Deep learning and cognitive science

Perconti, Pietro; Plebe, Alessio

doi:10.1016/j.cognition.2020.104365

Cited by 61 publications

(30 citation statements)

References 100 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The learning process should provide benefits for students to fully develop their capabilities (Skuballa, et al, 2018). Science is a substantial component to improve a critical thinking society (Perconti & Plebe, 2020). Students who master the concept of biology will always support the problem-solving efforts in their surrounding environment since concept mastery is the foundation for a network of ideas that guides someone's way of thinking (Chen, et al, 2020).…”

Section: Resultsmentioning

confidence: 99%

Analysis of the Relationship Between Concept Mastery and Problem-Solving Skills of Pre-Service Biology Teachers in Human Physiology Courses

Amanda

Sumitro

Lestari

et al. 2021

JPSI

View full text Add to dashboard Cite

21st century learning focuses on problem-solving skills. A higher level of education requires an understanding of a more systematic concept to elaborate problems. Problem-solving skill is one of the fundamental cognitive processes. It involves higher order thinking to discover solutions or ideas. This research aims to analyze the relationship between concept mastery and problem-solving skill of pre-service biology teacher in human physiology courses. This is descriptive correlational research conducted in Sulthan Thaha Saifuddin State Islamic University Jambi. The sample was selected using the purposive sampling technique. Respondents in this study were 33 students in semester VI. The instrument used in the study was an essay test of concept mastery integrated with problem-solving. The results showed that the average scores of the students' concept mastery and problem-solving were 56.8 and 58.0, respectively. Both included in the poor category. It also showed that there was a relationship between students' concept mastery and problem-solving skill. The correlation value was 0.76, with a significance value of p0.05; therefore, it included in the strong category.

show abstract

Section: Resultsmentioning

confidence: 99%

Analysis of the Relationship Between Concept Mastery and Problem-Solving Skills of Pre-Service Biology Teachers in Human Physiology Courses

Amanda

Sumitro

Lestari

et al. 2021

JPSI

View full text Add to dashboard Cite

show abstract

“…More recently, however, with the success of deep neural networks, things seem to have changed again and the initial opportunistic attitude seems to be back in vogue again. The resonance of the successes of deep learning has sparked intense reflections and discussions within the cognitive sciences and philosophy [9,[22][23][24][25][26] and the analogy between the biological brain and the artificial cognitive models has been even more heavily questioned, mainly because of the persistent opacity of such models [8,15]. Yet deep learning is by no means a perspective that conflicts with the idea of designing a certain cognitive architecture in a biologically inspired way.…”

Section: Incommensurable Cognitive Modelsmentioning

confidence: 99%

How Neurons in Deep Models Relate with Neurons in the Brain

Pavone

Plebe

2021

Algorithms

Self Cite

View full text Add to dashboard Cite

In dealing with the algorithmic aspects of intelligent systems, the analogy with the biological brain has always been attractive, and has often had a dual function. On the one hand, it has been an effective source of inspiration for their design, while, on the other hand, it has been used as the justification for their success, especially in the case of Deep Learning (DL) models. However, in recent years, inspiration from the brain has lost its grip on its first role, yet it continues to be proposed in its second role, although we believe it is also becoming less and less defensible. Outside the chorus, there are theoretical proposals that instead identify important demarcation lines between DL and human cognition, to the point of being even incommensurable. In this article we argue that, paradoxically, the partial indifference of the developers of deep neural models to the functioning of biological neurons is one of the reasons for their success, having promoted a pragmatically opportunistic attitude. We believe that it is even possible to glimpse a biological analogy of a different kind, in that the essentially heuristic way of proceeding in modern DL development bears intriguing similarities to natural evolution.

show abstract

“…In recent years, with the deepening of deep learning research, deep learning methods have proven to be quite successful in various pattern recognition and remote sensing image processing tasks [31][32][33]. As far as the processing of remote sensing images (HR/VHR remote sensing images, SAR images) is concerned, the deep learning method is more capable of capturing various spectral, spatial, and temporal features in the images, deeply mining high-level semantic features and understanding abstract expressions in high-dimensional features [6,11,34].…”

Section: Introductionmentioning

confidence: 99%

A Novel Squeeze-and-Excitation W-Net for 2D and 3D Building Change Detection with Multi-Source and Multi-Feature Remote Sensing Data

Zhang

Wang

et al. 2021

Remote Sensing

View full text Add to dashboard Cite

Building Change Detection (BCD) is one of the core issues in earth observation and has received extensive attention in recent years. With the rapid development of earth observation technology, the data source of remote sensing change detection is continuously enriched, which provides the possibility to describe the spatial details of the ground objects more finely and to characterize the ground objects with multiple perspectives and levels. However, due to the different physical mechanisms of multi-source remote sensing data, BCD based on heterogeneous data is a challenge. Previous studies mostly focused on the BCD of homogeneous remote sensing data, while the use of multi-source remote sensing data and considering multiple features to conduct 2D and 3D BCD research is sporadic. In this article, we propose a novel and general squeeze-and-excitation W-Net, which is developed from U-Net and SE-Net. Its unique advantage is that it can not only be used for BCD of homogeneous and heterogeneous remote sensing data respectively but also can input both homogeneous and heterogeneous remote sensing data for 2D or 3D BCD by relying on its bidirectional symmetric end-to-end network architecture. Moreover, from a unique perspective, we use image features that are stable in performance and less affected by radiation differences and temporal changes. We innovatively introduced the squeeze-and-excitation module to explicitly model the interdependence between feature channels so that the response between the feature channels is adaptively recalibrated to improve the information mining ability and detection accuracy of the model. As far as we know, this is the first proposed network architecture that can simultaneously use multi-source and multi-feature remote sensing data for 2D and 3D BCD. The experimental results in two 2D data sets and two challenging 3D data sets demonstrate that the promising performances of the squeeze-and-excitation W-Net outperform several traditional and state-of-the-art approaches. Moreover, both visual and quantitative analyses of the experimental results demonstrate competitive performance in the proposed network. This demonstrates that the proposed network and method are practical, physically justified, and have great potential application value in large-scale 2D and 3D BCD and qualitative and quantitative research.

show abstract

Deep learning and cognitive science

Cited by 61 publications

References 100 publications

Analysis of the Relationship Between Concept Mastery and Problem-Solving Skills of Pre-Service Biology Teachers in Human Physiology Courses

Analysis of the Relationship Between Concept Mastery and Problem-Solving Skills of Pre-Service Biology Teachers in Human Physiology Courses

How Neurons in Deep Models Relate with Neurons in the Brain

A Novel Squeeze-and-Excitation W-Net for 2D and 3D Building Change Detection with Multi-Source and Multi-Feature Remote Sensing Data

Contact Info

Product

Resources

About