The neuroconnectionist research programme

Nature reviews. Neuroscience, Journal Year: 2023, Volume and Issue: 24(7), P. 431 - 450

Published: May 30, 2023

Language: Английский

---

Smart waste management: A paradigm shift enabled by artificial intelligence

Waste Management Bulletin, Journal Year: 2024, Volume and Issue: 2(2), P. 244 - 263

Published: May 9, 2024

Waste management poses a pressing global challenge, necessitating innovative solutions for resource optimization and sustainability. Traditional practices often prove insufficient in addressing the escalating volume of waste its environmental impact. However, advent Artificial Intelligence (AI) technologies offers promising avenues tackling complexities systems. This review provides comprehensive examination AI's role management, encompassing collection, sorting, recycling, monitoring. It delineates potential benefits challenges associated with each application while emphasizing imperative improved data quality, privacy measures, cost-effectiveness, ethical considerations. Furthermore, future prospects AI integration Internet Things (IoT), advancements machine learning, importance collaborative frameworks policy initiatives were discussed. In conclusion, holds significant promise enhancing practices, such as concerns, cost implications is paramount. Through concerted efforts ongoing research endeavors, transformative can be fully harnessed to drive sustainable efficient practices.

Language: Английский

---

A new approach to neural network via double hierarchy linguistic information: Application in robot selection

Engineering Applications of Artificial Intelligence, Journal Year: 2023, Volume and Issue: 129, P. 107581 - 107581

Published: Dec. 12, 2023

Language: Английский

---

Obstacle Avoidance and Path Planning Methods for Autonomous Navigation of Mobile Robot

Sensors, Journal Year: 2024, Volume and Issue: 24(11), P. 3573 - 3573

Published: June 1, 2024

Path planning creates the shortest path from source to destination based on sensory information obtained environment. Within planning, obstacle avoidance is a crucial task in robotics, as autonomous operation of robots needs reach their without collisions. Obstacle algorithms play key role robotics and vehicles. These enable navigate environment efficiently, minimizing risk collisions safely avoiding obstacles. This article provides an overview algorithms, including classic techniques such Bug algorithm Dijkstra’s algorithm, newer developments like genetic approaches neural networks. It analyzes detail advantages, limitations, application areas these highlights current research directions robotics. aims provide comprehensive insight into state prospects applications. also mentions use predictive methods deep learning strategies.

Language: Английский

---

From Neural Networks to Emotional Networks: A Systematic Review of EEG-Based Emotion Recognition in Cognitive Neuroscience and Real-World Applications

Brain Sciences, Journal Year: 2025, Volume and Issue: 15(3), P. 220 - 220

Published: Feb. 20, 2025

Background/Objectives: This systematic review presents how neural and emotional networks are integrated into EEG-based emotion recognition, bridging the gap between cognitive neuroscience practical applications. Methods: Following PRISMA, 64 studies were reviewed that outlined latest feature extraction classification developments using deep learning models such as CNNs RNNs. Results: Indeed, findings showed multimodal approaches practical, especially combinations involving EEG with physiological signals, thus improving accuracy of classification, even surpassing 90% in some studies. Key signal processing techniques used during this process include spectral features, connectivity analysis, frontal asymmetry detection, which helped enhance performance recognition. Despite these advances, challenges remain more significant real-time processing, where a trade-off computational efficiency limits implementation. High cost is prohibitive to use real-world applications, therefore indicating need for development application optimization techniques. Aside from this, obstacles inconsistency labeling emotions, variation experimental protocols, non-standardized datasets regarding generalizability recognition systems. Discussion: These developing adaptive, algorithms, integrating other inputs like facial expressions sensors, standardized protocols elicitation classification. Further, related ethical issues respect privacy, data security, machine model biases be much proclaimed responsibly apply research on emotions areas healthcare, human–computer interaction, marketing. Conclusions: provides critical insight suggestions further field toward robust, scalable, applications by consolidating current methodologies identifying their key limitations.

