Browse
Submit Data
Databases
API
Help

Dataset Information

7 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

A Database for Learning Numbers by Visual Finger Recognition in Developmental Neuro-Robotics

ABSTRACT: Numerical cognition is a fundamental component of human intelligence that has not been fully understood yet. Indeed, it is a subject of research in many disciplines, e.g., neuroscience, education, cognitive and developmental psychology, philosophy of mathematics, linguistics. In Artificial Intelligence, aspects of numerical cognition have been modelled through neural networks to replicate and analytically study children behaviours. However, artificial models need to incorporate realistic sensory-motor information from the body to fully mimic the children's learning behaviours, e.g., the use of fingers to learn and manipulate numbers. To this end, this article presents a database of images, focused on number representation with fingers using both human and robot hands, which can constitute the base for building new realistic models of numerical cognition in humanoid robots, enabling a grounded learning approach in developmental autonomous agents. The article provides a benchmark analysis of the datasets in the database that are used to train, validate, and test five state-of-the art deep neural networks, which are compared for classification accuracy together with an analysis of the computational requirements of each network. The discussion highlights the trade-off between speed and precision in the detection, which is required for realistic applications in robotics.

SUBMITTER: Davies S

PROVIDER: S-EPMC7960766 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Json Xml

Similar Datasets

Zinc Finger Proteins in Neuro-Related Diseases Progression.

Project description:Zinc finger proteins (ZNF) are among the most abundant proteins in eukaryotic genomes. It contains several zinc finger domains that can selectively bind to certain DNA or RNA and associate with proteins, therefore, ZNF can regulate gene expression at the transcriptional and translational levels. In terms of neurological diseases, numerous studies have shown that many ZNF are associated with neurological diseases. The purpose of this review is to summarize the types and roles of ZNF in neuropsychiatric disorders. We will describe the structure and classification of ZNF, then focus on the pathophysiological role of ZNF in neuro-related diseases and summarize the mechanism of action of ZNF in neuro-related diseases.

| S-EPMC8637543 | biostudies-literature

Category learning induces position invariance of pattern recognition across the visual field.

Project description:Human object recognition is considered to be largely invariant to translation across the visual field. However, the origin of this invariance to positional changes has remained elusive, since numerous studies found that the ability to discriminate between visual patterns develops in a largely location-specific manner, with only a limited transfer to novel visual field positions. In order to reconcile these contradicting observations, we traced the acquisition of categories of unfamiliar grey-level patterns within an interleaved learning and testing paradigm that involved either the same or different retinal locations. Our results show that position invariance is an emergent property of category learning. Pattern categories acquired over several hours at a fixed location in either the peripheral or central visual field gradually become accessible at new locations without any position-specific feedback. Furthermore, categories of novel patterns presented in the left hemifield are distinctly faster learnt and better generalized to other locations than those learnt in the right hemifield. Our results suggest that during learning initially position-specific representations of categories based on spatial pattern structure become encoded in a relational, position-invariant format. Such representational shifts may provide a generic mechanism to achieve perceptual invariance in object recognition.

| S-EPMC2596832 | biostudies-other

Adults' visual recognition of actions simulations by finger gestures (ASFGs) produced by sighted and blind individuals.

Project description:The present study examines the visual recognition of action simulations by finger gestures (ASFGs) produced by sighted and blind individuals. In ASFGs, fingers simulate legs to represent actions such as jumping, spinning, climbing, etc. The question is to determine whether the common motor experience of one's own body is sufficient to produce adequate ASFGs or whether the possibility to see gestures from others are also necessary to do it. Three experiments were carried out to address this question. Experiment 1 examined in 74 sighted adults the recognition of 18 types of ASFGs produced by 20 blindfolded sighted adults. Results showed that rates of correct recognition were globally very high, but varied with the type of ASFG. Experiment 2 studied in 91 other sighted adults the recognition of ASFGs produced by 10 early blind and 7 late blind adults. Results also showed a high level of recognition with a similar order of recognizability by type of ASFG. However, ASFGs produced by early blind individuals were more poorly recognized than those produced by late blind individuals. In order to match data of recognition obtained with the form that gestures are produced by individuals, two independant judges evaluated prototypical and atypical attributes of ASFG produced by blindfolded sighted, early blind and late blind individuals in Experiment 3. Results revealed the occurrence of more atypical attributes in ASFG produced by blind individuals: their ASFGs transpose more body movements from a character-viewpoint in less agreement with visual rules. The practical interest of the study relates to the relevance of including ASFGs as a new exploratory procedure in tactile devices which are more apt to convey action concepts to blind users/readers.

| S-EPMC6438591 | biostudies-literature

Hazards&Robots: A dataset for visual anomaly detection in robotics.

