Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- research-articleOctober 2024
Multi-objective context-guided consensus of a massive array of techniques for the inference of Gene Regulatory Networks
Computers in Biology and Medicine (CBIM), Volume 179, Issue Chttps://doi.org/10.1016/j.compbiomed.2024.108850Abstract Background and Objective:Gene Regulatory Network (GRN) inference is a fundamental task in biology and medicine, as it enables a deeper understanding of the intricate mechanisms of gene expression present in organisms. This bioinformatics problem ...
Highlights- MO-GENECI optimizes GRN inference with a multi-objective evolutionary algorithm.
- MO-GENECI enhances inference by injecting relevant biological context information.
- Tested on 106 GRNs, MO-GENECI consistently outperforms individual ...
- ArticleAugust 2024
Strategic Reparameterization for Enhanced Inference in Imperfect Information Games: A Neural Network Approach
Advanced Intelligent Computing Technology and ApplicationsPages 162–173https://doi.org/10.1007/978-981-97-5591-2_14AbstractHow to infer useful information for making decisions is one of the core problems in imperfect information games. This paper tackles the problem by proposing a reparameterization technique to improve inference in imperfect information games. It ...
- short-paperJuly 2024
Preliminary Results of the MLPerf BERT Inference Benchmark on AMD Instinct GPUs
- Zixian Wang,
- Khai Vu,
- Miro Hodak,
- Aarush Mehrotra,
- Francisco Gutierrez,
- Kyle Smith,
- Gloria Seo,
- Austin Garcia,
- Bryan Chin,
- Marty Kandes,
- Mary P Thomas
PEARC '24: Practice and Experience in Advanced Research Computing 2024: Human Powered ComputingArticle No.: 59, Pages 1–5https://doi.org/10.1145/3626203.3670589In recent years, Artificial Intelligence (AI) has reshaped various facets of our day-to-day lives. To evaluate both hardware and software deployment of Machine Learning (ML) applications, it is necessary to measure system-wide performance and accuracy. ...
- research-articleJuly 2024
Infer-HiRes: Accelerating Inference for High-Resolution Images with Quantization and Distributed Deep Learning
PEARC '24: Practice and Experience in Advanced Research Computing 2024: Human Powered ComputingArticle No.: 5, Pages 1–9https://doi.org/10.1145/3626203.3670548High-Resolution Images are being used in various applications, including Medical Imaging, Satellite Imagery, and Surveillance. Due to the evolution of Deep Learning (DL) and its widespread usage, it has also become a prominent choice for high-resolution ...
- research-articleJune 2024
Bias-reduced and variance-corrected asymptotic Gaussian inference about extreme expectiles
AbstractThe expectile is a prime candidate for being a standard risk measure in actuarial and financial contexts, for its ability to recover information about probabilities and typical behavior of extreme values, as well as its excellent axiomatic ...
-
- research-articleJune 2024
The maximal coordination principle in regulatory Boolean networks
Journal of Computer and System Sciences (JCSS), Volume 142, Issue Chttps://doi.org/10.1016/j.jcss.2024.103518AbstractWe introduce a coordination index in regulatory Boolean networks and we expose the maximal coordination principle (MCP), according to which a cohesive society reaches the dynamics characterized by the highest coordination index. Based on simple ...
- research-articleApril 2024
The Importance of Workload Choice in Evaluating LLM Inference Systems
EuroMLSys '24: Proceedings of the 4th Workshop on Machine Learning and SystemsPages 39–46https://doi.org/10.1145/3642970.3655823The success of Large Language Models (LLMs) across a wide range of applications and use cases has created the need for faster and more scalable systems for LLM inference. These systems speed up LLM inference by optimizing scheduling decisions or ...
- research-articleApril 2024
A Benchmark for ML Inference Latency on Mobile Devices
EdgeSys '24: Proceedings of the 7th International Workshop on Edge Systems, Analytics and NetworkingPages 31–36https://doi.org/10.1145/3642968.3654818Inference latency prediction on mobile devices is essential for multiple applications, including collaborative inference and neural architecture search. Training accurate latency predictors using ML techniques requires sufficient and representative data; ...
- research-articleJuly 2024
A novel intelligent model for visualized inference of medical diagnosis: A case of TCM
Artificial Intelligence in Medicine (AIIM), Volume 149, Issue Chttps://doi.org/10.1016/j.artmed.2024.102799AbstractHow to present an intelligent model based on known diagnostic knowledge to assist medical diagnosis and display the reasoning process is an interesting issue worth exploring. This study developed a novel intelligent model for visualized inference ...