Language: Английский

---

What can 1.8 billion regressions tell us about the pressures shaping high-level visual representation in brains and machines?

bioRxiv (Cold Spring Harbor Laboratory), Journal Year: 2022, Volume and Issue: unknown

Published: March 29, 2022

Abstract The rapid development and open-source release of highly performant computer vision models offers new potential for examining how different inductive biases impact representation learning emergent alignment with the high-level human ventral visual system. Here, we assess a diverse set 224 models, curated to enable controlled comparison model properties, testing their brain predictivity using large-scale functional magnetic resonance imaging data. We find that qualitatively architectures (e.g. CNNs versus Transformers) markedly task objectives purely contrastive vision-language alignment) achieve near equivalent degrees predictivity, when other factors are held constant. Instead, variation across training diets yields largest, most consistent effect on predictivity. Overarching properties commonly suspected increase greater effective dimensionality; learnable parameter count) were not robust indicators this more extensive survey. highlight standard model-to-brain linear re-weighting methods may be too flexible, as have very similar brain-predictivity scores, despite significant in underlying representations. Broadly, our findings point importance diet, challenge common assumptions about used link brains, concretely outline future directions leveraging full diversity existing tools probe computational principles biological artificial systems.

Language: Английский

---

Deep Learning and Neural Networks: Decision-Making Implications

Symmetry, Journal Year: 2023, Volume and Issue: 15(9), P. 1723 - 1723

Published: Sept. 8, 2023

Deep learning techniques have found applications across diverse fields, enhancing the efficiency and effectiveness of decision-making processes. The integration these underscores significance interdisciplinary research. In particular, decisions often rely on output’s projected value or probability from neural networks, considering different values relevant output factor. This review examines impact deep systems, analyzing 25 papers published between 2017 2022. highlights improved accuracy but emphasizes need for addressing issues like interpretability, generalizability, to build reliable decision support systems. Future research directions include transparency, explainability, real-world validation, underscoring importance collaboration successful implementation.

Language: Английский

---

Gradients of Brain Organization: Smooth Sailing from Methods Development to User Community

Neuroinformatics, Journal Year: 2024, Volume and Issue: unknown

Published: April 3, 2024

Language: Английский

---

Artificial Intelligence-Based Algorithms in Medical Image Scan Segmentation and Intelligent Visual Content Generation—A Concise Overview

Electronics, Journal Year: 2024, Volume and Issue: 13(4), P. 746 - 746

Published: Feb. 13, 2024

Recently, artificial intelligence (AI)-based algorithms have revolutionized the medical image segmentation processes. Thus, precise of organs and their lesions may contribute to an efficient diagnostics process a more effective selection targeted therapies, as well increasing effectiveness training process. In this context, AI automatization scan increase quality resulting 3D objects, which lead generation realistic virtual objects. paper, we focus on AI-based solutions applied in intelligent visual content generation, i.e., computer-generated three-dimensional (3D) images context extended reality (XR). We consider different types neural networks used with special emphasis learning rules applied, taking into account algorithm accuracy performance, open data availability. This paper attempts summarize current development methods imaging that are XR. It concludes possible developments challenges applications reality-based solutions. Finally, future lines research directions applications, both solutions, discussed.

Language: Английский

---

The Physical Signature of Computation

Oxford University Press eBooks, Journal Year: 2024, Volume and Issue: unknown

Published: April 30, 2024

Abstract This book articulates and defends the robust mapping account—the most systematic, rigorous, comprehensive account of computational implementation to date. Drawing in part from recent results physical information theory, it argues that accounts can be made adequate by incorporating appropriate constraints. According account, key constraint on mappings states—the for establishing a computation is physically implemented—is physical-computational equivalence: evolving states bear neither more nor less about than do they map onto. When this highly nontrivial satisfied, among others are spelled out as system said implement sense, which means bears signature computation. The applies important questions foundations cognitive science, including alleged indeterminacy computation, pancomputationalism, theory mind. It shows determinate, versions pancomputationalism fail, cognition involves only insofar neurocognitive systems specific computations. also both consciousness physics outstrip

Language: Английский

---