AI Medical Compendium

Explore the latest research on artificial intelligence and machine learning in medicine.

Showing 251 to 260 of 2841 articles

Clear Filters

Semantic prioritization in visual counterfactual explanations with weighted segmentation and auto-adaptive region selection.

Neural networks : the official journal of the International Neural Network Society
In the domain of non-generative visual counterfactual explanations (CE), traditional techniques frequently involve the substitution of sections within a query image with corresponding sections from distractor images. Such methods have historically ov...

TIMAR: Transition-informed representation for sample-efficient multi-agent reinforcement learning.

Neural networks : the official journal of the International Neural Network Society
In MARL (Multi-Agent Reinforcement Learning), the trial-and-error learning paradigm based on multiple agents requires massive interactions to produce training samples, significantly increasing both the training cost and difficulty. Therefore, enhanci...

DICCR: Double-gated intervention and confounder causal reasoning for vision-language navigation.

Neural networks : the official journal of the International Neural Network Society
Vision-language navigation (VLN) is a challenging task that requires agents to capture the correlation between different modalities from redundant information according to instructions, and then make sequential decisions on visual scenes and text ins...

Synth-CLIP: Synthetic data make CLIP generalize better in data-limited scenarios.

Neural networks : the official journal of the International Neural Network Society
Prompt learning is a powerful technique that enables the transfer of Vision-Language Models (VLMs) like CLIP to downstream tasks. However, when the prompt-based methods are fine-tuned solely on base classes, they often struggle to generalize to novel...

Multi-scale multi-object semi-supervised consistency learning for ultrasound image segmentation.

Neural networks : the official journal of the International Neural Network Society
Manual annotation of ultrasound images relies on expert knowledge and requires significant time and financial resources. Semi-supervised learning (SSL) exploits large amounts of unlabeled data to improve model performance under limited labeled data. ...

MPIC: Exploring alternative approach to standard convolution in deep neural networks.

Neural networks : the official journal of the International Neural Network Society
In the rapidly evolving field of deep learning, Convolutional Neural Networks (CNNs) retain their unique strengths and applicability in processing grid-structured data such as images, despite the surge of Transformer architectures. This paper explore...

DFedGFM: Pursuing global consistency for Decentralized Federated Learning via global flatness and global momentum.

Neural networks : the official journal of the International Neural Network Society
To tackle high communication costs and privacy issues in Centralized Federated Learning (CFL), Decentralized Federated Learning (DFL) is an alternative. However, a significant discrepancy exists between local updates and the expected global update, k...

Fast ramp fraction loss SVM classifier with low computational complexity for pattern classification.

Neural networks : the official journal of the International Neural Network Society
The support vector machine (SVM) is a powerful tool for pattern classification thanks to its outstanding efficiency. However, when encountering extensive classification tasks, the considerable computational complexity may present a substantial barrie...

QTypeMix: Enhancing multi-agent cooperative strategies through heterogeneous and homogeneous value decomposition.

Neural networks : the official journal of the International Neural Network Society
In multi-agent cooperative tasks, the presence of heterogeneous agents is familiar. Compared to cooperation among homogeneous agents, collaboration requires considering the best-suited sub-tasks for each agent. However, the operation of multi-agent s...

H control for fractional order neural networks with uncertainties subject to deception attacks via Improved memory-event-triggered scheme and Its application.

Neural networks : the official journal of the International Neural Network Society
The article discusses an improved memory-event-triggered strategy for H control class of fractional-order neural networks (FONNs) with uncertainties, which are vulnerable to deception attacks. The system under consideration is simultaneously influenc...