations between machine learning concepts in a semantic network. The
developed methodology corresponds to a solution for a scenario of availability
of low computational power only, exploiting the extraction of low order
topological features and its incorporation in an optimized classifier to
estimate the degree of future connections between the nodes. The reasons that
motivated the developed methodologies will be discussed, as well as some
results, limitations and suggestions of improvements.
Related papers
- Uncertainty Estimation in Multi-Agent Distributed Learning for AI-Enabled Edge Devices [0.0]
Edge IoT devices have seen a paradigm shift with the introduction of FPGAs and AI accelerators.
This advancement has vastly amplified their computational capabilities, emphasizing the practicality of edge AI.
Our study explores methods that enable distributed data processing through AI-enabled edge devices, enhancing collaborative learning capabilities.
arXiv Detail & Related papers (2024-03-14T07:40:32Z) - Coherent Entity Disambiguation via Modeling Topic and Categorical
Dependency [87.16283281290053]
Previous entity disambiguation (ED) methods adopt a discriminative paradigm, where prediction is made based on matching scores between mention context and candidate entities.
We propose CoherentED, an ED system equipped with novel designs aimed at enhancing the coherence of entity predictions.
We achieve new state-of-the-art results on popular ED benchmarks, with an average improvement of 1.3 F1 points.
arXiv Detail & Related papers (2023-11-06T16:40:13Z) - Towards a Better Theoretical Understanding of Independent Subnetwork Training [56.24689348875711]
We take a closer theoretical look at Independent Subnetwork Training (IST)
IST is a recently proposed and highly effective technique for solving the aforementioned problems.
We identify fundamental differences between IST and alternative approaches, such as distributed methods with compressed communication.
arXiv Detail & Related papers (2023-06-28T18:14:22Z) - Large-Scale Sequential Learning for Recommender and Engineering Systems [91.3755431537592]
In this thesis, we focus on the design of an automatic algorithms that provide personalized ranking by adapting to the current conditions.
For the former, we propose novel algorithm called SAROS that take into account both kinds of feedback for learning over the sequence of interactions.
The proposed idea of taking into account the neighbour lines shows statistically significant results in comparison with the initial approach for faults detection in power grid.
arXiv Detail & Related papers (2022-05-13T21:09:41Z) - A Multi-criteria Approach to Evolve Sparse Neural Architectures for
Stock Market Forecasting [0.0]
This study proposes a new framework to evolve efficacious yet parsimonious neural architectures for the movement prediction of stock market indices.
A new search paradigm, Two-Dimensional Swarms (2DS) is proposed for the multi-criteria neural architecture search.
The results of this study convincingly demonstrate that the proposed approach can evolve parsimonious networks with better generalization capabilities.
arXiv Detail & Related papers (2021-11-15T19:44:10Z) - Artificial Intelligence Algorithms for Natural Language Processing and
the Semantic Web Ontology Learning [0.76146285961466]
A new evolutionary clustering algorithm star (ECA*) is proposed.
Experiments were conducted to evaluate ECA* against five state-of-the-art approaches.
The results indicate that ECA* overcomes its competitive techniques in terms of the ability to find the right clusters.
arXiv Detail & Related papers (2021-08-31T11:57:41Z) - Interpretable Social Anchors for Human Trajectory Forecasting in Crowds [84.20437268671733]
We propose a neural network-based system to predict human trajectory in crowds.
We learn interpretable rule-based intents, and then utilise the expressibility of neural networks to model scene-specific residual.
Our architecture is tested on the interaction-centric benchmark TrajNet++.
arXiv Detail & Related papers (2021-05-07T09:22:34Z) - GANTL: Towards Practical and Real-Time Topology Optimization with
Conditional GANs and Transfer Learning [0.0]
We present a deep learning method based on generative adversarial networks for generative design exploration.
The proposed method combines the generative power of conditional GANs with the knowledge transfer capabilities of transfer learning methods to predict optimal topologies for unseen boundary conditions.
arXiv Detail & Related papers (2021-05-07T03:13:32Z) - A Diagnostic Study of Explainability Techniques for Text Classification [52.879658637466605]
We develop a list of diagnostic properties for evaluating existing explainability techniques.
We compare the saliency scores assigned by the explainability techniques with human annotations of salient input regions to find relations between a model's performance and the agreement of its rationales with human ones.
arXiv Detail & Related papers (2020-09-25T12:01:53Z) - On Computability, Learnability and Extractability of Finite State
Machines from Recurrent Neural Networks [0.0]
This work aims at shedding some light on connections between finite state machines (FSMs), and recurrent neural networks (RNNs)
Examined connections in this master's thesis is threefold: the extractability of finite state machines from recurrent neural networks, learnability aspects and computationnal links.
arXiv Detail & Related papers (2020-09-10T15:55:30Z) - Decentralized MCTS via Learned Teammate Models [89.24858306636816]
We present a trainable online decentralized planning algorithm based on decentralized Monte Carlo Tree Search.
We show that deep learning and convolutional neural networks can be employed to produce accurate policy approximators.
arXiv Detail & Related papers (2020-03-19T13:10:20Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.