Project description:We propose Hazards&Robots, a dataset for Visual Anomaly Detection in Robotics. The dataset is composed of 324,408 RGB frames, and corresponding feature vectors; it contains 145,470 normal frames and 178,938 anomalous ones categorized in 20 different anomaly classes. The dataset can be used to train and test current and novel visual anomaly detection methods such as those based on deep learning vision models. The data is recorded with a DJI Robomaster S1 front facing camera. The ground robot, controlled by a human operator, traverses university corridors. Considered anomalies include presence of humans, unexpected objects on the floor, defects to the robot. Preliminary versions of the dataset are used in [1,3]. This version is available at [12].

| S-EPMC10294035 | biostudies-literature

Bootstrapping Virtual Bipedal Walkers with Robotics Scaffolded Learning.

Project description:We reach walking optimality from a very early age by using natural supports, which can be the hands of our parents, chairs, and training wheels, and bootstrap a new knowledge from the recently acquired one. The idea behind bootstrapping is to use the previously acquired knowledge from simpler tasks to accelerate the learning of more complicated ones. In this paper, we propose a scaffolded learning method from an evolutionary perspective, where a biped creature achieves stable and independent bipedal walking while exploiting the natural scaffold of its changing morphology to create a third limb. The novelty of this work is speeding up the learning process with an artificially recreated scaffolded learning. We compare three conditions of scaffolded learning (free, time-constrained, and performance-based scaffolded learning) to reach bipedalism, and we prove that a performance-based scaffold, which is designed by the walking velocity obtained, is the most conducive to bootstrap the learning of bipedal walking. The scope of this work is not to study bipedal locomotion but to investigate the contribution from scaffolded learning to a faster learning process. Beyond a pedagogical experiment, this work presents a powerful tool to accelerate the learning of complex tasks in the Robotics field.

| S-EPMC8456033 | biostudies-literature

A Differentiable Physics Engine for Deep Learning in Robotics.

Project description:An important field in robotics is the optimization of controllers. Currently, robots are often treated as a black box in this optimization process, which is the reason why derivative-free optimization methods such as evolutionary algorithms or reinforcement learning are omnipresent. When gradient-based methods are used, models are kept small or rely on finite difference approximations for the Jacobian. This method quickly grows expensive with increasing numbers of parameters, such as found in deep learning. We propose the implementation of a modern physics engine, which can differentiate control parameters. This engine is implemented for both CPU and GPU. Firstly, this paper shows how such an engine speeds up the optimization process, even for small problems. Furthermore, it explains why this is an alternative approach to deep Q-learning, for using deep learning in robotics. Finally, we argue that this is a big step for deep learning in robotics, as it opens up new possibilities to optimize robots, both in hardware and software.

| S-EPMC6416213 | biostudies-other

Dynamic recognition and mirage using neuro-metamaterials.

Project description:Breakthroughs in the field of object recognition facilitate ubiquitous applications in the modern world, ranging from security and surveillance equipment to accessibility devices for the visually impaired. Recently-emerged optical computing provides a fundamentally new computing modality to accelerate its solution with photons; however, it still necessitates digital processing for in situ application, inextricably tied to Moore's law. Here, from an entirely optical perspective, we introduce the concept of neuro-metamaterials that can be applied to realize a dynamic object- recognition system. The neuro-metamaterials are fabricated from inhomogeneous metamaterials or transmission metasurfaces, and optimized using, such as topology optimization and deep learning. We demonstrate the concept in experiments where living rabbits play freely in front of the neuro-metamaterials, which enable to perceive in light speed the rabbits' representative postures. Furthermore, we show how this capability enables a new physical mechanism for creating dynamic optical mirages, through which a sequence of rabbit movements is converted into a holographic video of a different animal. Our work provides deep insight into how metamaterials could facilitate a myriad of in situ applications, such as illusive cloaking and speed-of-light information display, processing, and encryption, possibly ushering in an "Optical Internet of Things" era.

| S-EPMC9110342 | biostudies-literature

Computational Optimization of Image-Based Reinforcement Learning for Robotics.