Highlights- Developing a novel intelligent model that can show the inference process of medical diagnosis with visualized digraphs.
- Developing a novel method to train model with known and priori knowledge instead of clinical samples (cases).
- ...
- review-articleApril 2024
A critical review of common pitfalls and guidelines to effectively infer parameters of agent-based models using Approximate Bayesian Computation
Environmental Modelling & Software (ENMS), Volume 172, Issue Chttps://doi.org/10.1016/j.envsoft.2023.105905AbstractThe agent-based modelling paradigm often results in complex, highly detailed models, containing unknown or uncertain parameters. Approximate Bayesian Computation (ABC) offers a simulation-based approach for inferring these parameters from ...
Highlights- We review the application of ABC for estimating parameters of agent-based models.
- We find that necessary validation methods are applied too infrequently.
- Our remarks are illustrated by simulations with a benchmark model in ...
- ArticleDecember 2023
A Knowledge Rich Task Planning Framework for Human-Robot Collaboration
AbstractIn this paper, we position ourselves within the context of collaborative planning. Drawing upon our recent research, we introduce a novel, knowledge rich task planning framework that represents and reasons and effectively addresses agents’ first-...
- ArticleFebruary 2024
Can We Infer Move Sequences in Go from Stone Arrangements?
AbstractInference commonly happens in our daily lives and is also a hot topic for AI research. In this paper, we infer move sequences in Go, i.e., the order in which moves are played, from stone arrangements on the board. We formulate the problem as ...
- research-articleNovember 2023
Capturing the Varieties of Natural Language Inference: A Systematic Survey of Existing Datasets and Two Novel Benchmarks
Journal of Logic, Language and Information (KLU-JLLI), Volume 33, Issue 1Pages 21–48https://doi.org/10.1007/s10849-023-09410-4AbstractTransformer-based Pre-Trained Language Models currently dominate the field of Natural Language Inference (NLI). We first survey existing NLI datasets, and we systematize them according to the different kinds of logical inferences that are being ...
- ArticleNovember 2023
Inference in Probabilistic Answer Set Programming Under the Credal Semantics
AIxIA 2023 – Advances in Artificial IntelligencePages 367–380https://doi.org/10.1007/978-3-031-47546-7_25AbstractProbabilistic Answer Set Programming under the credal semantics (PASP) describes an uncertain domain through an answer set program extended with probabilistic facts. The PASTA language leverages PASP to express statistical statements. A solver ...
- ArticleOctober 2023
An Inferential Theory of Causal Reasoning
AbstractWe present a general formalism of causal reasoning that encompasses both Pearl’s approach to causality and a number of key systems of nonmonotonic reasoning in artificial intelligence.
- research-articleOctober 2023
Alignment and stability of embeddings: Measurement and inference improvement
AbstractRepresentation learning (RL) methods learn objects’ latent embeddings where information is preserved by distance. Since certain distance functions are invariant to certain linear transformations, one may obtain different embeddings while ...
- abstractOctober 2023
Reasoning and inference for (Maximum) satisfiability: new insights
AbstractAt the heart of computer science and artificial intelligence, logic is often used as a powerful language to model and solve complex problems that arise in academia and in real-world applications. A well-known formalism in this context is the ...
- research-articleSeptember 2023
Learning, inference, and prediction on probability density functions with constrained Gaussian processes
Information Sciences: an International Journal (ISCI), Volume 642, Issue Chttps://doi.org/10.1016/j.ins.2023.119068AbstractProbability density functions (PDFs) play an important role in machine learning, statistics, and in many real-world applications. In this paper, we introduce a new framework to learn, infer and predict nonparametric PDFs with a ...
- research-articleSeptember 2023
Interval-based reasoning over continuous variables using independent component analysis and Bayesian networks
International Journal of Approximate Reasoning (IJAR), Volume 160, Issue Chttps://doi.org/10.1016/j.ijar.2023.108970AbstractBayesian networks (BNs) can be used for probabilistic reasoning over discrete variables. Their extension to the continuous domain, however, remains an open research issue. In this work, we address the Bayesian inference problem for ...
- ArticleSeptember 2024
Benchmarking Large Language Models: Opportunities and Challenges
AbstractWith exponentially growing popularity of Large Language Models (LLMs) and LLM-based applications like ChatGPT and Bard, the Artificial Intelligence (AI) community of developers and users are in need of representative benchmarks to enable careful ...