Project description:The robotics field has been deeply influenced by the advent of deep learning. In recent years, this trend has been characterized by the adoption of large, pretrained models for robotic use cases, which are not compatible with the computational hardware available in robotic systems. Moreover, such large, computationally intensive models impede the low-latency execution which is required for many closed-loop control systems. In this work, we propose different strategies for improving the computational efficiency of the deep-learning models adopted in reinforcement-learning (RL) scenarios. As a use-case project, we consider an image-based RL method on the synergy between push-and-grasp actions. As a first optimization step, we reduce the model architecture in complexity, by decreasing the number of layers and by altering the architecture structure. Second, we consider downscaling the input resolution to reduce the computational load. Finally, we perform weight quantization, where we compare post-training quantization and quantized-aware training. We benchmark the improvements introduced in each optimization by running a standard testing routine. We show that the optimization strategies introduced can improve the computational efficiency by around 300 times, while also slightly improving the functional performance of the system. In addition, we demonstrate closed-loop control behaviour on a real-world robot, while processing everything on a Jetson Xavier NX edge device.

| S-EPMC9571553 | biostudies-literature

Developmental Prosopagnosia and Elastic Versus Static Face Recognition in an Incidental Learning Task.

Project description:Previous research on the beneficial effect of motion has postulated that learning a face in motion provides additional cues to recognition. Surprisingly, however, few studies have examined the beneficial effect of motion in an incidental learning task and developmental prosopagnosia (DP) even though such studies could provide more valuable information about everyday face recognition compared to the perception of static faces. In the current study, 18 young adults (Experiment 1) and five DPs and 10 age-matched controls (Experiment 2) participated in an incidental learning task during which both static and elastically moving unfamiliar faces were sequentially presented and were to be recognized in a delayed visual search task during which the faces could either keep their original presentation or switch (from static to elastically moving or vice versa). In Experiment 1, performance in the elastic-elastic condition reached a significant improvement relative to the elastic-static and static-elastic condition, however, no significant difference could be detected relative to the static-static condition. Except for higher scores in the elastic-elastic compared to the static-elastic condition in the age-matched group, no other significant differences were detected between conditions for both the DPs and the age-matched controls. The current study could not provide compelling evidence for a general beneficial effect of motion. Age-matched controls performed generally worse than DPs, which may potentially be explained by their higher rates of false alarms. Factors that could have influenced the results are discussed.

| S-EPMC7488957 | biostudies-literature

The visual magnocellular-dorsal dysfunction in Chinese children with developmental dyslexia impedes Chinese character recognition.

Project description:The visual magnocellular-dorsal (M-D) deficit theory of developmental dyslexia (DD) is still highly debated. Many researchers have made great efforts to investigate the relationship between M-D dysfunction and reading disability. Given that visual analysis plays an important role in Chinese reading, the present study tried to examine how the M-D dysfunction affected Chinese character recognition in Chinese children with DD. Sixteen DD children with M-D deficit, fifteen DD children with normal M-D function and twenty-seven age-matched typically developing children participated in this study. A global/local decision task was adopted, in which we manipulated the spatial frequency of target characters to separate an M-D condition from an unfiltered condition. Results of reaction times and error rates showed that in the M-D condition both M-D normal dyslexics and controls exhibited a significant global precedence effect, with faster responses and lower error rates in global decision than in local decision. In contrast, this global advantage was absent for the M-D impaired dyslexics. Accordingly, we propose that the M-D impairment present in some but not all dyslexics might influence global recognition of Chinese characters in this subgroup of children with DD, which might be implicated in their difficulties in learning to read.

| S-EPMC4238300 | biostudies-other

OmicsDI is part of the ELIXIR infrastructure

OmicsDI is an Elixir interoperability service. Learn more ›

Tweets

OmicsDI Databases

PRIDE
PeptideAtlas
MassIVE
JPOST Repository
Physiome Model Repository

EGA
EVA
ENA
LINCS
PAXDB
Cell Collective

MetaboLights
Metabolomics Workbench
MetabolomeExpress
GNPS
BioModels
FAIRDOMHub

ArrayExpress
dbGaP
ExpressionAtlas
GEO
NODE

Information

Databases
Help
API
Contact us
Code on GitHub
Terms of use
Submit Data